Cross-Modal Retrieval for Knowledge-Based Visual Question Answering.
Paul LernerOlivier FerretCamille GuinaudeauPublished in: ECIR (1) (2024)
Keyphrases
- cross modal
- question answering
- multi modal
- multimedia retrieval
- information retrieval
- multimedia databases
- passage retrieval
- visual similarity
- image retrieval
- natural language processing
- information extraction
- natural language
- visual data
- question answering systems
- named entities
- content based retrieval
- multimedia
- semantic similarity
- knn
- object recognition
- visual features
- language model
- image database
- low level