Vision transformers are emerging as a powerful tool to solve computer vision problems.
Recent techniques have also proven the efficacy of transformers beyond the image domain …

Understanding human behavior and activity facilitates advancement of numerous real-world
applications, and is critical for video analysis. Despite the progress of action recognition …

In action recognition, although the combination of spatio-temporal videos and skeleton
features can improve the recognition performance, a separate model and balancing feature …

With the exponential growth of video data, there is an urgent need for automated technology
to analyze and comprehend video content. However, existing video understanding models …

Transformer models have shown great success handling long-range interactions, making
them a promising tool for modeling video. However, they lack inductive biases and scale …

Current few-shot action recognition methods reach impressive performance by learning
discriminative features for each video via episodic training and designing various temporal …

Current state-of-the-art approaches for few-shot action recognition achieve promising
performance by conducting frame-level matching on learned visual features. However, they …

We propose a flow-guided transformer, which innovatively leverage the motion discrepancy
exposed by optical flows to instruct the attention retrieval in transformer for high fidelity video …

Streaming video recognition reasons about objects and their actions in every frame of a
video. A good streaming recognition model captures both long-term dynamics and short …

We address the problem of online action segmentation for egocentric procedural task
videos. While previous studies have mostly focused on offline action segmentation where …