Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection.
Yang CaoYihan ZengHang XuDan XuPublished in: CoRR (2024)
Keyphrases
- d objects
- cross modal
- pose normalization
- multi modal
- multi view
- multiple views
- viewpoint
- object recognition
- pose estimation
- minimum bounding
- three dimensional
- cad models
- shape descriptors
- object classes
- visual recognition
- object detection
- multimedia retrieval
- image retrieval
- multimedia databases
- computer vision
- shape model
- machine learning