Multi-modal Contextual Graph Neural Network for Text Visual Question Answering.
Yaoyuan LiangXin WangXuguang DuanWenwu ZhuPublished in: ICPR (2020)
Keyphrases
- multi modal
- question answering
- video search
- cross modal
- syntactic information
- information retrieval
- multiple modalities
- text summarization
- information extraction
- natural language processing
- single modality
- passage retrieval
- audio visual
- question classification
- qa clef
- textual entailment recognition
- visual information
- structured data
- natural language
- question answering systems
- text mining
- named entities
- semantic concepts
- text documents
- natural language questions
- cross language
- high dimensional
- visual features
- high level
- feature extraction
- semantic roles
- news video
- contextual information
- relation extraction
- image annotation
- text retrieval
- graph cuts
- document retrieval
- question answer pairs
- machine learning