Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?
Abhishek DasHarsh AgrawalC. Lawrence ZitnickDevi ParikhDhruv BatraPublished in: CoRR (2016)
Keyphrases
- question answering
- visual stimuli
- information retrieval
- information extraction
- question classification
- natural language
- qa clef
- named entities
- question answering systems
- natural language processing
- natural language questions
- syntactic information
- passage retrieval
- open domain question answering
- relation extraction
- cross language
- eye movements
- visual features
- visual attention
- answering questions
- multi modal
- text classification