UntrimmedNets for Weakly Supervised Action Recognition and Detection
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2017)
摘要
Current action recognition methods heavily rely on trimmed videos for model training. However, it is expensive and time-consuming to acquire a large-scale trimmed video dataset. This paper presents a new weakly supervised architecture, called UntrimmedNet, which is able to directly learn action recognition models from untrimmed videos without the requirement of temporal annotations of action instances. Our UntrimmedNet couples two important components, the classification module and the selection module, to learn the action models and reason about the temporal duration of action instances, respectively. These two components are implemented with feed-forward networks, and UntrimmedNet is therefore an end-to-end trainable architecture. We exploit the learned models for action recognition (WSR) and detection (WSD) on the untrimmed video datasets of THUMOS14 and ActivityNet. Although our UntrimmedNet only employs weak supervision, our method achieves performance superior or comparable to that of those strongly supervised approaches on these two datasets.
更多查看译文
关键词
weakly supervised action recognition,weakly supervised architecture,UntrimmedNet,action detection,feed-forward networks,end-to-end trainable architecture,selection module,classification module,untrimmed videos
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络