Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions?
Abhishek DasHarsh AgrawalLarry ZitnickDevi ParikhDhruv BatraPublished in: EMNLP (2016)
Keyphrases
- question answering
- visual stimuli
- information extraction
- information retrieval
- natural language
- syntactic information
- natural language processing
- question classification
- qa clef
- visual information
- relation extraction
- question answering systems
- passage retrieval
- named entities
- cross language
- sentence retrieval
- natural language questions
- semantic roles
- visual features
- eye movements
- open domain question answering
- n gram
- multi modal
- knowledge representation
- answering questions
- answer validation