Breaking video into pieces for action recognition.
Ying ZhengHongxun YaoXiaoshuai SunXuesong JiangFatih PorikliPublished in: Multim. Tools Appl. (2017)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- action detection
- video dataset
- recognition of human actions
- recognizing human actions
- motion features
- activity recognition
- bag of words
- static images
- space time interest points
- human activities
- spatio temporal interest points
- human detection
- computer vision
- mid level
- video sequences
- motion history images
- event recognition
- video data
- view invariant
- spatio temporal
- video streams
- body parts
- human motion
- video content
- space time
- human pose
- video frames
- action primitives
- three dimensional
- multimedia
- view invariant action recognition
- atomic actions
- max margin
- video images
- bag of features
- video analysis
- video surveillance