Implicitly using Human Skeleton in Self-supervised Learning: Influence on Spatio-temporal Puzzle Solving and on Video Action Recognition.
Mathieu RiandLaurent DolléPatrick Le CalletPublished in: ROBOVIS (2021)
Keyphrases
- action recognition
- human actions
- spatio temporal interest points
- spatio temporal
- static images
- spatial temporal
- action classification
- video dataset
- bag of words
- human activities
- activity recognition
- recognition of human actions
- temporal information
- space time
- spatial and temporal
- human movements
- human detection
- max margin
- multimedia
- action detection
- view invariant
- recognizing actions
- action recognition in videos
- video sequences
- recognizing human actions
- video images
- image sequences
- temporal structure
- motion features
- structured prediction
- video analysis
- video data