ViTA: Visual-Linguistic Translation by Aligning Object Tags.
Kshitij GuptaDevansh GautamRadhika MamidiPublished in: WAT@ACL/IJCNLP (2021)
Keyphrases
- visual objects
- visual appearance
- web objects
- spatial relations
- complex objects
- visual concepts
- visual properties
- visual information
- visual scene
- keywords
- visual input
- data objects
- natural language processing
- d objects
- visual perception
- web resources
- syntactic analysis
- contextual cues
- spatial configurations
- part of speech
- cross language information retrieval
- object model
- object tracking
- image regions
- visual features
- vision system
- low level
- natural language