Co-Attending Free-Form Regions and Detections With Multi-Modal Multiplicative Feature Embedding for Visual Question Answering.
Pan LuHongsheng LiWei ZhangJianyong WangXiaogang WangPublished in: AAAI (2018)
Keyphrases
- multi modal
- question answering
- free form
- cross modal
- video search
- image features
- single modality
- information retrieval
- natural language processing
- cross language
- question classification
- passage retrieval
- complex scenes
- information extraction
- high dimensional
- visual information
- natural language questions
- qa clef
- natural language
- feature set
- audio visual
- answering questions
- question answering systems
- syntactic information
- vector space
- multiple modalities
- semantic concepts
- image annotation
- image content
- document retrieval
- visual features
- feature vectors
- image processing
- artificial intelligence