VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments.
Bufang YangLixing HeKaiwei LiuZhenyu YanPublished in: CoRR (2024)
Keyphrases
- multi modal
- language model
- language modeling
- probabilistic model
- multi modality
- n gram
- information retrieval
- language modelling
- speech recognition
- retrieval model
- statistical language models
- document retrieval
- query expansion
- audio visual
- cross modal
- high dimensional
- test collection
- video search
- recommender systems
- document ranking
- spoken term detection
- uni modal
- single modality
- language models for information retrieval
- smoothing methods
- user ratings
- image annotation
- query terms
- co occurrence
- image retrieval