Share-and-Chat: Achieving Human-Level Video Commenting by Search and Multi-View Embedding.
Yehao LiTing YaoTao MeiHongyang ChaoYong RuiPublished in: ACM Multimedia (2016)
Keyphrases
- multi view
- human level
- dynamic scenes
- single view
- free viewpoint
- depth video
- multiple views
- three dimensional
- d objects
- depth map
- machine intelligence
- artificial general intelligence
- video sequences
- semi supervised
- intelligent systems
- human intelligence
- video data
- visual hull
- multi view face detection
- multi view clustering
- view synthesis
- web intelligence
- video content
- multi view learning
- video frames
- image sequences
- artificial intelligence
- multi view video coding
- real time