Deep Local Video Feature for Action Recognition.
Zhen-Zhong LanYi ZhuAlexander G. HauptmannShawn D. NewsamPublished in: CVPR Workshops (2017)
Keyphrases
- action recognition
- spatio temporal interest points
- motion features
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- recognition of human actions
- bag of words
- mid level features
- activity recognition
- human activities
- static images
- recognizing human actions
- computer vision
- recognizing actions
- space time interest points
- human detection
- mid level
- view invariant
- body parts
- video data
- depth sensors
- motion history images
- global features
- video streams
- motion capture data
- video sequences
- multimedia
- bag of features
- video frames
- spatio temporal
- temporal structure
- atomic actions
- video images
- human pose
- video surveillance
- video content
- action recognition in videos
- feature vectors
- view invariant action recognition