VQA-GNN: Reasoning with Multimodal Semantic Graph for Visual Question Answering.
Yanan WangMichihiro YasunagaHongyu RenShinya WadaJure LeskovecPublished in: CoRR (2022)
Keyphrases
- question answering
- answering questions
- natural language processing
- information retrieval
- named entities
- natural language
- image database
- syntactic information
- relation extraction
- cross language
- information extraction
- question answering systems
- visual information
- question classification
- natural language questions
- passage retrieval
- qa clef
- low level
- multi modal
- visual features
- knowledge base
- sentence retrieval
- knowledge representation
- answer validation
- semantic roles
- high level
- qa systems
- audio visual
- document retrieval
- information retrieval systems
- relevance feedback
- data mining