Enhancing Multi-modal Features Using Local Self-attention for 3D Object Detection.
Hao LiZehan ZhangXian ZhaoYulong WangYuxi ShenShiliang PuHui MaoPublished in: ECCV (10) (2022)
Keyphrases
- multi modal
- d objects
- object features
- viewpoint
- range data
- multi view
- audio visual
- cross modal
- shape descriptors
- object recognition
- partial matching
- multi modality
- feature vectors
- multiple views
- multi views
- object representation
- pose estimation
- feature space
- feature extraction
- three dimensional
- d mesh
- physically plausible
- object model
- object detection
- three dimensional objects
- image features
- high dimensional
- cad models
- image segmentation