Causality-aware Visual Scene Discovery for Cross-Modal Question Reasoning.
Yang LiuGuanbin LiLiang LinPublished in: CoRR (2023)
Keyphrases
- cross modal
- visual scene
- multi modal
- perceptual information
- visual attention
- vision system
- multimedia retrieval
- complex scenes
- visual recognition
- image retrieval
- object recognition
- natural images
- visual similarity
- visual information
- multimedia databases
- knowledge base
- natural scenes
- spatial relations
- visual data
- image collections
- visual features
- multiscale
- machine learning