CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection.

Yang Cao Yihan Zeng Hang Xu Dan Xu

Published in: NeurIPS (2023)

Keyphrases

d objects
cross modal
pose normalization
multi modal
object recognition
multi view
viewpoint
multiple views
minimum bounding
pose estimation
shape descriptors
three dimensional
multimedia retrieval
object detection
object classes
cad models
visual recognition
multimedia databases
multimedia
keywords