UniFormer: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View.
Zequn QinJingyu ChenChao ChenXiaozhi ChenXi LiPublished in: CoRR (2022)
Keyphrases
- multi view
- spatial temporal
- multiple views
- single view
- multiple viewpoints
- d objects
- spatial and temporal
- three dimensional
- depth map
- action recognition
- view dependent
- video shots
- range images
- semi supervised
- view synthesis
- viewpoint
- temporal information
- multi view learning
- multi view clustering
- spatio temporal
- image representation
- visual hull
- image classification
- multi view images
- video retrieval
- eye movements
- supervised learning
- computer vision
- multi view face detection
- learning algorithm