Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition.
Hao TangJun LiuShuanglin YanRui YanZechao LiJinhui TangPublished in: CoRR (2023)
Keyphrases
- fine grained
- multi view
- action recognition
- view invariant
- single view
- human actions
- multiple views
- activity recognition
- depth map
- d objects
- bag of words
- access control
- dynamic scenes
- three dimensional
- body parts
- semi supervised
- range images
- computer vision
- multiple viewpoints
- keypoints
- video data
- motion capture
- view synthesis
- image matching
- video sequences
- multiple cameras
- visual features
- human activities
- pairwise
- image sequences