Differentiable Parsing and Visual Grounding of Verbal Instructions for Object Placement.
Zirui ZhaoWee Sun LeeDavid HsuPublished in: CoRR (2022)
Keyphrases
- visual objects
- visual appearance
- natural language
- d objects
- complex objects
- spatial relations
- visual properties
- category specific
- low level
- multiple objects
- object model
- object description
- visual features
- moving objects
- object segmentation
- spatial relationships
- object tracking
- dependency parsing
- keypoints
- linguistic analysis
- information extraction
- objective function