MouSi: Poly-Visual-Expert Vision-Language Models.
Xiaoran FanTao JiChanghao JiangShuo LiSenjie JinSirui SongJunke WangBoyang HongLu ChenGuodong ZhengMing ZhangCaishuang HuangRui ZhengZhiheng XiYuhao ZhouShihan DouJunjie YeHang YanTao GuiQi ZhangXipeng QiuXuanjing HuangZuxuan WuYu-Gang JiangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- speech recognition
- language modelling
- information retrieval
- query expansion
- statistical language models
- computer vision
- language model for information retrieval
- retrieval model
- okapi bm
- ad hoc information retrieval
- query terms
- visual information
- translation model
- test collection
- vector space model
- pseudo relevance feedback
- language models for information retrieval
- relevance model
- term dependencies
- visual features
- information retrieval systems