See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data.
Yuhang LuQi JiangRunnan ChenYuenan HouXinge ZhuYuexin MaPublished in: ICCV (2023)
Keyphrases
- multi modal
- visual data
- point cloud
- audio visual
- high dimensional
- cross modal
- visual information
- structure from motion
- image segmentation
- visual features
- video data
- point sets
- image data
- medical images
- multimedia data
- image sequences
- contextual information
- high dimensional data
- video sequences
- image content
- human motion
- medical imaging
- low level
- human actions
- data sets