VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering.
Ekta SoodFabian KögelFlorian StrohmPrajit DharAndreas BullingPublished in: CoRR (2021)
Keyphrases
- question answering
- information retrieval
- named entities
- information extraction
- open domain question answering
- question classification
- multi modal
- natural language
- cross language
- visual information
- visual attention
- natural language processing
- qa clef
- answer validation
- document retrieval
- eye movements
- passage retrieval
- syntactic information
- low level