SAViR-T: Spatially Attentive Visual Reasoning with Transformers.
Pritish SahuKalliopi BasiotiVladimir PavlovicPublished in: ECML/PKDD (3) (2022)
Keyphrases
- visual motion
- visual information
- visual perception
- spatial reasoning
- visual features
- knowledge base
- visual analysis
- pre attentive
- formal models
- reasoning systems
- visual attention
- knowledge representation
- spatial relations
- visual processing
- low level
- model based reasoning
- deductive reasoning
- neural network
- visual cues
- reasoning process
- visual representations
- learning algorithm