MVFNet: Multi-View Fusion Network for Efficient Video Recognition.
Wenhao WuDongliang HeTianwei LinFu LiChuang GanErrui DingPublished in: CoRR (2020)
Keyphrases
- multi view
- dynamic scenes
- multiple views
- single view
- d objects
- depth video
- free viewpoint
- stereo video
- depth map
- camera calibration
- object recognition
- multiple cameras
- semi supervised
- multi view learning
- three dimensional
- co training
- scene reconstruction
- multi view images
- multi view clustering
- multi view reconstruction
- video data
- multi view face detection
- cross view action recognition
- multi view stereo
- video content
- human activities
- range images
- video sequences
- view synthesis
- action recognition
- viewpoint
- feature extraction