Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition

One-Shot Action Localization by Learning Sequence Matching Network

2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning

Temporal Hallucinating for Action Recognition With Few Still Images

Im2Flow: Motion Hallucination From Static Images for Action Recognition

Compressed Video Action Recognition

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

A Closer Look at Spatiotemporal Convolutions for Action Recognition

Recognize Actions by Disentangling Components of Dynamics

Temporal Deformable Residual Networks for Action Segmentation in Videos

Pulling Actions out of Context: Explicit Separation for Effective Combination

What Have We Learned From Deep Representations for Action Recognition?

Towards Universal Representation for Unseen Action Recognition

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?