Multimodal Network Embedding via Attention based Multi-view Variational Autoencoder.
Feiran HuangXiaoming ZhangChaozhuo LiZhoujun LiYueying HeZhonghua ZhaoPublished in: ICMR (2018)
Keyphrases
- multi view
- single view
- multiple views
- d objects
- depth map
- camera calibration
- multi view stereo
- scene reconstruction
- view synthesis
- semi supervised
- range images
- surface reconstruction
- multi view face detection
- multi view reconstruction
- three dimensional
- co training
- multiple viewpoints
- multiple cameras
- light field
- viewpoint
- free viewpoint
- multi view images
- d scene
- motion vectors
- visual hull
- optical flow
- high quality
- image segmentation