Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models.
Qiji ZhouRuochen ZhouZike HuPanzhong LuSiyang GaoYue ZhangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- image data
- low level
- image retrieval
- image features
- probabilistic model
- image classification
- document retrieval
- speech recognition
- visual data
- n gram
- information retrieval
- image content
- image regions
- query expansion
- statistical language models
- retrieval model
- image collections
- context sensitive
- language models for information retrieval
- language modelling
- language model for information retrieval
- pseudo relevance feedback
- vector space model
- bag of words
- image representation
- visual features