SVFormer: Semi-supervised Video Transformer for Action Recognition.
Zhen XingQi DaiHan HuJingjing ChenZuxuan WuYu-Gang JiangPublished in: CVPR (2023)
Keyphrases
- action recognition
- human actions
- semi supervised
- action classification
- action detection
- video dataset
- spatial temporal
- recognizing human actions
- motion features
- recognition of human actions
- static images
- space time interest points
- human activities
- bag of words
- activity recognition
- mid level
- human detection
- body parts
- video data
- computer vision
- semi supervised learning
- video sequences
- view invariant
- motion history images
- bag of features
- video content
- recognizing actions
- pairwise
- human pose
- multimedia
- atomic actions
- machine learning
- depth sensors
- active learning
- labeled data
- video streams
- video frames
- human activity recognition
- image features
- event recognition
- human computer interaction
- key frames
- space time