Multi-Modal Human Action Recognition With Sub-Action Exploiting and Class-Privacy Preserved Collaborative Representation Learning.
Chengwu LiangDeyin LiuLin QiLing GuanPublished in: IEEE Access (2020)
Keyphrases
- multi modal
- action recognition
- recognizing human actions
- human actions
- recognition of human actions
- view invariant
- spatio temporal interest points
- multi modality
- bag of words
- recognizing actions
- action classification
- cross modal
- action detection
- computer vision
- human detection
- activity recognition
- action models
- semantic concepts
- max margin
- static images
- video search
- action primitives
- human activities
- action recognition in videos
- image segmentation