SkillCLIP: Skill Aware Modality Fusion Visual Question Answering (Student Abstract).
Atharva NaikYash Parag ButalaNavaneethan VaikunthanRaghav KapoorPublished in: AAAI (2024)
Keyphrases
- question answering
- information extraction
- natural language processing
- low level
- question classification
- high level
- natural language
- visual information
- open domain question answering
- multi modal
- question answering systems
- cross language
- information retrieval
- passage retrieval
- visual features
- qa clef
- natural language questions
- syntactic information
- named entities
- answer validation
- relation extraction
- candidate answers
- answer extraction
- sentence retrieval
- qa systems
- textual entailment recognition
- artificial intelligence