SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition.
Bruno KorbarDu TranLorenzo TorresaniPublished in: CoRR (2019)
Keyphrases
- action recognition
- video database
- human actions
- action classification
- spatial temporal
- video dataset
- recognizing human actions
- action detection
- static images
- bag of words
- activity recognition
- computer vision
- motion features
- recognition of human actions
- video data
- human activities
- space time interest points
- video clips
- human detection
- mid level
- multimedia
- depth sensors
- spatio temporal
- human pose
- video analysis
- view invariant
- view invariant action recognition
- video shots
- body parts
- low level features
- video content
- atomic actions
- key frames
- visual words
- video streams