Selective Volume Mixup for Video Action Recognition.
Yi TanZhaofan QiuYanbin HaoTing YaoXiangnan HeTao MeiPublished in: CoRR (2023)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- recognition of human actions
- static images
- motion features
- spatio temporal interest points
- recognizing human actions
- activity recognition
- human activities
- space time interest points
- bag of words
- mid level
- computer vision
- human detection
- video data
- video frames
- video content
- space time
- motion capture data
- video sequences
- motion history images
- motion recognition
- atomic actions
- depth sensors
- body parts
- human motion
- multimedia
- action primitives
- bag of features
- view invariant
- video shots
- video analysis
- event detection
- spatial and temporal
- global features
- recognizing actions
- temporal information
- spatio temporal
- view invariant action recognition