Few-shot action recognition with implicit temporal alignment and pair similarity optimization.
Congqi CaoYajuan LiQinyi LvPeng WangYanning ZhangPublished in: Comput. Vis. Image Underst. (2021)
Keyphrases
- action recognition
- human actions
- activity recognition
- bag of words
- action classification
- human detection
- spatial temporal
- similarity measure
- recognition of human actions
- computer vision
- depth sensors
- human activities
- recognizing human actions
- semantic similarity
- body parts
- view invariant
- pairwise
- video sequences
- view invariant action recognition
- bag of features
- human pose
- action primitives
- video dataset
- recognizing actions
- video shots
- depth cameras
- static images
- key frames
- video data
- visual features
- feature extraction