Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts.
Övgü ÖzdemirErdem AkagündüzPublished in: CoRR (2024)
Keyphrases
- question answering
- question classification
- question answering systems
- image content
- answer extraction
- qa clef
- image retrieval
- natural language questions
- low level
- image features
- open domain question answering
- qa systems
- visual features
- answer validation
- image representation
- answering questions
- natural language
- natural language processing
- information extraction
- candidate answers
- visual information
- named entities
- image classification
- visual data
- passage retrieval
- cross language
- visual content
- image collections
- sentence retrieval
- relation extraction
- data mining
- information retrieval
- machine learning
- document retrieval
- probabilistic model