Motion Aware Self-Supervision for Generic Event Boundary Detection
WACV(2023)
摘要
The task of Generic Event Boundary Detection (GEBD) aims to detect moments in videos that are naturally perceived by humans as generic and taxonomy-free event boundaries. Modeling the dynamically evolving temporal and spatial changes in a video makes GEBD a difficult problem to solve. Existing approaches involve very complex and sophisticated pipelines in terms of architectural design choices, hence creating a need for more straightforward and simplified approaches. In this work, we address this issue by revisiting a simple and effective self-supervised method and augment it with a differentiable motion feature learning module to tackle the spatial and temporal diversities in the GEBD task. We perform extensive experiments on the challenging Kinetics-GEBD and TAPOS datasets to demonstrate the efficacy of the proposed approach compared to the other self-supervised state-of-the-art methods. We also show that this simple self-supervised approach learns motion features without any explicit motion-specific pretext task. Our results can be reproduced on github.
更多查看译文
关键词
Algorithms: Video recognition and understanding (tracking,action recognition,etc.),Machine learning architectures,formulations,and algorithms (including transfer,low-shot,semi-,self-,and un-supervised learning)
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要