Recurring the Transformer for Video Action Recognition.
Jiewen YangXingbo DongLiujun LiuChao ZhangJiajun ShenDahai YuPublished in: CVPR (2022)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- recognition of human actions
- recognizing human actions
- space time interest points
- static images
- motion features
- spatio temporal interest points
- bag of words
- computer vision
- activity recognition
- human activities
- human detection
- mid level
- video sequences
- multimedia
- motion history images
- bag of features
- video streams
- video clips
- video data
- view invariant
- recognizing actions
- space time
- spatio temporal
- video retrieval
- video content
- human activity recognition
- human pose
- body parts
- action primitives
- three dimensional
- key frames
- spatial and temporal