Temporal sparse feature auto-combination deep network for video action recognition.
Qicong WangDingxi GongMan QiYehu ShenYunqi LeiPublished in: Concurr. Comput. Pract. Exp. (2018)
Keyphrases
- action recognition
- spatio temporal interest points
- spatial temporal
- human actions
- spatio temporal
- motion features
- action classification
- motion history images
- video dataset
- action detection
- recognition of human actions
- recognizing human actions
- bag of words
- spatial and temporal
- activity recognition
- human activities
- human detection
- static images
- computer vision
- space time interest points
- body parts
- space time
- temporal information
- bag of features
- atomic actions
- multimedia
- depth sensors
- mid level
- temporal structure
- video frames
- video retrieval
- feature vectors
- video sequences
- view invariant
- mid level features
- video surveillance
- recognizing actions
- motion recognition
- global features
- optical flow
- action recognition in videos