SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition.
Wenbo HuangJinghui ZhangXuwei QianZhen WuMeng WangLei ZhangPublished in: CoRR (2024)
Keyphrases
- action recognition
- human actions
- spatio temporal
- spatial temporal
- action recognition in videos
- spatio temporal interest points
- view invariant
- video shots
- recognition of human actions
- video sequences
- bag of words
- human detection
- recognizing human actions
- video database
- computer vision
- activity recognition
- visual features
- spatial and temporal
- human activities
- bag of features
- action classification
- recognizing actions
- body parts
- moving objects
- space time
- depth sensors
- image sequences
- video content
- independent subspace analysis
- video data
- depth cameras
- static images
- human pose
- key frames