Differentiable Parsing and Visual Grounding of Natural Language Instructions for Object Placement.
Zirui ZhaoWee Sun LeeDavid HsuPublished in: ICRA (2023)
Keyphrases
- natural language
- natural language processing
- visual objects
- spatial relations
- d objects
- visual features
- visual appearance
- highly ambiguous
- visual properties
- syntactic structures
- machine learning
- language understanding
- natural language parsing
- visual input
- language processing
- semantic representation
- natural language understanding
- natural language sentences
- real world objects
- semantic interpretation
- high level
- multiple objects
- object model
- complex objects
- visual information
- object tracking
- knowledge representation
- low level
- objective function
- computer programs
- natural language interface
- visual scene
- moving objects