Ask a Question

Prefer a chat interface with context about you and your work?

Action recognition with trajectory-pooled deep-convolutional descriptors

Action recognition with trajectory-pooled deep-convolutional descriptors

Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted features and deep-learned features. Specifically, we utilize deep architectures to learn discriminative convolutional feature maps, and conduct trajectory-constrained pooling …