M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition.
Hao TangJun LiuShuanglin YanRui YanZechao LiJinhui TangPublished in: ACM Multimedia (2023)
Keyphrases
- fine grained
- multi view
- action recognition
- view invariant
- single view
- bag of words
- human actions
- multiple views
- activity recognition
- access control
- computer vision
- three dimensional
- depth map
- dynamic scenes
- d objects
- multiple cameras
- range images
- body parts
- video sequences
- image matching
- semi supervised
- surface reconstruction
- feature points
- human activities
- video content
- motion capture
- visual hull
- view synthesis