Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision.
Xiaoyu ZhangHaichao ShiChangsheng LiKai ZhengXiaobin ZhuLixin DuanPublished in: AAAI (2019)
Keyphrases
- action recognition
- human actions
- action classification
- recognition of human actions
- video dataset
- bag of words
- recognizing actions
- human activities
- recognizing human actions
- computer vision
- static images
- body parts
- activity recognition
- human detection
- spatial temporal
- view invariant
- spatio temporal interest points
- human body