Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition.
Unaiza AhsanRishi MadhokIrfan A. EssaPublished in: WACV (2019)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- unsupervised learning
- space time
- video dataset
- action detection
- recognizing human actions
- video sequences
- static images
- activity recognition
- recognition of human actions
- video content
- video data
- spatial and temporal
- video streams
- human activities
- video frames
- human detection
- bag of words
- body parts
- human pose
- video clips
- video retrieval
- motion features
- human activity recognition
- motion history images
- space time interest points
- event recognition
- multimedia
- mid level
- temporal structure
- video analysis
- machine learning
- video surveillance
- key frames
- event detection
- temporal information