Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition.
Unaiza AhsanRishi MadhokIrfan A. EssaPublished in: CoRR (2018)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- space time
- action detection
- video dataset
- video sequences
- unsupervised learning
- recognizing human actions
- static images
- spatial and temporal
- motion features
- video data
- human activities
- computer vision
- multimedia
- supervised learning
- bag of words
- activity recognition
- video frames
- spatio temporal
- mid level
- space time interest points
- video content
- video images
- video streams
- video analysis
- video search
- human detection
- bag of features
- image classification
- action primitives
- video clips