Self-Chained Image-Language Model for Video Localization and Question Answering.
Shoubin YuJaemin ChoPrateek YadavMohit BansalPublished in: NeurIPS (2023)
Keyphrases
- question answering
- language model
- passage retrieval
- information retrieval
- language modeling
- sentence retrieval
- retrieval model
- probabilistic model
- image content
- n gram
- natural language
- image retrieval
- image classification
- named entities
- multimedia
- natural language processing
- speech recognition
- document retrieval
- cross language
- visual data
- relevance model
- information extraction
- text categorization
- query expansion
- query terms
- video retrieval
- vector space model
- statistical machine translation
- hidden markov models