Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching.
Jiazheng XingMengmeng WangYudi RuanBofan ChenYaowei GuoBoyu MuGuang DaiJingdong WangYong LiuPublished in: CoRR (2023)
Keyphrases
- action recognition
- human actions
- activity recognition
- human detection
- bag of words
- computer vision
- recognition of human actions
- action classification
- spatial temporal
- video sequences
- body parts
- recognizing human actions
- image matching
- video shots
- static images
- bag of features
- human pose
- human activities
- depth sensors
- recognizing actions
- keypoints
- action primitives
- human body
- mid level
- video dataset
- depth cameras
- feature points
- action detection
- graph structure
- text classification
- view invariant action recognition