Projects

Context-aware RCNN: A baseline for action detection in videos. ECCV 2020.
[paper] [code]

Optical flow guided feature: A fast and robust motion representation for video action recognition. CVPR 2018.
[paper] [code]

An efficient and effective motion representation to replace optical flow.

Temporal sequence distillation: Towards few-frame action recognition in videos. ACM MM 2018.
[paper]

Video Analytics Software as a Service (VA SaaS) has been rapidly growing in recent years. VA SaaS is typically accessed by users using a lightweight client. Because the transmission bandwidth between the client and cloud is usually limited and expensive, it brings great benefits to design cloud video analysis algorithms with a limited data transmission requirement. As the first attempt in this direction, this work introduces a problem of few-frame action recognition, which aims at maintaining high recognition accuracy, when accessing only a few frames during both training and test.

Extractive video summarizer with memory augmented neural networks. ACM MM 2018.

Humans usually create a summary after viewing and understanding the whole video, and the global attention mechanism capturing information from all video frames plays a key role in the summarization process. Motivated by this observation, we proposed a memory augmented extractive video summarizer, which utilizes an external memory to record visual information of the whole video with high capacity. With the external memory, the video summarizer simply predicts the importance score of a video shot based on the global understanding of the video frames.

Fast video shot transition localization with deep structured models. ACCV 2018.
[paper]

A deep learning approach to detect both cut transitions and gradual transitions for shot boundary detection.