ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation.
Yangyi ChenXingyao WangManling LiDerek HoiemHeng JiPublished in: CoRR (2023)
Keyphrases
- knowledge extraction
- visual perception
- knowledge discovery
- textual documents
- visual representation
- data mining
- systems engineering
- information retrieval
- computer vision
- low level
- visual properties
- visual processing
- real time
- databases
- visual field
- visual representations
- medical databases
- visual information
- human vision
- spatial relations
- image representation
- visual features
- vision system
- source code
- rough sets
- image processing
- perceptual information