ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding.
Ziyang LuYunqiang PeiGuoqing WangYang YangZheng WangHeng Tao ShenPublished in: CoRR (2023)
Keyphrases
- visual data mining
- visual information
- user friendly
- visual representations
- virtual reality
- low level
- visual cues
- visual representation
- high level
- intelligent systems
- parallel coordinates
- multimedia
- situated agents
- information visualization
- visual perception
- reference frame
- visual data
- visual features
- object recognition