Knowledge-aware image understanding with multi-level visual representation enhancement for visual question answering.
Feng YanZhe LiWushour SilamuYanbing LiPublished in: Mach. Learn. (2024)
Keyphrases
- image understanding
- question answering
- visual representation
- visual representations
- syntactic information
- information extraction
- natural language
- information retrieval
- question classification
- computer vision
- user interface
- domain knowledge
- object recognition
- question answering systems
- named entities
- natural language processing
- qa clef
- image processing
- image segmentation
- object detection
- knowledge base
- image annotation
- cross language
- qa systems
- passage retrieval
- sentence retrieval
- open domain question answering
- visual information
- multi modal
- multi class
- knowledge representation
- image analysis
- artificial intelligence
- semantic information
- training data
- answer validation
- data mining