DVANet: Disentangling View and Action Features for Multi-View Action Recognition.
Nyle SiddiquiPraveen TirupatturMubarak ShahPublished in: AAAI (2024)
Keyphrases
- multi view
- view invariant
- action recognition
- multiple views
- human actions
- single view
- multiple viewpoints
- recognizing human actions
- action classification
- depth map
- d objects
- recognizing actions
- space time interest points
- multiple cameras
- recognition of human actions
- semi supervised
- motion history images
- three dimensional
- feature vectors
- computer vision
- feature extraction
- view synthesis
- image features
- activity recognition
- human pose
- action detection
- motion capture
- human motion
- spatio temporal
- similarity measure
- body parts