SU\G(𝔸)/K·U
Sign Up for free Log In

Author Description

Login to generate an author description

Ask a Question About This Mathematician

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

2017-07-01
Jonathan Huang , Vivek Rathod , Chen Sun +7 more
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this … The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-toapples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We present a unified implementation of the Faster R-CNN [30], R-FCN [6] and SSD [25] systems, which we view as meta-architectures and trace out the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures. On one extreme end of this spectrum where speed and memory are critical, we present a detector that achieves real time speeds and can be deployed on a mobile device. On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.
View PDF Chat

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

2017-10-01
Chen Sun , Abhinav Shrivastava , Saurabh Singh +1 more
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there … The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10 × or 100 × ? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between 'enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pre-training) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-the-art results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.
View PDF Chat

ViViT: A Video Vision Transformer

2021-10-01
Anurag Arnab , Mostafa Dehghani , Georg Heigold +3 more
We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatiotemporal tokens from the input video, which are … We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatiotemporal tokens from the input video, which are then encoded by a series of transformer layers. In order to handle the long sequences of tokens encountered in video, we propose several, efficient variants of our model which factorise the spatial- and temporal-dimensions of the input. Although transformer-based models are known to only be effective when large training datasets are available, we show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple video classification benchmarks including Kinetics 400 and 600, Epic Kitchens, Something-Something v2 and Moments in Time, outperforming prior methods based on deep 3D convolutional networks.
View PDF Chat

The iNaturalist Species Classification and Detection Dataset

2018-06-01
Grant Van Horn , Oisin Mac Aodha , Yang Song +6 more
Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. In contrast, the natural world is heavily imbalanced, as some species … Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. In contrast, the natural world is heavily imbalanced, as some species are more abundant and easier to photograph than others. To encourage further progress in challenging real world conditions we present the iNaturalist species classification and detection dataset, consisting of 859,000 images from over 5,000 different species of plants and animals. It features visually similar species, captured in a wide variety of situations, from all over the world. Images were collected with different camera types, have varying image quality, feature a large class imbalance, and have been verified by multiple citizen scientists. We discuss the collection of the dataset and present extensive baseline experiments using state-of-the-art computer vision classification and detection models. Results show that current non-ensemble based methods achieve only 67% top one classification accuracy, illustrating the difficulty of the dataset. Specifically, we observe poor results for classes with small numbers of training examples suggesting more attention is needed in low-shot learning.
View PDF Chat

VideoBERT: A Joint Model for Video and Language Representation Learning

2019-10-01
Chen Sun , Austin Myers , Carl Vondrick +2 more
Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic … Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respectively. We use VideoBERT in numerous tasks, including action classification and video captioning. We show that it can be applied directly to open-vocabulary classification, and confirm that large amounts of training data and cross-modal information are critical to performance. Furthermore, we outperform the state-of-the-art on video captioning, and quantitative results verify that the model learns high-level semantic features.
View PDF Chat

What Makes for Good Views for Contrastive Learning?

2020-01-01
Yonglong Tian , Chen Sun , Ben Poole +3 more
Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different … Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less studied. In this paper, we use theoretical and empirical analysis to better understand the importance of view selection, and argue that we should reduce the mutual information (MI) between views while keeping task-relevant information intact. To verify this hypothesis, we devise unsupervised and semi-supervised frameworks that learn effective views by aiming to reduce their MI. We also consider data augmentation as a way to reduce MI, and show that increasing data augmentation indeed leads to decreasing MI and improves downstream classification accuracy. As a by-product, we achieve a new state-of-the-art accuracy on unsupervised pre-training for ImageNet classification ($73\%$ top-1 linear readout with a ResNet-50). In addition, transferring our models to PASCAL VOC object detection and COCO instance segmentation consistently outperforms supervised pre-training. Code:http://github.com/HobbitLong/PyContrast

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

2018-06-01
Yin Cui , Yang Song , Chen Sun +2 more
Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make … Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make & model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets.
View PDF Chat

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

2017-10-01
Jiyang Gao , Zhenheng Yang , Chen Sun +2 more
Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale … Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale video analysis. We propose a novel Temporal Unit Regression Network (TURN) model. There are two salient aspects of TURN: (1) TURN jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression: (2) Fast computation is enabled by unit feature reuse: a long untrimmed video is decomposed into video units, which are reused as basic building blocks of temporal proposals. TURN outperforms the previous state-of-the-art methods under average recall (AR) by a large margin on THUMOS-14 and ActivityNet datasets, and runs at over 880 frames per second (FPS) on a TITAN X GPU. We further apply TURN as a proposal generation stage for existing temporal action localization pipelines, it outperforms state-of-the-art performance on THUMOS-14 and ActivityNet.
View PDF Chat

Composing Text and Image for Image Retrieval - an Empirical Odyssey

2019-06-01
Nam Vo , Lu Jiang , Chen Sun +4 more
In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to … In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to the input image. For example, we may present an image of the Eiffel tower, and ask the system to find images which are visually similar, but are modified in small ways, such as being taken at nighttime instead of during the day. o tackle this task, we embed the query (reference image plus modification text) and the target (images). The encoding function of the image text query learns a representation, such that the similarity with the target image representation is high iff it is a ``positive match''. We propose a new way to combine image and text through residual connection, that is designed for this retrieval task. We show this outperforms existing approaches on 3 different datasets, namely Fashion-200k, MIT-States and a new synthetic dataset we create based on CLEVR. We also show that our approach can be used to perform image classification with compositionally novel labels, and we outperform previous methods on MIT-States on this task.
View PDF Chat

Attention Bottlenecks for Multimodal Fusion

2021-01-01
Arsha Nagrani , Shan Yang , Anurag Arnab +3 more
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised … Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-attention, our model forces information between different modalities to pass through a small number of bottleneck latents, requiring the model to collate and condense the most relevant information in each modality and only share what is necessary. We find that such a strategy improves fusion performance, at the same time reducing computational cost. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks including Audioset, Epic-Kitchens and VGGSound. All code and models will be released.
View PDF Chat

Learning Video Representations using Contrastive Bidirectional Transformer

2019-01-01
Chen Sun , Fabien Baradel , Kevin Murphy +1 more
This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. … This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our method extends the BERT model for text sequences to the case of sequences of real-valued feature vectors, by replacing the softmax loss with noise contrastive estimation (NCE). We also show how to learn representations from sequences of visual features and sequences of words derived from ASR (automatic speech recognition), and show that such cross-modal training (when possible) helps even more.
View PDF Chat

Multiview Transformers for Video Recognition

2022-06-01
Yan Shen , Xuehan Xiong , Anurag Arnab +4 more
Video understanding requires reasoning at multiple spatiotemporal resolutions – from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art, they have … Video understanding requires reasoning at multiple spatiotemporal resolutions – from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art, they have not explicitly modelled different spatiotemporal resolutions. To this end, we present Multiview Transformers for Video Recognition (MTV). Our model consists of separate encoders to represent different views of the input video with lateral connections to fuse information across views. We present thorough ablation studies of our model and show that MTV consistently performs better than single-view counterparts in terms of accuracy and computational cost across a range of model sizes. Furthermore, we achieve state-of-the-art results on six standard datasets, and improve even further with large-scale pretraining. Code and checkpoints are available at: https://github.com/google-research/scenic.
View PDF Chat

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

2017-01-01
Chen Sun , Abhinav Shrivastava , Saurabh Singh +1 more
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there … The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10x or 100x? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between `enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pre-training) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-the-art results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.
View PDF Chat

D3D: Distilled 3D Networks for Video Action Recognition

2020-03-01
Jonathan Stroud , David A. Ross , Chen Sun +2 more
State-of-the-art methods for action recognition commonly use two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent … State-of-the-art methods for action recognition commonly use two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent work, both streams are 3D Convolutional Neural Networks, which use spatiotemporal filters. These filters can respond to motion, and therefore should allow the network to learn motion representations, removing the need for optical flow. However, we still see significant benefits in performance by feeding optical flow into the temporal stream, indicating that the spatial stream is "missing" some of the signal that the temporal stream captures. In this work, we first investigate whether motion representations are indeed missing in the spatial stream, and show that there is significant room for improvement. Second, we demonstrate that these motion representations can be improved using distillation, that is, by tuning the spatial stream to mimic the temporal stream, effectively combining both models into a single stream. Finally, we show that our Distilled 3D Network (D3D) achieves performance on par with the two-stream approach, with no need to compute optical flow during inference.
View PDF Chat

Speed/accuracy trade-offs for modern convolutional object detectors

2016-01-01
Jonathan Huang , Vivek Rathod , Chen Sun +7 more
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this … The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-to-apples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We present a unified implementation of the Faster R-CNN [Ren et al., 2015], R-FCN [Dai et al., 2016] and SSD [Liu et al., 2015] systems, which we view as "meta-architectures" and trace out the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures. On one extreme end of this spectrum where speed and memory are critical, we present a detector that achieves real time speeds and can be deployed on a mobile device. On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.
View PDF Chat

VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

2017-10-01
Chuang Gan , Yandong Li , Haoxiang Li +2 more
Rich and dense human labeled datasets are among the main enabling factors for the recent advance on visionlanguage understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering … Rich and dense human labeled datasets are among the main enabling factors for the recent advance on visionlanguage understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering (VQA)) are inherently connected in that they reveal different levels and perspectives of human understandings about the same visual scenes — and even the same set of images (e.g., of COCO). The popularity of COCO correlates those annotations and tasks. Explicitly linking them up may significantly benefit both individual tasks and the unified vision and language modeling.,,We present the preliminary work of linking the instance segmentations provided by COCO to the questions and answers (QAs) in the VQA dataset, and name the collected links visual questions and segmentation answers (VQS). They transfer human supervision between the previously separate tasks, offer more effective leverage to existing problems, and also open the door for new research problems and models. We study two applications of the VQS data in this paper: supervised attention for VQA and a novel question-focused semantic segmentation task. For the former, we obtain state-of-the-art results on the VQA real multiple-choice task by simply augmenting the multilayer perceptrons with some attention features that are learned using the segmentation-QA links as explicit supervision. To put the latter in perspective, we study two plausible methods and compare them to an oracle method assuming that the instance segmentations are given at the test stage.
View PDF Chat

Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images

2015-10-13
Chen Sun , Sanketh Shetty , Rahul Sukthankar +1 more
We address the problem of fine-grained action localization from temporally untrimmed web videos. We assume that only weak video-level annotations are available for training. The goal is to use these … We address the problem of fine-grained action localization from temporally untrimmed web videos. We assume that only weak video-level annotations are available for training. The goal is to use these weak labels to identify temporal segments corresponding to the actions, and learn models that generalize to unconstrained web videos. We find that web images queried by action names serve as well-localized highlights for many actions, but are noisily labeled. To solve this problem, we propose a simple yet effective method that takes weak video labels and noisy image labels as input, and generates localized action frames as output. This is achieved by cross-domain transfer between video frames and web images, using pre-trained deep convolutional neural networks. We then use the localized action frames to train action recognition models with long short-term memory networks. We collect a fine-grained sports action data set FGA-240 of more than 130,000 YouTube videos. It has 240 fine-grained actions under 85 sports activities. Convincing results are shown on the FGA-240 data set, as well as the THUMOS 2014 localization data set with untrimmed training videos.
View PDF Chat

Episodic Transformer for Vision-and-Language Navigation

2021-10-01
Alexander Pashevich , Cordelia Schmid , Chen Sun
Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and … Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and understanding complex human instructions. We propose Episodic Transformer (E.T.), a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions. To improve training, we leverage synthetic instructions as an intermediate representation that decouples understanding the visual appearance of an environment from the variations of natural language instructions. We demonstrate that encoding the history with a transformer is critical to solve compositional tasks, and that pretraining and joint training with synthetic instructions further improve the performance. Our approach sets a new state of the art on the challenging ALFRED benchmark, achieving 38.4% and 8.5% task success rates on seen and unseen test splits.
View PDF Chat

Relational Action Forecasting

2019-06-01
Chen Sun , Abhinav Shrivastava , Carl Vondrick +3 more
This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions … This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions for the next T frames. Our approach jointly models temporal and spatial interactions among different actors by constructing a recurrent graph, using actor proposals obtained with Faster R-CNN as nodes. Our method learns to select a subset of discriminative relations without requiring explicit supervision, thus enabling us to tackle challenging visual data. We refer to our model as Discriminative Relational Recurrent Network (DRRN). Evaluation of action prediction on AVA demonstrates the effectiveness of our proposed method compared to simpler baselines. Furthermore, we significantly improve performance on the task of early action classification on J-HMDB, from the previous SOTA of 48% to 60%.
View PDF Chat

ViViT: A Video Vision Transformer

2021-03-29
Anurag Arnab , Mostafa Dehghani , Georg Heigold +3 more
We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are … We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of transformer layers. In order to handle the long sequences of tokens encountered in video, we propose several, efficient variants of our model which factorise the spatial- and temporal-dimensions of the input. Although transformer-based models are known to only be effective when large training datasets are available, we show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple video classification benchmarks including Kinetics 400 and 600, Epic Kitchens, Something-Something v2 and Moments in Time, outperforming prior methods based on deep 3D convolutional networks. To facilitate further research, we will release code and models.

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

2017-01-01
Jiyang Gao , Zhenheng Yang , Chen Sun +2 more
Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale … Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale video analysis. We propose a novel Temporal Unit Regression Network (TURN) model. There are two salient aspects of TURN: (1) TURN jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression; (2) Fast computation is enabled by unit feature reuse: a long untrimmed video is decomposed into video units, which are reused as basic building blocks of temporal proposals. TURN outperforms the state-of-the-art methods under average recall (AR) by a large margin on THUMOS-14 and ActivityNet datasets, and runs at over 880 frames per second (FPS) on a TITAN X GPU. We further apply TURN as a proposal generation stage for existing temporal action localization pipelines, it outperforms state-of-the-art performance on THUMOS-14 and ActivityNet.

ProNet: Learning to Propose Object-Specific Boxes for Cascaded Neural Networks

2016-06-01
Chen Sun , Manohar Paluri , Ronan Collobert +2 more
This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and … This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and in different scales. In this paper, we propose a novel classification architecture ProNet based on convolutional neural networks. It uses computationally efficient neural networks to propose image regions that are likely to contain objects, and applies more powerful but slower networks on the proposed regions. The basic building block is a multi-scale fully-convolutional network which assigns object confidence scores to boxes at different locations and scales. We show that such networks can be trained effectively using image-level annotations, and can be connected into cascades or trees for efficient object classification. ProNet outperforms previous state-of-the-art significantly on PASCAL VOC 2012 and MS COCO datasets for object classification and point-based localization.
View PDF Chat

Speech2Action: Cross-Modal Supervision for Action Recognition

2020-06-01
Arsha Nagrani , Chen Sun , David A. Ross +3 more
Is it possible to guess human action from dialogue alone? In this work we investigate the link between spoken words and actions in movies. We note that movie screenplays describe … Is it possible to guess human action from dialogue alone? In this work we investigate the link between spoken words and actions in movies. We note that movie screenplays describe actions, as well as contain the speech of characters and hence can be used to learn this correlation with no additional supervision. We train a BERT-based Speech2Action classifier on over a thousand movie screenplays, to predict action labels from transcribed speech segments. We then apply this model to the speech segments of a large unlabelled movie corpus (188M speech segments from 288K movies). Using the predictions of this model, we obtain weak action labels for over 800K video clips. By training on these video clips, we demonstrate superior action recognition performance on standard action recognition benchmarks, without using a single manually labelled action example.
View PDF Chat

Learning Audio-Video Modalities from Image Captions

2022-01-01
Arsha Nagrani , Paul Hongsuck Seo , Bryan Seybold +4 more
View PDF Chat

TALL: Temporal Activity Localization via Language Query

2017-01-01
Jiyang Gao , Chen Sun , Zhenheng Yang +1 more
This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. … This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. However, activities in the wild consist of a wide combination of actors, actions and objects; it is difficult to design a proper activity list that meets users' needs. We propose to localize activities by natural language queries. Temporal Activity Localization via Language (TALL) is challenging as it requires: (1) suitable design of text and video representations to allow cross-modal matching of actions and language queries; (2) ability to locate actions accurately given features from sliding windows of limited granularity. We propose a novel Cross-modal Temporal Regression Localizer (CTRL) to jointly model text query and video clips, output alignment scores and action boundary regression results for candidate clips. For evaluation, we adopt TaCoS dataset, and build a new dataset for this task on top of Charades by adding sentence temporal annotations, called Charades-STA. We also build complex sentence queries in Charades-STA for test. Experimental results show that CTRL outperforms previous methods significantly on both datasets.
View PDF Chat

Unified Graph Structured Models for Video Understanding

2021-10-01
Anurag Arnab , Chen Sun , Cordelia Schmid
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network … Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly models these spatio-temporal relations and can use explicit representations of objects, when supervision is available, and implicit representations otherwise. Our formulation generalises previous structured models for video understanding, and allows us to study how different design choices in graph structure and representation affect the model’s performance. We demonstrate our method on two different tasks requiring relational reasoning in videos – spatio-temporal action detection on AVA and UCF101-24, and video scene graph classification on the recent Action Genome dataset – and achieve state-of-the-art results on all three datasets. Furthermore, we show quantitatively and qualitatively how our method is able to more effectively model relationships between relevant entities in the scene.
View PDF Chat

DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks.

2018-01-22
Unaiza Ahsan , Chen Sun , Irfan Essa
We propose an action recognition framework using Gen- erative Adversarial Networks. Our model involves train- ing a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without … We propose an action recognition framework using Gen- erative Adversarial Networks. Our model involves train- ing a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without la- bel information. Then we use the trained discriminator from the GAN model as an unsupervised pre-training step and fine-tune the trained discriminator model on a labeled dataset to recognize human activities. We determine good network architectural and hyperparameter settings for us- ing the discriminator from DCGAN as a trained model to learn useful representations for action recognition. Our semi-supervised framework using only appearance infor- mation achieves superior or comparable performance to the current state-of-the-art semi-supervised action recog- nition methods on two challenging video activity datasets: UCF101 and HMDB51.

Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos

2020-01-01
Anurag Arnab , Chen Sun , Arsha Nagrani +1 more
View PDF Chat

VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

2017-01-01
Chuang Gan , Yandong Li , Haoxiang Li +2 more
Rich and dense human labeled datasets are among the main enabling factors for the recent advance on vision-language understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering … Rich and dense human labeled datasets are among the main enabling factors for the recent advance on vision-language understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering (VQA)) are inherently connected in that they reveal different levels and perspectives of human understandings about the same visual scenes --- and even the same set of images (e.g., of COCO). The popularity of COCO correlates those annotations and tasks. Explicitly linking them up may significantly benefit both individual tasks and the unified vision and language modeling. We present the preliminary work of linking the instance segmentations provided by COCO to the questions and answers (QAs) in the VQA dataset, and name the collected links visual questions and segmentation answers (VQS). They transfer human supervision between the previously separate tasks, offer more effective leverage to existing problems, and also open the door for new research problems and models. We study two applications of the VQS data in this paper: supervised attention for VQA and a novel question-focused semantic segmentation task. For the former, we obtain state-of-the-art results on the VQA real multiple-choice task by simply augmenting the multilayer perceptrons with some attention features that are learned using the segmentation-QA links as explicit supervision. To put the latter in perspective, we study two plausible methods and compare them to an oracle method assuming that the instance segmentations are given at the test stage.
View PDF Chat

AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions

2017-01-01
Chunhui Gu , Chen Sun , David A. Ross +7 more
This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are … This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently. The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute video clips; (4) people temporally linked across consecutive segments; and (5) using movies to gather a varied set of action representations. This departs from existing datasets for spatio-temporal action recognition, which typically provide sparse annotations for composite actions in short video clips. We will release the dataset publicly. AVA, with its realistic scene and action complexity, exposes the intrinsic difficulty of action recognition. To benchmark this, we present a novel approach for action localization that builds upon the current state-of-the-art methods, and demonstrates better performance on JHMDB and UCF101-24 categories. While setting a new state of the art on existing datasets, the overall results on AVA are low at 15.6% mAP, underscoring the need for developing new approaches for video understanding.

Unsupervised Learning of Object Structure and Dynamics from Videos.

2019-06-19
Matthias Minderer , Chen Sun , Ruben Villegas +3 more
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn … Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics model of the keypoints. Future frames are reconstructed from the keypoints and a reference frame. By modeling dynamics in the keypoint coordinate space, we achieve stable learning and avoid compounding of errors in pixel space. Our method improves upon unstructured representations both for pixel-level video prediction and for downstream tasks requiring object-level understanding of motion dynamics. We evaluate our model on diverse datasets: a multi-agent sports dataset, the Human3.6M dataset, and datasets based on continuous control tasks from the DeepMind Control Suite. The spatially structured representation outperforms unstructured representations on a range of motion-related tasks such as object tracking, action recognition and reward prediction.

D3D: Distilled 3D Networks for Video Action Recognition

2018-12-19
Jonathan Stroud , David A. Ross , Chen Sun +2 more
State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow … State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent work, both of these streams consist of 3D Convolutional Neural Networks, which apply spatiotemporal filters to the video clip before performing classification. Conceptually, the temporal filters should allow the spatial stream to learn motion representations, making the temporal stream redundant. However, we still see significant benefits in action recognition performance by including an entirely separate temporal stream, indicating that the spatial stream is some of the signal captured by the temporal stream. In this work, we first investigate whether motion representations are indeed missing in the spatial stream of 3D CNNs. Second, we demonstrate that these motion representations can be improved by distillation, by tuning the spatial stream to predict the outputs of the temporal stream, effectively combining both models into a single stream. Finally, we show that our Distilled 3D Network (D3D) achieves performance on par with two-stream approaches, using only a single model and with no need to compute optical flow.

Automatic Concept Discovery from Parallel Text and Visual Corpora

2015-01-01
Chen Sun , Chuang Gan , Ram Nevatia
Humans connect language and vision to perceive the world. How to build a similar connection for computers? One possible way is via visual concepts, which are text terms that relate … Humans connect language and vision to perceive the world. How to build a similar connection for computers? One possible way is via visual concepts, which are text terms that relate to visually discriminative entities. We propose an automatic visual concept discovery algorithm using parallel text and visual corpora; it filters text terms based on the visual discriminative power of the associated images, and groups them into concepts using visual and semantic similarities. We illustrate the applications of the discovered concepts using bidirectional image and sentence retrieval task and image tagging task, and show that the discovered concepts not only outperform several large sets of manually selected concepts significantly, but also achieves the state-of-the-art performance in the retrieval task.
View PDF Chat

Composable Augmentation Encoding for Video Representation Learning

2021-10-01
Chen Sun , Arsha Nagrani , Yonglong Tian +1 more
We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, … We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data instances as negatives. These methods implicitly assume a set of representational invariances to the view selection mechanism (e.g., sampling frames with temporal shifts), which may lead to poor performance on downstream tasks which violate these invariances (fine-grained video action recognition that would benefit from temporal information). To overcome this limitation, we propose an 'augmentation aware' contrastive learning framework, where we explicitly provide a sequence of augmentation parameterisations (such as the values of the time shifts used to create data views) as composable augmentation encodings (CATE) to our model when projecting the video representations for contrastive learning. We show that representations learned by our method encode valuable information about specified spatial or temporal augmentation, and in doing so also achieve state-of-the-art performance on a number of video benchmarks.
View PDF Chat

Relational Action Forecasting

2019-01-01
Chen Sun , Abhinav Shrivastava , Carl Vondrick +3 more
This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions … This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions for the next T frames. Our approach jointly models temporal and spatial interactions among different actors by constructing a recurrent graph, using actor proposals obtained with Faster R-CNN as nodes. Our method learns to select a subset of discriminative relations without requiring explicit supervision, thus enabling us to tackle challenging visual data. We refer to our model as Discriminative Relational Recurrent Network (DRRN). Evaluation of action prediction on AVA demonstrates the effectiveness of our proposed method compared to simpler baselines. Furthermore, we significantly improve performance on the task of early action classification on J-HMDB, from the previous SOTA of 48% to 60%.
View PDF Chat

Affordance Learning In Direct Perception for Autonomous Driving

2019-01-01
Chen Sun , Jean Marie Uwabeza Vianney , Dongpu Cao
Recent development in autonomous driving involves high-level computer vision and detailed road scene understanding. Today, most autonomous vehicles are using mediated perception approach for path planning and control, which highly … Recent development in autonomous driving involves high-level computer vision and detailed road scene understanding. Today, most autonomous vehicles are using mediated perception approach for path planning and control, which highly rely on high-definition 3D maps and real time sensors. Recent research efforts aim to substitute the massive HD maps with coarse road attributes. In this paper, we follow the direct perception based method to train a deep neural network for affordance learning in autonomous driving. Our goal in this work is to develop the affordance learning model based on freely available Google Street View panoramas and Open Street Map road vector attributes. Driving scene understanding can be achieved by learning affordances from the images captured by car-mounted cameras. Such scene understanding by learning affordances may be useful for corroborating base maps such as HD maps so that the required data storage space is minimized and available for processing in real time. We compare capability in road attribute identification between human volunteers and our model by experimental evaluation. Our results indicate that this method could act as a cheaper way for training data collection in autonomous driving. The cross validation results also indicate the effectiveness of our model.

Learning Temporal Dynamics from Cycles in Narrated Video

2021-10-01
Dave Epstein , Jiajun Wu , Cordelia Schmid +1 more
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We introduce a self-supervised approach to this problem that solves … Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We introduce a self-supervised approach to this problem that solves a multi-modal temporal cycle consistency objective jointly in vision and language. This objective requires a model to learn modality-agnostic functions to predict the future and past that undo each other when composed. We hypothesize that a model trained on this objective will discover long-term temporal dynamics in video. We verify this hypothesis by using the resultant visual representations and predictive models as-is to solve a variety of downstream tasks. Our method outperforms state-of-the-art self-supervised video prediction methods on future action anticipation, temporal image ordering, and arrow-of-time classification tasks, without training on target datasets or their labels.
View PDF Chat

ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks

2015-01-01
Chen Sun , Manohar Paluri , Ronan Collobert +2 more
This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and … This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and in different scales. In this paper, we propose a novel classification architecture ProNet based on convolutional neural networks. It uses computationally efficient neural networks to propose image regions that are likely to contain objects, and applies more powerful but slower networks on the proposed regions. The basic building block is a multi-scale fully-convolutional network which assigns object confidence scores to boxes at different locations and scales. We show that such networks can be trained effectively using image-level annotations, and can be connected into cascades or trees for efficient object classification. ProNet outperforms previous state-of-the-art significantly on PASCAL VOC 2012 and MS COCO datasets for object classification and point-based localization.
View PDF Chat

ACD: Action Concept Discovery from Image-Sentence Corpora

2016-01-01
Jiyang Gao , Chen Sun , Ram Nevatia
Action classification in still images is an important task in computer vision. It is challenging as the appearances of ac- tions may vary depending on their context (e.g. associated objects). … Action classification in still images is an important task in computer vision. It is challenging as the appearances of ac- tions may vary depending on their context (e.g. associated objects). Manually labeling of context information would be time consuming and difficult to scale up. To address this challenge, we propose a method to automatically discover and cluster action concepts, and learn their classifiers from weakly supervised image-sentence corpora. It obtains candidate action concepts by extracting verb-object pairs from sentences and verifies their visualness with the associated images. Candidate action concepts are then clustered by using a multi-modal representation with image embeddings from deep convolutional networks and text embeddings from word2vec. More than one hundred human action concept classifiers are learned from the Flickr 30k dataset with no additional human effort and promising classification results are obtained. We further apply the AdaBoost algorithm to automatically select and combine relevant action concepts given an action query. Promising results have been shown on the PASCAL VOC 2012 action classification benchmark, which has zero overlap with Flickr30k.

Complex Event Recognition from Images with Few Training Examples

2017-01-17
Unaiza Ahsan , Chen Sun , James Hays +1 more
We propose to leverage concept-level representations for complex event recognition in photographs given limited training examples. We introduce a novel framework to discover event concept attributes from the web and … We propose to leverage concept-level representations for complex event recognition in photographs given limited training examples. We introduce a novel framework to discover event concept attributes from the web and use that to extract semantic features from images and classify them into social event categories with few training examples. Discovered concepts include a variety of objects, scenes, actions and event sub-types, leading to a discriminative and compact representation for event images. Web images are obtained for each discovered event concept and we use (pretrained) CNN features to train concept classifiers. Extensive experiments on challenging event datasets demonstrate that our proposed method outperforms several baselines using deep CNN features directly in classifying images into events with limited training examples. We also demonstrate that our method achieves the best overall accuracy on a dataset with unseen event categories using a single training example.

Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos

2020-07-21
Anurag Arnab , Chen Sun , Arsha Nagrani +1 more
Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this … Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present a spatio-temporal action recognition model that is trained with only video-level labels, which are significantly easier to annotate. Our method leverages per-frame person detectors which have been trained on large image datasets within a Multiple Instance Learning framework. We show how we can apply our method in cases where the standard Multiple Instance Learning assumption, that each bag contains at least one instance with the specified label, is invalid using a novel probabilistic variant of MIL where we estimate the uncertainty of each prediction. Furthermore, we report the first weakly-supervised results on the AVA dataset and state-of-the-art results among weakly-supervised methods on UCF101-24.

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

2018-01-01
Yin Cui , Yang Song , Chen Sun +2 more
Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make … Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make and model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets.
View PDF Chat

Anti-Disturbance Boundary Control for a Wave Equation With Input Disturbance

2022-11-03
Xiaoyang Wu , Yonghao Ma , Qiang Fu +3 more
In this article, we investigate the exponential stabilization issue of a wave equation with the external input disturbance, which is described by a nonlinear exogenous system. A novel disturbance observer … In this article, we investigate the exponential stabilization issue of a wave equation with the external input disturbance, which is described by a nonlinear exogenous system. A novel disturbance observer is constructed to estimate the unknown input disturbance. Then, based on the proposed disturbance observer, a boundary control strategy is developed to cancel the effect of disturbance and stabilize the system. The exponential stability is proven by employing the Lyapunov's direct method. This method can be extended to a class of flexible systems described by the hyperbolic partial differential equation met in the practical engineer area. The example of a nonuniform flexible string system is given, where the effectiveness of the proposed strategy is evaluated based on simulations.

Learning Temporal Dynamics from Cycles in Narrated Video

2021-01-01
Dave Epstein , Jiajun Wu , Cordelia Schmid +1 more
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal … Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal cycle consistency jointly in vision and language, training on narrated video. Our model learns modality-agnostic functions to predict forward and backward in time, which must undo each other when composed. This constraint leads to the discovery of high-level transitions between moments in time, since such transitions are easily inverted and shared across modalities. We justify the design of our model with an ablation study on different configurations of the cycle consistency problem. We then show qualitatively and quantitatively that our approach yields a meaningful, high-level model of the future and past. We apply the learned dynamics model without further training to various tasks, such as predicting future action and temporally ordering sets of images. Project page: https://dave.ml/mmcc
View PDF Chat

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

2024-10-17
Lijie Fan , Tianhong Li , Siyang Qin +6 more
Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, … Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether models use discrete or continuous tokens, and whether tokens are generated in a random or fixed raster order using BERT- or GPT-like transformer architectures. Our empirical results show that, while all models scale effectively in terms of validation loss, their evaluation performance -- measured by FID, GenEval score, and visual quality -- follows different trends. Models based on continuous tokens achieve significantly better visual quality than those using discrete tokens. Furthermore, the generation order and attention mechanisms significantly affect the GenEval score: random-order models achieve notably better GenEval scores compared to raster-order models. Inspired by these findings, we train Fluid, a random-order autoregressive model on continuous tokens. Fluid 10.5B model achieves a new state-of-the-art zero-shot FID of 6.16 on MS-COCO 30K, and 0.69 overall score on the GenEval benchmark. We hope our findings and results will encourage future efforts to further bridge the scaling gap between vision and language models.
View PDF Chat

Composing Text and Image for Image Retrieval - An Empirical Odyssey

2018-01-01
Nam Vo , Lu Jiang , Chen Sun +4 more
In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to … In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to the input image. For example, we may present an image of the Eiffel tower, and ask the system to find images which are visually similar but are modified in small ways, such as being taken at nighttime instead of during the day. To tackle this task, we learn a similarity metric between a target image and a source image plus source text, an embedding and composing function such that target image feature is close to the source image plus text composition feature. We propose a new way to combine image and text using such function that is designed for the retrieval task. We show this outperforms existing approaches on 3 different datasets, namely Fashion-200k, MIT-States and a new synthetic dataset we create based on CLEVR. We also show that our approach can be used to classify input queries, in addition to image retrieval.
View PDF Chat

Unified Graph Structured Models for Video Understanding

2021-03-29
Anurag Arnab , Chen Sun , Cordelia Schmid
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network … Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly models these spatio-temporal relations and can use explicit representations of objects, when supervision is available, and implicit representations otherwise. Our formulation generalises previous structured models for video understanding, and allows us to study how different design choices in graph structure and representation affect the model's performance. We demonstrate our method on two different tasks requiring relational reasoning in videos -- spatio-temporal action detection on AVA and UCF101-24, and video scene graph classification on the recent Action Genome dataset -- and achieve state-of-the-art results on all three datasets. Furthermore, we show quantitatively and qualitatively how our method is able to more effectively model relationships between relevant entities in the scene.

HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps

2021-01-01
Mi Lu , Hang Zhao , Charlie Nash +7 more
High Definition (HD) maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. They are critical for several key stages in an autonomous driving … High Definition (HD) maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. They are critical for several key stages in an autonomous driving system, including motion forecasting and planning. However, there are only a small amount of real-world road topologies and geometries, which significantly limits our ability to test out the self-driving stack to generalize onto new unseen scenarios. To address this issue, we introduce a new challenging task to generate HD maps. In this work, we explore several autoregressive models using different data representations, including sequence, plain graph, and hierarchical graph. We propose HDMapGen, a hierarchical graph generation model capable of producing high-quality and diverse HD maps through a coarse-to-fine approach. Experiments on the Argoverse dataset and an in-house dataset show that HDMapGen significantly outperforms baseline methods. Additionally, we demonstrate that HDMapGen achieves high scalability and efficiency.
View PDF Chat

Composable Augmentation Encoding for Video Representation Learning

2021-01-01
Chen Sun , Arsha Nagrani , Yonglong Tian +1 more
We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, … We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data instances as negatives. These methods implicitly assume a set of representational invariances to the view selection mechanism (eg, sampling frames with temporal shifts), which may lead to poor performance on downstream tasks which violate these invariances (fine-grained video action recognition that would benefit from temporal information). To overcome this limitation, we propose an 'augmentation aware' contrastive learning framework, where we explicitly provide a sequence of augmentation parameterisations (such as the values of the time shifts used to create data views) as composable augmentation encodings (CATE) to our model when projecting the video representations for contrastive learning. We show that representations learned by our method encode valuable information about specified spatial or temporal augmentation, and in doing so also achieve state-of-the-art performance on a number of video benchmarks.
View PDF Chat

Learning Temporal Dynamics from Cycles in Narrated Video

2021-01-06
Dave Epstein , Jiajun Wu , Cordelia Schmid +1 more
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal … Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal cycle consistency jointly in vision and language, training on narrated video. Our model learns modality-agnostic functions to predict forward and backward in time, which must undo each other when composed. This constraint leads to the discovery of high-level transitions between moments in time, since such transitions are easily inverted and shared across modalities. We justify the design of our model with an ablation study on different configurations of the cycle consistency problem. We then show qualitatively and quantitatively that our approach yields a meaningful, high-level model of the future and past. We apply the learned dynamics model without further training to various tasks, such as predicting future action and temporally ordering sets of images. Project page: https://dave.ml/mmcc
View PDF Chat

Model-Free Control Framework for Stability and Path-tracking of Autonomous Independent-Drive Vehicles

2025-01-01
Yong Wang , Jianming Tang , Qin Li +3 more

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

2024-10-17
Lijie Fan , Tianhong Li , Siyang Qin +6 more
Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, … Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether models use discrete or continuous tokens, and whether tokens are generated in a random or fixed raster order using BERT- or GPT-like transformer architectures. Our empirical results show that, while all models scale effectively in terms of validation loss, their evaluation performance -- measured by FID, GenEval score, and visual quality -- follows different trends. Models based on continuous tokens achieve significantly better visual quality than those using discrete tokens. Furthermore, the generation order and attention mechanisms significantly affect the GenEval score: random-order models achieve notably better GenEval scores compared to raster-order models. Inspired by these findings, we train Fluid, a random-order autoregressive model on continuous tokens. Fluid 10.5B model achieves a new state-of-the-art zero-shot FID of 6.16 on MS-COCO 30K, and 0.69 overall score on the GenEval benchmark. We hope our findings and results will encourage future efforts to further bridge the scaling gap between vision and language models.
View PDF Chat

NLOS Dies Twice: Challenges and Solutions of V2X for Cooperative Perception

2023-01-01
Lantao Li , Chen Sun
Multi-agent multi-lidar sensor fusion between connected vehicles for cooperative perception has recently been recognized as the best technique for minimizing the blind zone of individual vehicular perception systems and further … Multi-agent multi-lidar sensor fusion between connected vehicles for cooperative perception has recently been recognized as the best technique for minimizing the blind zone of individual vehicular perception systems and further enhancing the overall safety of autonomous driving systems. This technique relies heavily on the reliability and availability of vehicle-to-everything (V2X) communication. In practical sensor fusion application scenarios, the non-line-of-sight (NLOS) issue causes blind zones for not only the perception system but also V2X direct communication. To counteract underlying communication issues, we introduce an abstract perception matrix matching method for quick sensor fusion matching procedures and mobility-height hybrid relay determination procedures, proactively improving the efficiency and performance of V2X communication to serve the upper layer application fusion requirements. To demonstrate the effectiveness of our solution, we design a new simulation framework to consider autonomous driving, sensor fusion and V2X communication in general, paving the way for end-to-end performance evaluation and further solution derivation.
View PDF Chat

Emergence of Abstract State Representations in Embodied Sequence Modeling

2023-01-01
Yun Tian , Zilai Zeng , Kunal Handa +4 more
Decision making via sequence modeling aims to mimic the success of language models, where actions taken by an embodied agent are modeled as tokens to predict. Despite their promising performance, … Decision making via sequence modeling aims to mimic the success of language models, where actions taken by an embodied agent are modeled as tokens to predict. Despite their promising performance, it remains unclear if embodied sequence modeling leads to the emergence of internal representations that represent the environmental state information. A model that lacks abstract state representations would be liable to make decisions based on surface statistics which fail to generalize. We take the BabyAI environment, a grid world in which language-conditioned navigation tasks are performed, and build a sequence modeling Transformer, which takes a language instruction, a sequence of actions, and environmental observations as its inputs. In order to investigate the emergence of abstract state representations, we design a "blindfolded" navigation task, where only the initial environmental layout, the language instruction, and the action sequence to complete the task are available for training. Our probing results show that intermediate environmental layouts can be reasonably reconstructed from the internal activations of a trained model, and that language instructions play a role in the reconstruction accuracy. Our results suggest that many key features of state representations can emerge via embodied sequence modeling, supporting an optimistic outlook for applications of sequence modeling objectives to more complex embodied decision-making domains.

Analyzing Modular Approaches for Visual Question Decomposition

2023-01-01
Apoorv Khandelwal , Ellie Pavlick , Chen Sun
Modular neural networks without additional training have recently been shown to surpass end-to-end neural networks on challenging vision-language tasks. The latest such methods simultaneously introduce LLM-based code generation to build … Modular neural networks without additional training have recently been shown to surpass end-to-end neural networks on challenging vision-language tasks. The latest such methods simultaneously introduce LLM-based code generation to build programs and a number of skill-specific, task-oriented modules to execute them. In this paper, we focus on ViperGPT and ask where its additional performance comes from and how much is due to the (state-of-art, end-to-end) BLIP-2 model it subsumes vs. additional symbolic components. To do so, we conduct a controlled study (comparing end-to-end, modular, and prompting-based methods across several VQA benchmarks). We find that ViperGPT's reported gains over BLIP-2 can be attributed to its selection of task-specific modules, and when we run ViperGPT using a more task-agnostic selection of modules, these gains go away. Additionally, ViperGPT retains much of its performance if we make prominent alterations to its selection of modules: e.g. removing or retaining only BLIP-2. Finally, we compare ViperGPT against a prompting-based decomposition strategy and find that, on some benchmarks, modular approaches significantly benefit by representing subtasks with natural language, instead of code.

Anti-Disturbance Boundary Control for a Wave Equation With Input Disturbance

2022-11-03
Xiaoyang Wu , Yonghao Ma , Qiang Fu +3 more
In this article, we investigate the exponential stabilization issue of a wave equation with the external input disturbance, which is described by a nonlinear exogenous system. A novel disturbance observer … In this article, we investigate the exponential stabilization issue of a wave equation with the external input disturbance, which is described by a nonlinear exogenous system. A novel disturbance observer is constructed to estimate the unknown input disturbance. Then, based on the proposed disturbance observer, a boundary control strategy is developed to cancel the effect of disturbance and stabilize the system. The exponential stability is proven by employing the Lyapunov's direct method. This method can be extended to a class of flexible systems described by the hyperbolic partial differential equation met in the practical engineer area. The example of a nonuniform flexible string system is given, where the effectiveness of the proposed strategy is evaluated based on simulations.

Multiview Transformers for Video Recognition

2022-06-01
Yan Shen , Xuehan Xiong , Anurag Arnab +4 more
Video understanding requires reasoning at multiple spatiotemporal resolutions – from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art, they have … Video understanding requires reasoning at multiple spatiotemporal resolutions – from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art, they have not explicitly modelled different spatiotemporal resolutions. To this end, we present Multiview Transformers for Video Recognition (MTV). Our model consists of separate encoders to represent different views of the input video with lateral connections to fuse information across views. We present thorough ablation studies of our model and show that MTV consistently performs better than single-view counterparts in terms of accuracy and computational cost across a range of model sizes. Furthermore, we achieve state-of-the-art results on six standard datasets, and improve even further with large-scale pretraining. Code and checkpoints are available at: https://github.com/google-research/scenic.
View PDF Chat

Learning Audio-Video Modalities from Image Captions

2022-01-01
Arsha Nagrani , Paul Hongsuck Seo , Bryan Seybold +4 more
View PDF Chat

Composable Augmentation Encoding for Video Representation Learning

2021-10-01
Chen Sun , Arsha Nagrani , Yonglong Tian +1 more
We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, … We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data instances as negatives. These methods implicitly assume a set of representational invariances to the view selection mechanism (e.g., sampling frames with temporal shifts), which may lead to poor performance on downstream tasks which violate these invariances (fine-grained video action recognition that would benefit from temporal information). To overcome this limitation, we propose an 'augmentation aware' contrastive learning framework, where we explicitly provide a sequence of augmentation parameterisations (such as the values of the time shifts used to create data views) as composable augmentation encodings (CATE) to our model when projecting the video representations for contrastive learning. We show that representations learned by our method encode valuable information about specified spatial or temporal augmentation, and in doing so also achieve state-of-the-art performance on a number of video benchmarks.
View PDF Chat

Unified Graph Structured Models for Video Understanding

2021-10-01
Anurag Arnab , Chen Sun , Cordelia Schmid
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network … Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly models these spatio-temporal relations and can use explicit representations of objects, when supervision is available, and implicit representations otherwise. Our formulation generalises previous structured models for video understanding, and allows us to study how different design choices in graph structure and representation affect the model’s performance. We demonstrate our method on two different tasks requiring relational reasoning in videos – spatio-temporal action detection on AVA and UCF101-24, and video scene graph classification on the recent Action Genome dataset – and achieve state-of-the-art results on all three datasets. Furthermore, we show quantitatively and qualitatively how our method is able to more effectively model relationships between relevant entities in the scene.
View PDF Chat

ViViT: A Video Vision Transformer

2021-10-01
Anurag Arnab , Mostafa Dehghani , Georg Heigold +3 more
We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatiotemporal tokens from the input video, which are … We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatiotemporal tokens from the input video, which are then encoded by a series of transformer layers. In order to handle the long sequences of tokens encountered in video, we propose several, efficient variants of our model which factorise the spatial- and temporal-dimensions of the input. Although transformer-based models are known to only be effective when large training datasets are available, we show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple video classification benchmarks including Kinetics 400 and 600, Epic Kitchens, Something-Something v2 and Moments in Time, outperforming prior methods based on deep 3D convolutional networks.
View PDF Chat

Episodic Transformer for Vision-and-Language Navigation

2021-10-01
Alexander Pashevich , Cordelia Schmid , Chen Sun
Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and … Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and understanding complex human instructions. We propose Episodic Transformer (E.T.), a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions. To improve training, we leverage synthetic instructions as an intermediate representation that decouples understanding the visual appearance of an environment from the variations of natural language instructions. We demonstrate that encoding the history with a transformer is critical to solve compositional tasks, and that pretraining and joint training with synthetic instructions further improve the performance. Our approach sets a new state of the art on the challenging ALFRED benchmark, achieving 38.4% and 8.5% task success rates on seen and unseen test splits.
View PDF Chat

Learning Temporal Dynamics from Cycles in Narrated Video

2021-10-01
Dave Epstein , Jiajun Wu , Cordelia Schmid +1 more
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We introduce a self-supervised approach to this problem that solves … Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We introduce a self-supervised approach to this problem that solves a multi-modal temporal cycle consistency objective jointly in vision and language. This objective requires a model to learn modality-agnostic functions to predict the future and past that undo each other when composed. We hypothesize that a model trained on this objective will discover long-term temporal dynamics in video. We verify this hypothesis by using the resultant visual representations and predictive models as-is to solve a variety of downstream tasks. Our method outperforms state-of-the-art self-supervised video prediction methods on future action anticipation, temporal image ordering, and arrow-of-time classification tasks, without training on target datasets or their labels.
View PDF Chat

ViViT: A Video Vision Transformer

2021-03-29
Anurag Arnab , Mostafa Dehghani , Georg Heigold +3 more
We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are … We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of transformer layers. In order to handle the long sequences of tokens encountered in video, we propose several, efficient variants of our model which factorise the spatial- and temporal-dimensions of the input. Although transformer-based models are known to only be effective when large training datasets are available, we show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple video classification benchmarks including Kinetics 400 and 600, Epic Kitchens, Something-Something v2 and Moments in Time, outperforming prior methods based on deep 3D convolutional networks. To facilitate further research, we will release code and models.

Unified Graph Structured Models for Video Understanding

2021-03-29
Anurag Arnab , Chen Sun , Cordelia Schmid
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network … Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly models these spatio-temporal relations and can use explicit representations of objects, when supervision is available, and implicit representations otherwise. Our formulation generalises previous structured models for video understanding, and allows us to study how different design choices in graph structure and representation affect the model's performance. We demonstrate our method on two different tasks requiring relational reasoning in videos -- spatio-temporal action detection on AVA and UCF101-24, and video scene graph classification on the recent Action Genome dataset -- and achieve state-of-the-art results on all three datasets. Furthermore, we show quantitatively and qualitatively how our method is able to more effectively model relationships between relevant entities in the scene.

Learning Temporal Dynamics from Cycles in Narrated Video

2021-01-06
Dave Epstein , Jiajun Wu , Cordelia Schmid +1 more
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal … Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal cycle consistency jointly in vision and language, training on narrated video. Our model learns modality-agnostic functions to predict forward and backward in time, which must undo each other when composed. This constraint leads to the discovery of high-level transitions between moments in time, since such transitions are easily inverted and shared across modalities. We justify the design of our model with an ablation study on different configurations of the cycle consistency problem. We then show qualitatively and quantitatively that our approach yields a meaningful, high-level model of the future and past. We apply the learned dynamics model without further training to various tasks, such as predicting future action and temporally ordering sets of images. Project page: https://dave.ml/mmcc
View PDF Chat

Learning Temporal Dynamics from Cycles in Narrated Video

2021-01-01
Dave Epstein , Jiajun Wu , Cordelia Schmid +1 more
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal … Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal cycle consistency jointly in vision and language, training on narrated video. Our model learns modality-agnostic functions to predict forward and backward in time, which must undo each other when composed. This constraint leads to the discovery of high-level transitions between moments in time, since such transitions are easily inverted and shared across modalities. We justify the design of our model with an ablation study on different configurations of the cycle consistency problem. We then show qualitatively and quantitatively that our approach yields a meaningful, high-level model of the future and past. We apply the learned dynamics model without further training to various tasks, such as predicting future action and temporally ordering sets of images. Project page: https://dave.ml/mmcc
View PDF Chat

Attention Bottlenecks for Multimodal Fusion

2021-01-01
Arsha Nagrani , Shan Yang , Anurag Arnab +3 more
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised … Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-attention, our model forces information between different modalities to pass through a small number of bottleneck latents, requiring the model to collate and condense the most relevant information in each modality and only share what is necessary. We find that such a strategy improves fusion performance, at the same time reducing computational cost. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks including Audioset, Epic-Kitchens and VGGSound. All code and models will be released.
View PDF Chat

HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps

2021-01-01
Mi Lu , Hang Zhao , Charlie Nash +7 more
High Definition (HD) maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. They are critical for several key stages in an autonomous driving … High Definition (HD) maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. They are critical for several key stages in an autonomous driving system, including motion forecasting and planning. However, there are only a small amount of real-world road topologies and geometries, which significantly limits our ability to test out the self-driving stack to generalize onto new unseen scenarios. To address this issue, we introduce a new challenging task to generate HD maps. In this work, we explore several autoregressive models using different data representations, including sequence, plain graph, and hierarchical graph. We propose HDMapGen, a hierarchical graph generation model capable of producing high-quality and diverse HD maps through a coarse-to-fine approach. Experiments on the Argoverse dataset and an in-house dataset show that HDMapGen significantly outperforms baseline methods. Additionally, we demonstrate that HDMapGen achieves high scalability and efficiency.
View PDF Chat

Composable Augmentation Encoding for Video Representation Learning

2021-01-01
Chen Sun , Arsha Nagrani , Yonglong Tian +1 more
We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, … We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data instances as negatives. These methods implicitly assume a set of representational invariances to the view selection mechanism (eg, sampling frames with temporal shifts), which may lead to poor performance on downstream tasks which violate these invariances (fine-grained video action recognition that would benefit from temporal information). To overcome this limitation, we propose an 'augmentation aware' contrastive learning framework, where we explicitly provide a sequence of augmentation parameterisations (such as the values of the time shifts used to create data views) as composable augmentation encodings (CATE) to our model when projecting the video representations for contrastive learning. We show that representations learned by our method encode valuable information about specified spatial or temporal augmentation, and in doing so also achieve state-of-the-art performance on a number of video benchmarks.
View PDF Chat

Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos

2020-07-21
Anurag Arnab , Chen Sun , Arsha Nagrani +1 more
Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this … Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present a spatio-temporal action recognition model that is trained with only video-level labels, which are significantly easier to annotate. Our method leverages per-frame person detectors which have been trained on large image datasets within a Multiple Instance Learning framework. We show how we can apply our method in cases where the standard Multiple Instance Learning assumption, that each bag contains at least one instance with the specified label, is invalid using a novel probabilistic variant of MIL where we estimate the uncertainty of each prediction. Furthermore, we report the first weakly-supervised results on the AVA dataset and state-of-the-art results among weakly-supervised methods on UCF101-24.

Speech2Action: Cross-Modal Supervision for Action Recognition

2020-06-01
Arsha Nagrani , Chen Sun , David A. Ross +3 more
Is it possible to guess human action from dialogue alone? In this work we investigate the link between spoken words and actions in movies. We note that movie screenplays describe … Is it possible to guess human action from dialogue alone? In this work we investigate the link between spoken words and actions in movies. We note that movie screenplays describe actions, as well as contain the speech of characters and hence can be used to learn this correlation with no additional supervision. We train a BERT-based Speech2Action classifier on over a thousand movie screenplays, to predict action labels from transcribed speech segments. We then apply this model to the speech segments of a large unlabelled movie corpus (188M speech segments from 288K movies). Using the predictions of this model, we obtain weak action labels for over 800K video clips. By training on these video clips, we demonstrate superior action recognition performance on standard action recognition benchmarks, without using a single manually labelled action example.
View PDF Chat

D3D: Distilled 3D Networks for Video Action Recognition

2020-03-01
Jonathan Stroud , David A. Ross , Chen Sun +2 more
State-of-the-art methods for action recognition commonly use two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent … State-of-the-art methods for action recognition commonly use two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent work, both streams are 3D Convolutional Neural Networks, which use spatiotemporal filters. These filters can respond to motion, and therefore should allow the network to learn motion representations, removing the need for optical flow. However, we still see significant benefits in performance by feeding optical flow into the temporal stream, indicating that the spatial stream is "missing" some of the signal that the temporal stream captures. In this work, we first investigate whether motion representations are indeed missing in the spatial stream, and show that there is significant room for improvement. Second, we demonstrate that these motion representations can be improved using distillation, that is, by tuning the spatial stream to mimic the temporal stream, effectively combining both models into a single stream. Finally, we show that our Distilled 3D Network (D3D) achieves performance on par with the two-stream approach, with no need to compute optical flow during inference.
View PDF Chat

What Makes for Good Views for Contrastive Learning?

2020-01-01
Yonglong Tian , Chen Sun , Ben Poole +3 more
Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different … Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less studied. In this paper, we use theoretical and empirical analysis to better understand the importance of view selection, and argue that we should reduce the mutual information (MI) between views while keeping task-relevant information intact. To verify this hypothesis, we devise unsupervised and semi-supervised frameworks that learn effective views by aiming to reduce their MI. We also consider data augmentation as a way to reduce MI, and show that increasing data augmentation indeed leads to decreasing MI and improves downstream classification accuracy. As a by-product, we achieve a new state-of-the-art accuracy on unsupervised pre-training for ImageNet classification ($73\%$ top-1 linear readout with a ResNet-50). In addition, transferring our models to PASCAL VOC object detection and COCO instance segmentation consistently outperforms supervised pre-training. Code:http://github.com/HobbitLong/PyContrast

Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos

2020-01-01
Anurag Arnab , Chen Sun , Arsha Nagrani +1 more
View PDF Chat

VideoBERT: A Joint Model for Video and Language Representation Learning

2019-10-01
Chen Sun , Austin Myers , Carl Vondrick +2 more
Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic … Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respectively. We use VideoBERT in numerous tasks, including action classification and video captioning. We show that it can be applied directly to open-vocabulary classification, and confirm that large amounts of training data and cross-modal information are critical to performance. Furthermore, we outperform the state-of-the-art on video captioning, and quantitative results verify that the model learns high-level semantic features.
View PDF Chat

Unsupervised Learning of Object Structure and Dynamics from Videos.

2019-06-19
Matthias Minderer , Chen Sun , Ruben Villegas +3 more
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn … Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics model of the keypoints. Future frames are reconstructed from the keypoints and a reference frame. By modeling dynamics in the keypoint coordinate space, we achieve stable learning and avoid compounding of errors in pixel space. Our method improves upon unstructured representations both for pixel-level video prediction and for downstream tasks requiring object-level understanding of motion dynamics. We evaluate our model on diverse datasets: a multi-agent sports dataset, the Human3.6M dataset, and datasets based on continuous control tasks from the DeepMind Control Suite. The spatially structured representation outperforms unstructured representations on a range of motion-related tasks such as object tracking, action recognition and reward prediction.

Composing Text and Image for Image Retrieval - an Empirical Odyssey

2019-06-01
Nam Vo , Lu Jiang , Chen Sun +4 more
In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to … In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to the input image. For example, we may present an image of the Eiffel tower, and ask the system to find images which are visually similar, but are modified in small ways, such as being taken at nighttime instead of during the day. o tackle this task, we embed the query (reference image plus modification text) and the target (images). The encoding function of the image text query learns a representation, such that the similarity with the target image representation is high iff it is a ``positive match''. We propose a new way to combine image and text through residual connection, that is designed for this retrieval task. We show this outperforms existing approaches on 3 different datasets, namely Fashion-200k, MIT-States and a new synthetic dataset we create based on CLEVR. We also show that our approach can be used to perform image classification with compositionally novel labels, and we outperform previous methods on MIT-States on this task.
View PDF Chat

Relational Action Forecasting

2019-06-01
Chen Sun , Abhinav Shrivastava , Carl Vondrick +3 more
This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions … This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions for the next T frames. Our approach jointly models temporal and spatial interactions among different actors by constructing a recurrent graph, using actor proposals obtained with Faster R-CNN as nodes. Our method learns to select a subset of discriminative relations without requiring explicit supervision, thus enabling us to tackle challenging visual data. We refer to our model as Discriminative Relational Recurrent Network (DRRN). Evaluation of action prediction on AVA demonstrates the effectiveness of our proposed method compared to simpler baselines. Furthermore, we significantly improve performance on the task of early action classification on J-HMDB, from the previous SOTA of 48% to 60%.
View PDF Chat

Affordance Learning In Direct Perception for Autonomous Driving

2019-01-01
Chen Sun , Jean Marie Uwabeza Vianney , Dongpu Cao
Recent development in autonomous driving involves high-level computer vision and detailed road scene understanding. Today, most autonomous vehicles are using mediated perception approach for path planning and control, which highly … Recent development in autonomous driving involves high-level computer vision and detailed road scene understanding. Today, most autonomous vehicles are using mediated perception approach for path planning and control, which highly rely on high-definition 3D maps and real time sensors. Recent research efforts aim to substitute the massive HD maps with coarse road attributes. In this paper, we follow the direct perception based method to train a deep neural network for affordance learning in autonomous driving. Our goal in this work is to develop the affordance learning model based on freely available Google Street View panoramas and Open Street Map road vector attributes. Driving scene understanding can be achieved by learning affordances from the images captured by car-mounted cameras. Such scene understanding by learning affordances may be useful for corroborating base maps such as HD maps so that the required data storage space is minimized and available for processing in real time. We compare capability in road attribute identification between human volunteers and our model by experimental evaluation. Our results indicate that this method could act as a cheaper way for training data collection in autonomous driving. The cross validation results also indicate the effectiveness of our model.

Relational Action Forecasting

2019-01-01
Chen Sun , Abhinav Shrivastava , Carl Vondrick +3 more
This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions … This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions for the next T frames. Our approach jointly models temporal and spatial interactions among different actors by constructing a recurrent graph, using actor proposals obtained with Faster R-CNN as nodes. Our method learns to select a subset of discriminative relations without requiring explicit supervision, thus enabling us to tackle challenging visual data. We refer to our model as Discriminative Relational Recurrent Network (DRRN). Evaluation of action prediction on AVA demonstrates the effectiveness of our proposed method compared to simpler baselines. Furthermore, we significantly improve performance on the task of early action classification on J-HMDB, from the previous SOTA of 48% to 60%.
View PDF Chat

Learning Video Representations using Contrastive Bidirectional Transformer

2019-01-01
Chen Sun , Fabien Baradel , Kevin Murphy +1 more
This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. … This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our method extends the BERT model for text sequences to the case of sequences of real-valued feature vectors, by replacing the softmax loss with noise contrastive estimation (NCE). We also show how to learn representations from sequences of visual features and sequences of words derived from ASR (automatic speech recognition), and show that such cross-modal training (when possible) helps even more.
View PDF Chat

D3D: Distilled 3D Networks for Video Action Recognition

2018-12-19
Jonathan Stroud , David A. Ross , Chen Sun +2 more
State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow … State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent work, both of these streams consist of 3D Convolutional Neural Networks, which apply spatiotemporal filters to the video clip before performing classification. Conceptually, the temporal filters should allow the spatial stream to learn motion representations, making the temporal stream redundant. However, we still see significant benefits in action recognition performance by including an entirely separate temporal stream, indicating that the spatial stream is some of the signal captured by the temporal stream. In this work, we first investigate whether motion representations are indeed missing in the spatial stream of 3D CNNs. Second, we demonstrate that these motion representations can be improved by distillation, by tuning the spatial stream to predict the outputs of the temporal stream, effectively combining both models into a single stream. Finally, we show that our Distilled 3D Network (D3D) achieves performance on par with two-stream approaches, using only a single model and with no need to compute optical flow.

The iNaturalist Species Classification and Detection Dataset

2018-06-01
Grant Van Horn , Oisin Mac Aodha , Yang Song +6 more
Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. In contrast, the natural world is heavily imbalanced, as some species … Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. In contrast, the natural world is heavily imbalanced, as some species are more abundant and easier to photograph than others. To encourage further progress in challenging real world conditions we present the iNaturalist species classification and detection dataset, consisting of 859,000 images from over 5,000 different species of plants and animals. It features visually similar species, captured in a wide variety of situations, from all over the world. Images were collected with different camera types, have varying image quality, feature a large class imbalance, and have been verified by multiple citizen scientists. We discuss the collection of the dataset and present extensive baseline experiments using state-of-the-art computer vision classification and detection models. Results show that current non-ensemble based methods achieve only 67% top one classification accuracy, illustrating the difficulty of the dataset. Specifically, we observe poor results for classes with small numbers of training examples suggesting more attention is needed in low-shot learning.
View PDF Chat

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

2018-06-01
Yin Cui , Yang Song , Chen Sun +2 more
Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make … Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make & model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets.
View PDF Chat

DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks.

2018-01-22
Unaiza Ahsan , Chen Sun , Irfan Essa
We propose an action recognition framework using Gen- erative Adversarial Networks. Our model involves train- ing a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without … We propose an action recognition framework using Gen- erative Adversarial Networks. Our model involves train- ing a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without la- bel information. Then we use the trained discriminator from the GAN model as an unsupervised pre-training step and fine-tune the trained discriminator model on a labeled dataset to recognize human activities. We determine good network architectural and hyperparameter settings for us- ing the discriminator from DCGAN as a trained model to learn useful representations for action recognition. Our semi-supervised framework using only appearance infor- mation achieves superior or comparable performance to the current state-of-the-art semi-supervised action recog- nition methods on two challenging video activity datasets: UCF101 and HMDB51.

Composing Text and Image for Image Retrieval - An Empirical Odyssey

2018-01-01
Nam Vo , Lu Jiang , Chen Sun +4 more
In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to … In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to the input image. For example, we may present an image of the Eiffel tower, and ask the system to find images which are visually similar but are modified in small ways, such as being taken at nighttime instead of during the day. To tackle this task, we learn a similarity metric between a target image and a source image plus source text, an embedding and composing function such that target image feature is close to the source image plus text composition feature. We propose a new way to combine image and text using such function that is designed for the retrieval task. We show this outperforms existing approaches on 3 different datasets, namely Fashion-200k, MIT-States and a new synthetic dataset we create based on CLEVR. We also show that our approach can be used to classify input queries, in addition to image retrieval.
View PDF Chat

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

2018-01-01
Yin Cui , Yang Song , Chen Sun +2 more
Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make … Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make and model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets.
View PDF Chat

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

2017-10-01
Jiyang Gao , Zhenheng Yang , Chen Sun +2 more
Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale … Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale video analysis. We propose a novel Temporal Unit Regression Network (TURN) model. There are two salient aspects of TURN: (1) TURN jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression: (2) Fast computation is enabled by unit feature reuse: a long untrimmed video is decomposed into video units, which are reused as basic building blocks of temporal proposals. TURN outperforms the previous state-of-the-art methods under average recall (AR) by a large margin on THUMOS-14 and ActivityNet datasets, and runs at over 880 frames per second (FPS) on a TITAN X GPU. We further apply TURN as a proposal generation stage for existing temporal action localization pipelines, it outperforms state-of-the-art performance on THUMOS-14 and ActivityNet.
View PDF Chat

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

2017-10-01
Chen Sun , Abhinav Shrivastava , Saurabh Singh +1 more
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there … The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10 × or 100 × ? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between 'enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pre-training) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-the-art results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.
View PDF Chat

VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

2017-10-01
Chuang Gan , Yandong Li , Haoxiang Li +2 more
Rich and dense human labeled datasets are among the main enabling factors for the recent advance on visionlanguage understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering … Rich and dense human labeled datasets are among the main enabling factors for the recent advance on visionlanguage understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering (VQA)) are inherently connected in that they reveal different levels and perspectives of human understandings about the same visual scenes — and even the same set of images (e.g., of COCO). The popularity of COCO correlates those annotations and tasks. Explicitly linking them up may significantly benefit both individual tasks and the unified vision and language modeling.,,We present the preliminary work of linking the instance segmentations provided by COCO to the questions and answers (QAs) in the VQA dataset, and name the collected links visual questions and segmentation answers (VQS). They transfer human supervision between the previously separate tasks, offer more effective leverage to existing problems, and also open the door for new research problems and models. We study two applications of the VQS data in this paper: supervised attention for VQA and a novel question-focused semantic segmentation task. For the former, we obtain state-of-the-art results on the VQA real multiple-choice task by simply augmenting the multilayer perceptrons with some attention features that are learned using the segmentation-QA links as explicit supervision. To put the latter in perspective, we study two plausible methods and compare them to an oracle method assuming that the instance segmentations are given at the test stage.
View PDF Chat

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

2017-07-01
Jonathan Huang , Vivek Rathod , Chen Sun +7 more
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this … The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-toapples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We present a unified implementation of the Faster R-CNN [30], R-FCN [6] and SSD [25] systems, which we view as meta-architectures and trace out the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures. On one extreme end of this spectrum where speed and memory are critical, we present a detector that achieves real time speeds and can be deployed on a mobile device. On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.
View PDF Chat

Complex Event Recognition from Images with Few Training Examples

2017-01-17
Unaiza Ahsan , Chen Sun , James Hays +1 more
We propose to leverage concept-level representations for complex event recognition in photographs given limited training examples. We introduce a novel framework to discover event concept attributes from the web and … We propose to leverage concept-level representations for complex event recognition in photographs given limited training examples. We introduce a novel framework to discover event concept attributes from the web and use that to extract semantic features from images and classify them into social event categories with few training examples. Discovered concepts include a variety of objects, scenes, actions and event sub-types, leading to a discriminative and compact representation for event images. Web images are obtained for each discovered event concept and we use (pretrained) CNN features to train concept classifiers. Extensive experiments on challenging event datasets demonstrate that our proposed method outperforms several baselines using deep CNN features directly in classifying images into events with limited training examples. We also demonstrate that our method achieves the best overall accuracy on a dataset with unseen event categories using a single training example.

TALL: Temporal Activity Localization via Language Query

2017-01-01
Jiyang Gao , Chen Sun , Zhenheng Yang +1 more
This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. … This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. However, activities in the wild consist of a wide combination of actors, actions and objects; it is difficult to design a proper activity list that meets users' needs. We propose to localize activities by natural language queries. Temporal Activity Localization via Language (TALL) is challenging as it requires: (1) suitable design of text and video representations to allow cross-modal matching of actions and language queries; (2) ability to locate actions accurately given features from sliding windows of limited granularity. We propose a novel Cross-modal Temporal Regression Localizer (CTRL) to jointly model text query and video clips, output alignment scores and action boundary regression results for candidate clips. For evaluation, we adopt TaCoS dataset, and build a new dataset for this task on top of Charades by adding sentence temporal annotations, called Charades-STA. We also build complex sentence queries in Charades-STA for test. Experimental results show that CTRL outperforms previous methods significantly on both datasets.
View PDF Chat

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

2017-01-01
Chen Sun , Abhinav Shrivastava , Saurabh Singh +1 more
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there … The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10x or 100x? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between `enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pre-training) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-the-art results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.
View PDF Chat

VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

2017-01-01
Chuang Gan , Yandong Li , Haoxiang Li +2 more
Rich and dense human labeled datasets are among the main enabling factors for the recent advance on vision-language understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering … Rich and dense human labeled datasets are among the main enabling factors for the recent advance on vision-language understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering (VQA)) are inherently connected in that they reveal different levels and perspectives of human understandings about the same visual scenes --- and even the same set of images (e.g., of COCO). The popularity of COCO correlates those annotations and tasks. Explicitly linking them up may significantly benefit both individual tasks and the unified vision and language modeling. We present the preliminary work of linking the instance segmentations provided by COCO to the questions and answers (QAs) in the VQA dataset, and name the collected links visual questions and segmentation answers (VQS). They transfer human supervision between the previously separate tasks, offer more effective leverage to existing problems, and also open the door for new research problems and models. We study two applications of the VQS data in this paper: supervised attention for VQA and a novel question-focused semantic segmentation task. For the former, we obtain state-of-the-art results on the VQA real multiple-choice task by simply augmenting the multilayer perceptrons with some attention features that are learned using the segmentation-QA links as explicit supervision. To put the latter in perspective, we study two plausible methods and compare them to an oracle method assuming that the instance segmentations are given at the test stage.
View PDF Chat

AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions

2017-01-01
Chunhui Gu , Chen Sun , David A. Ross +7 more
This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are … This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently. The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute video clips; (4) people temporally linked across consecutive segments; and (5) using movies to gather a varied set of action representations. This departs from existing datasets for spatio-temporal action recognition, which typically provide sparse annotations for composite actions in short video clips. We will release the dataset publicly. AVA, with its realistic scene and action complexity, exposes the intrinsic difficulty of action recognition. To benchmark this, we present a novel approach for action localization that builds upon the current state-of-the-art methods, and demonstrates better performance on JHMDB and UCF101-24 categories. While setting a new state of the art on existing datasets, the overall results on AVA are low at 15.6% mAP, underscoring the need for developing new approaches for video understanding.

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

2017-01-01
Jiyang Gao , Zhenheng Yang , Chen Sun +2 more
Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale … Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale video analysis. We propose a novel Temporal Unit Regression Network (TURN) model. There are two salient aspects of TURN: (1) TURN jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression; (2) Fast computation is enabled by unit feature reuse: a long untrimmed video is decomposed into video units, which are reused as basic building blocks of temporal proposals. TURN outperforms the state-of-the-art methods under average recall (AR) by a large margin on THUMOS-14 and ActivityNet datasets, and runs at over 880 frames per second (FPS) on a TITAN X GPU. We further apply TURN as a proposal generation stage for existing temporal action localization pipelines, it outperforms state-of-the-art performance on THUMOS-14 and ActivityNet.

ProNet: Learning to Propose Object-Specific Boxes for Cascaded Neural Networks

2016-06-01
Chen Sun , Manohar Paluri , Ronan Collobert +2 more
This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and … This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and in different scales. In this paper, we propose a novel classification architecture ProNet based on convolutional neural networks. It uses computationally efficient neural networks to propose image regions that are likely to contain objects, and applies more powerful but slower networks on the proposed regions. The basic building block is a multi-scale fully-convolutional network which assigns object confidence scores to boxes at different locations and scales. We show that such networks can be trained effectively using image-level annotations, and can be connected into cascades or trees for efficient object classification. ProNet outperforms previous state-of-the-art significantly on PASCAL VOC 2012 and MS COCO datasets for object classification and point-based localization.
View PDF Chat

ACD: Action Concept Discovery from Image-Sentence Corpora

2016-01-01
Jiyang Gao , Chen Sun , Ram Nevatia
Action classification in still images is an important task in computer vision. It is challenging as the appearances of ac- tions may vary depending on their context (e.g. associated objects). … Action classification in still images is an important task in computer vision. It is challenging as the appearances of ac- tions may vary depending on their context (e.g. associated objects). Manually labeling of context information would be time consuming and difficult to scale up. To address this challenge, we propose a method to automatically discover and cluster action concepts, and learn their classifiers from weakly supervised image-sentence corpora. It obtains candidate action concepts by extracting verb-object pairs from sentences and verifies their visualness with the associated images. Candidate action concepts are then clustered by using a multi-modal representation with image embeddings from deep convolutional networks and text embeddings from word2vec. More than one hundred human action concept classifiers are learned from the Flickr 30k dataset with no additional human effort and promising classification results are obtained. We further apply the AdaBoost algorithm to automatically select and combine relevant action concepts given an action query. Promising results have been shown on the PASCAL VOC 2012 action classification benchmark, which has zero overlap with Flickr30k.
Coauthor Papers Together
Cordelia Schmid 23
Kevin Murphy 9
Ram Nevatia 8
Anurag Arnab 8
Rahul Sukthankar 7
Arsha Nagrani 7
Yang Song 5
Jiyang Gao 5
Abhinav Shrivastava 4
David A. Ross 4
Yonglong Tian 4
Zhenheng Yang 3
James Hays 3
Carl Vondrick 3
Yin Cui 3
Serge Belongie 3
Jiajun Wu 3
Chuang Gan 3
Dave Epstein 3
Boqing Gong 2
Menglong Zhu 2
Haoxiang Li 2
Yandong Li 2
Nam Vo 2
Jia Deng 2
Li Fei-Fei 2
Kan Chen 2
Mostafa Dehghani 2
Unaiza Ahsan 2
Mario Lučić 2
Jonathan Huang 2
Vivek Rathod 2
Zbigniew Wojna 2
Sergio Guadarrama 2
Georg Heigold 2
Li-Jia Li 2
Alireza Fathi 2
Anoop Korattikara 2
Andrew Howard 2
Ronan Collobert 2
Saurabh Singh 2
Lubomir Bourdev 2
Ellie Pavlick 2
Jonathan Stroud 2
Manohar Paluri 2
Ian Fischer 2
Irfan Essa 2
Lu Jiang 2
Dongpu Cao 1
Charlie Nash 1

Deep Residual Learning for Image Recognition

2016-06-01
Kaiming He , Xiangyu Zhang , Shaoqing Ren +1 more
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly … Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers - 8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
View PDF Chat

The Kinetics Human Action Video Dataset

2017-01-01
Andrew Zisserman , João Carreira , Karen Simonyan +7 more
We describe the DeepMind Kinetics human action video dataset. The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s … We describe the DeepMind Kinetics human action video dataset. The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s and is taken from a different YouTube video. The actions are human focussed and cover a broad range of classes including human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands. We describe the statistics of the dataset, how it was collected, and give some baseline performance figures for neural network architectures trained and tested for human action classification on this dataset. We also carry out a preliminary analysis of whether imbalance in the dataset leads to bias in the classifiers.

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

2017-07-01
João Carreira , Andrew Zisserman
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale … The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper re-evaluates state-of-the-art architectures in light of the new Kinetics Human Action Video dataset. Kinetics has two orders of magnitude more data, with 400 human action classes and over 400 clips per class, and is collected from realistic, challenging YouTube videos. We provide an analysis on how current architectures fare on the task of action classification on this dataset and how much performance improves on the smaller benchmark datasets after pre-training on Kinetics. We also introduce a new Two-Stream Inflated 3D ConvNet (I3D) that is based on 2D ConvNet inflation: filters and pooling kernels of very deep image classification ConvNets are expanded into 3D, making it possible to learn seamless spatio-temporal feature extractors from video while leveraging successful ImageNet architecture designs and even their parameters. We show that, after pre-training on Kinetics, I3D models considerably improve upon the state-of-the-art in action classification, reaching 80.2% on HMDB-51 and 97.9% on UCF-101.
View PDF Chat

Going deeper with convolutions

2015-06-01
Christian Szegedy , Wei Liu , Yangqing Jia +6 more
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 … We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
View PDF Chat

Very Deep Convolutional Networks for Large-Scale Image Recognition

2014-09-04
Karen Simonyan , Andrew Zisserman
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks … In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

2012-12-03
Khurram Soomro , Amir Zamir , Mubarak Shah
We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists … We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists of realistic user uploaded videos containing camera motion and cluttered background. Additionally, we provide baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%. To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large number of classes, large number of clips and also unconstrained nature of such clips.

Non-local Neural Networks

2018-06-01
Xiaolong Wang , Ross Girshick , Abhinav Gupta +1 more
Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks … Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. Inspired by the classical non-local means method in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On the task of video classification, even without any bells and whistles, our non-local models can compete or outperform current competition winners on both Kinetics and Charades datasets. In static image recognition, our non-local models improve object detection/segmentation and pose estimation on the COCO suite of tasks. Code is available at https://github.com/facebookresearch/video-nonlocal-net .
View PDF Chat

ImageNet Large Scale Visual Recognition Challenge

2015-04-10
Olga Russakovsky , Jia Deng , Hao Su +7 more
View PDF Chat

Two-Stream Convolutional Networks for Action Recognition in Videos

2014-01-01
Karen Simonyan , Andrew Zisserman
We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion … We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data. Finally, we show that multi-task learning, applied to two different action classification datasets, can be used to increase the amount of training data and improve the performance on both. Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art. It also exceeds by a large margin previous attempts to use deep nets for video classification.

SlowFast Networks for Video Recognition

2019-10-01
Christoph Feichtenhofer , Haoqi Fan , Jitendra Malik +1 more
We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at … We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art accuracy on major video recognition benchmarks, Kinetics, Charades and AVA. Code has been made available at: https://github.com/facebookresearch/SlowFast.
View PDF Chat

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

2017-10-01
Chen Sun , Abhinav Shrivastava , Saurabh Singh +1 more
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there … The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10 × or 100 × ? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between 'enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pre-training) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-the-art results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.
View PDF Chat

Generating Videos with Scene Dynamics

2016-01-01
Carl Vondrick , Hamed Pirsiavash , Antonio Torralba
We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. … We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative adversarial network for video with a spatio-temporal convolutional architecture that untangles the scene's foreground from the background. Experiments suggest this model can generate tiny videos up to a second at full frame rate better than simple baselines, and we show its utility at predicting plausible futures of static images. Moreover, experiments and visualizations show the model internally learns useful features for recognizing actions with minimal supervision, suggesting scene dynamics are a promising signal for representation learning. We believe generative video models can impact many applications in video understanding and simulation.

SSD: Single Shot MultiBox Detector

2016-01-01
Wei Liu , Dragomir Anguelov , Dumitru Erhan +4 more
View PDF Chat

Rethinking the Inception Architecture for Computer Vision

2016-06-01
Christian Szegedy , Vincent Vanhoucke , Sergey Ioffe +2 more
Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding … Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios. Here we are exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. We benchmark our methods on the ILSVRC 2012 classification challenge validation set demonstrate substantial gains over the state of the art: 21:2% top-1 and 5:6% top-5 error for single frame evaluation using a network with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. With an ensemble of 4 models and multi-crop evaluation, we report 3:5% top-5 error and 17:3% top-1 error on the validation set and 3:6% top-5 error on the official test set.
View PDF Chat

Attention Is All You Need

2017-01-01
Ashish Vaswani , Noam Shazeer , Niki Parmar +5 more
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an … The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

Squeeze-and-Excitation Networks

2018-06-01
Jie Hu , Li Shen , Gang Sun
Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local receptive fields. In order to boost the representational … Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local receptive fields. In order to boost the representational power of a network, several recent approaches have shown the benefit of enhancing spatial encoding. In this work, we focus on the channel relationship and propose a novel architectural unit, which we term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We demonstrate that by stacking these blocks together, we can construct SENet architectures that generalise extremely well across challenging datasets. Crucially, we find that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost. SENets formed the foundation of our ILSVRC 2017 classification submission which won first place and significantly reduced the top-5 error to 2.251%, achieving a ~25% relative improvement over the winning entry of 2016. Code and models are available at https://github.com/hujie-frank/SENet.
View PDF Chat

Moments in Time Dataset: One Million Videos for Event Understanding

2019-02-25
Mathew Monfort , Carl Vondrick , Aude Oliva +7 more
We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for … We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions occurring in 3 second videos poses many challenges: meaningful events do not include only people, but also objects, animals, and natural phenomena; visual and auditory events can be symmetrical in time ("opening" is "closing" in reverse), and either transient or sustained. We describe the annotation process of our dataset (each video is tagged with one action or activity label among 339 different classes), analyze its scale and diversity in comparison to other large-scale video datasets for action recognition, and report results of several baseline models addressing separately, and jointly, three modalities: spatial, temporal and auditory. The Moments in Time dataset, designed to have a large coverage and diversity of events in both visual and auditory modalities, can serve as a new challenge to develop models that scale to the level of complexity and abstract reasoning that a human processes on a daily basis.
View PDF Chat

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

2016-06-06
Shaoqing Ren , Kaiming He , Ross Girshick +1 more
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, … State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network(RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features-using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model [3], our detection system has a frame rate of 5 fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.
View PDF Chat

Video Action Transformer Network

2019-06-01
Rohit Girdhar , João Carreira , Carl Doersch +1 more
We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person … We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we are trying to classify. We show that by using high-resolution, person-specific, class-agnostic queries, the model spontaneously learns to track individual people and to pick up on semantic context from the actions of others. Additionally its attention mechanism learns to emphasize hands and faces, which are often crucial to discriminate an action - all without explicit supervision other than boxes and class labels. We train and test our Action Transformer network on the Atomic Visual Actions (AVA) dataset, outperforming the state-of-the-art by a significant margin using only raw RGB frames as input.
View PDF Chat

Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification

2018-01-01
Saining Xie , Chen Sun , Jonathan Huang +2 more
View PDF Chat

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

2014-06-01
Ross Girshick , Jeff Donahue , Trevor Darrell +1 more
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level … Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.
View PDF Chat

A Closer Look at Spatiotemporal Convolutions for Action Recognition

2018-06-01
Du Tran , Heng Wang , Lorenzo Torresani +3 more
In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied … In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work we empirically demonstrate the accuracy advantages of 3D CNNs over 2D CNNs within the framework of residual learning. Furthermore, we show that factorizing the 3D convolutional filters into separate spatial and temporal components yields significantly gains in accuracy. Our empirical study leads to the design of a new spatiotemporal convolutional block "R(2+1)D" which produces CNNs that achieve results comparable or superior to the state-of-the-art on Sports-1M, Kinetics, UCF101, and HMDB51.
View PDF Chat

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

2015-01-01
Shaoqing Ren , Kaiming He , Ross Girshick +1 more
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region … State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

2015-01-01
Sergey Ioffe , Christian Szegedy
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down … Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters.

Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification

2016-01-01
Ishan Misra , C. Lawrence Zitnick , Martial Hebert
View PDF Chat

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

2019-10-01
Antoine Miech , Dimitri Zhukov , Jean-Baptiste Alayrac +3 more
Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on … Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose instead to learn such embeddings from video data with readily available natural language annotations in the form of automatically transcribed narrations. The contributions of this work are three-fold. First, we introduce HowTo100M: a large-scale dataset of 136 million video clips sourced from 1.22M narrated instructional web videos depicting humans performing and describing over 23k different visual tasks. Our data collection procedure is fast, scalable and does not require any additional manual annotation. Second, we demonstrate that a text-video embedding trained on this data leads to state-of-the-art results for text-to-video retrieval and action localization on instructional video datasets such as YouCook2 or CrossTask. Finally, we show that this embedding transfers well to other domains: fine-tuning on generic Youtube videos (MSR-VTT dataset) and movies (LSMDC dataset) outperforms models trained on these datasets alone. Our dataset, code and models are publicly available.
View PDF Chat

Ambient Sound Provides Supervision for Visual Learning

2016-01-01
Andrew Owens , Jiajun Wu , Josh H. McDermott +2 more
View PDF Chat

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

2017-02-12
Christian Szegedy , Sergey Ioffe , Vincent Vanhoucke +1 more
Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve … Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance at relatively low computational cost. Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network. This raises the question: Are there any benefits to combining Inception architectures with residual connections? Here we give clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly. There is also some evidence of residual Inception networks outperforming similarly expensive Inception networks without residual connections by a thin margin. We also present several new streamlined architectures for both residual and non-residual Inception networks. These variations improve the single-frame recognition performance on the ILSVRC 2012 classification task significantly. We further demonstrate how proper activation scaling stabilizes the training of very wide residual Inception networks. With an ensemble of three residual and one Inception-v4 networks, we achieve 3.08% top-5 error on the test set of the ImageNet classification (CLS) challenge.
View PDF Chat

VideoBERT: A Joint Model for Video and Language Representation Learning

2019-10-01
Chen Sun , Austin Myers , Carl Vondrick +2 more
Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic … Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respectively. We use VideoBERT in numerous tasks, including action classification and video captioning. We show that it can be applied directly to open-vocabulary classification, and confirm that large amounts of training data and cross-modal information are critical to performance. Furthermore, we outperform the state-of-the-art on video captioning, and quantitative results verify that the model learns high-level semantic features.
View PDF Chat

Learning Spatiotemporal Features with 3D Convolutional Networks

2015-12-01
Du Tran , Lubomir Bourdev , Rob Fergus +2 more
We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: … We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets, 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets, and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.
View PDF Chat

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

2018-01-01
Jacob Devlin , Ming‐Wei Chang , Kenton Lee +1 more
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations … We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

Distilling the Knowledge in a Neural Network

2015-01-01
Geoffrey E. Hinton , Oriol Vinyals , Jay B. Dean
A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions. … A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions. Unfortunately, making predictions using a whole ensemble of models is cumbersome and may be too computationally expensive to allow deployment to a large number of users, especially if the individual models are large neural nets. Caruana and his collaborators have shown that it is possible to compress the knowledge in an ensemble into a single model which is much easier to deploy and we develop this approach further using a different compression technique. We achieve some surprising results on MNIST and we show that we can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model. We also introduce a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse. Unlike a mixture of experts, these specialist models can be trained rapidly and in parallel.

Spatiotemporal Residual Networks for Video Action Recognition

2016-01-01
Christoph Feichtenhofer , Axel Pinz , Richard P. Wildes
Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In … Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we introduce spatiotemporal ResNets as a combination of these two approaches. Our novel architecture generalizes ResNets for the spatiotemporal domain by introducing residual connections in two ways. First, we inject residual connections between the appearance and motion pathways of a two-stream architecture to allow spatiotemporal interaction between the two streams. Second, we transform pretrained image ConvNets into spatiotemporal networks by equipping these with learnable convolutional filters that are initialized as temporal residual connections and operate on adjacent feature maps in time. This approach slowly increases the spatiotemporal receptive field as the depth of the model increases and naturally integrates image ConvNet design principles. The whole model is trained end-to-end to allow hierarchical learning of complex spatiotemporal features. We evaluate our novel spatiotemporal ResNet using two widely used action recognition benchmarks where it exceeds the previous state-of-the-art.

Long-Term Feature Banks for Detailed Video Understanding

2019-06-01
Chao-Yuan Wu , Christoph Feichtenhofer , Haoqi Fan +3 more
To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do … To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank—supportive information extracted over the entire span of a video—to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades. Code is available online.
View PDF Chat

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

2015-02-11
Sergey Ioffe , Christian Szegedy
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down … Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters.

Video Representation Learning by Dense Predictive Coding

2019-10-01
Tengda Han , Weidi Xie , Andrew Zisserman
The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) … The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for self-supervised representation learning on videos. This learns a dense encoding of spatio-temporal blocks by recurrently predicting future representations; Second, we propose a curriculum training scheme to predict further into the future with progressively less temporal context. This encourages the model to only encode slowly varying spatial-temporal signals, therefore leading to semantic representations; Third, we evaluate the approach by first training the DPC model on the Kinetics-400 dataset with self-supervised learning, and then finetuning the representation on a downstream task, i.e. action recognition. With single stream (RGB only), DPC pretrained representations achieve state-of-the-art self-supervised performance on both UCF101(75.7% top1 acc) and HMDB51(35.7% top1 acc), outperforming all previous learning methods by a significant margin, and approaching the performance of a baseline pre-trained on ImageNet.
View PDF Chat

Long-term recurrent convolutional networks for visual recognition and description

2015-06-01
Jeff Donahue , Lisa Anne Hendricks , Sergio Guadarrama +4 more
Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual … Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep" in that they can be compositional in spatial and temporal "layers". Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.
View PDF Chat

FaceNet: A unified embedding for face recognition and clustering

2015-06-01
Florian Schroff , Dmitry Kalenichenko , James Philbin
Despite significant recent advances in the field of face recognition [10, 14, 15, 17], implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this … Despite significant recent advances in the field of face recognition [10, 14, 15, 17], implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity. Once this space has been produced, tasks such as face recognition, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings asfeature vectors. Our method uses a deep convolutional network trained to directly optimize the embedding itself, rather than an intermediate bottleneck layer as in previous deep learning approaches. To train, we use triplets of roughly aligned matching / non-matching face patches generated using a novel online triplet mining method. The benefit of our approach is much greater representational efficiency: we achieve state-of-the-artface recognition performance using only 128-bytes perface. On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves 95.12%. Our system cuts the error rate in comparison to the best published result [15] by 30% on both datasets.
View PDF Chat

Spot On: Action Localization from Pointly-Supervised Proposals

2016-01-01
Pascal Mettes , Jan van Gemert , Cees G. M. Snoek
View PDF Chat

Learning Video Representations using Contrastive Bidirectional Transformer

2019-01-01
Chen Sun , Fabien Baradel , Kevin Murphy +1 more
This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. … This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our method extends the BERT model for text sequences to the case of sequences of real-valued feature vectors, by replacing the softmax loss with noise contrastive estimation (NCE). We also show how to learn representations from sequences of visual features and sequences of words derived from ASR (automatic speech recognition), and show that such cross-modal training (when possible) helps even more.
View PDF Chat

Anticipating Visual Representations from Unlabeled Video

2016-06-01
Carl Vondrick , Hamed Pirsiavash , Antonio Torralba
Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive … Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world that is difficult to write down. We believe that a promising resource for efficiently learning this knowledge is through readily available unlabeled video. We present a framework that capitalizes on temporal structure in unlabeled video to learn to anticipate human actions and objects. The key idea behind our approach is that we can train deep networks to predict the visual representation of images in the future. Visual representations are a promising prediction target because they encode images at a higher semantic level than pixels yet are automatic to compute. We then apply recognition algorithms on our predicted representation to anticipate objects and actions. We experimentally validate this idea on two datasets, anticipating actions one second in the future and objects five seconds in the future.
View PDF Chat

Attention is All you Need

2017-06-12
Ashish Vaswani , Noam Shazeer , Niki Parmar +5 more
The dominant sequence transduction models are based on complex recurrent orconvolutional neural networks in an encoder and decoder configuration. The best performing such models also connect the encoder and decoder … The dominant sequence transduction models are based on complex recurrent orconvolutional neural networks in an encoder and decoder configuration. The best performing such models also connect the encoder and decoder through an attentionm echanisms. We propose a novel, simple network architecture based solely onan attention mechanism, dispensing with recurrence and convolutions entirely.Experiments on two machine translation tasks show these models to be superiorin quality while being more parallelizable and requiring significantly less timeto train. Our single model with 165 million parameters, achieves 27.5 BLEU onEnglish-to-German translation, improving over the existing best ensemble result by over 1 BLEU. On English-to-French translation, we outperform the previoussingle state-of-the-art with model by 0.7 BLEU, achieving a BLEU score of 41.1.

Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition

2019-06-01
Deepti Ghadiyaram , Du Tran , Dhruv Mahajan
Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents … Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of using large volumes of web videos for pre-training video models for the task of action recognition. Our primary empirical finding is that pre-training at a very large scale (over 65 million videos), despite on noisy social-media videos and hashtags, substantially improves the state-of-the-art on three challenging public action recognition datasets. Further, we examine three questions in the construction of weakly-supervised video action datasets. First, given that actions involve interactions with objects, how should one construct a verb-object pre-training label space to benefit transfer learning the most? Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning? Finally, actions are generally less well-localized in long videos vs. short videos; since action labels are provided at a video level, how should one choose video clips for best performance, given some fixed budget of number or minutes of videos?
View PDF Chat

The “Something Something” Video Database for Learning and Evaluating Visual Common Sense

2017-10-01
Raghav Goyal , Samira Ebrahimi Kahou , Vincent Michalski +7 more
Neural networks trained on datasets such as ImageNet have led to major advances in visual object classification. One obstacle that prevents networks from reasoning more deeply about complex scenes and … Neural networks trained on datasets such as ImageNet have led to major advances in visual object classification. One obstacle that prevents networks from reasoning more deeply about complex scenes and situations, and from integrating visual knowledge with natural language, like humans do, is their lack of common sense knowledge about the physical world. Videos, unlike still images, contain a wealth of detailed information about the physical world. However, most labelled video datasets represent high-level concepts rather than detailed physical aspects about actions and scenes. In this work, we describe our ongoing collection of the "something-something" database of video prediction tasks whose solutions require a common sense understanding of the depicted situation. The database currently contains more than 100,000 videos across 174 classes, which are defined as caption-templates. We also describe the challenges in crowd-sourcing this data at scale.
View PDF Chat

Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction

2017-10-01
Gurkirt Singh , Suman Saha , Michael Sapienza +2 more
We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation and classification. Current state-of-the-art approaches work offline, and are too slow to be useful in real-world settings. To … We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation and classification. Current state-of-the-art approaches work offline, and are too slow to be useful in real-world settings. To overcome their limitations we introduce two major developments. Firstly, we adopt real-time SSD (Single Shot Multi-Box Detector) CNNs to regress and classify detection boxes in each video frame potentially containing an action of interest. Secondly, we design an original and efficient online algorithm to incrementally construct and label 'action tubes' from the SSD frame level detections. As a result, our system is not only capable of performing S/T detection in real time, but can also perform early action prediction in an online fashion. We achieve new state-of-the-art results in both S/T action localisation and early action prediction on the challenging UCF101-24 and J-HMDB-21 benchmarks, even when compared to the top offline competitors. To the best of our knowledge, ours is the first real-time (up to 40fps) system able to perform online S/T action localisation on the untrimmed videos of UCF101-24.
View PDF Chat

Unsupervised Learning from Narrated Instruction Videos

2016-06-01
Jean-Baptiste Alayrac , Piotr Bojanowski , Nishant Agrawal +3 more
We address the problem of automatically learning the main steps to complete a certain task, such as changing a car tire, from a set of narrated instruction videos. The contributions … We address the problem of automatically learning the main steps to complete a certain task, such as changing a car tire, from a set of narrated instruction videos. The contributions of this paper are three-fold. First, we develop a new unsupervised learning approach that takes advantage of the complementary nature of the input video and the associated narration. The method solves two clustering problems, one in text and one in video, applied one after each other and linked by joint constraints to obtain a single coherent sequence of steps in both modalities. Second, we collect and annotate a new challenging dataset of real-world instruction videos from the Internet. The dataset contains about 800,000 frames for five different tasks <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> that include complex interactions between people and objects, and are captured in a variety of indoor and outdoor settings. Third, we experimentally demonstrate that the proposed method can automatically discover, in an unsupervised manner, the main steps to achieve the task and locate the steps in the input videos.
View PDF Chat

Very Deep Convolutional Networks for Large-Scale Image Recognition

2014-01-01
Karen Simonyan , Andrew Zisserman
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks … In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Feature Pyramid Networks for Object Detection

2017-07-01
Tsung-Yi Lin , Piotr Dollár , Ross Girshick +3 more
Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors that are based on deep … Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors that are based on deep convolutional networks, partially because they are slow to compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant improvement as a generic feature extractor in several applications. Using a basic Faster R-CNN system, our method achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles, surpassing all existing single-model entries including those from the COCO 2016 challenge winners. In addition, our method can run at 5 FPS on a GPU and thus is a practical and accurate solution to multi-scale object detection. Code will be made publicly available.
View PDF Chat

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

2017-07-01
Jonathan Huang , Vivek Rathod , Chen Sun +7 more
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this … The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-toapples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We present a unified implementation of the Faster R-CNN [30], R-FCN [6] and SSD [25] systems, which we view as meta-architectures and trace out the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures. On one extreme end of this spectrum where speed and memory are critical, we present a detector that achieves real time speeds and can be deployed on a mobile device. On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.
View PDF Chat

Aggregated Residual Transformations for Deep Neural Networks

2017-07-01
Saining Xie , Ross Girshick , Piotr Dollár +2 more
We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. … We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call cardinality (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy. Moreover, increasing cardinality is more effective than going deeper or wider when we increase the capacity. Our models, named ResNeXt, are the foundations of our entry to the ILSVRC 2016 classification task in which we secured 2nd place. We further investigate ResNeXt on an ImageNet-5K set and the COCO detection set, also showing better results than its ResNet counterpart. The code and models are publicly available online.
View PDF Chat