CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection.
Yang CaoYihan ZengHang XuDan XuPublished in: CoRR (2023)
Keyphrases
- d objects
- cross modal
- multi modal
- pose normalization
- multi view
- viewpoint
- object recognition
- minimum bounding
- pose estimation
- multiple views
- multimedia retrieval
- cad models
- three dimensional
- object detection
- shape descriptors
- visual recognition
- multimedia databases
- object classes
- multi views
- image retrieval
- image sequences
- visual similarity
- low level