Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models.
Jiayu WangYifei MingZhenmei ShiVibhav VineetXin WangNeel JoshiPublished in: CoRR (2024)
Keyphrases
- spatial reasoning
- language model
- n gram
- language modeling
- out of vocabulary
- statistical language modeling
- multiword
- document retrieval
- translation model
- probabilistic model
- temporal reasoning
- speech recognition
- language modelling
- spatial relations
- query expansion
- retrieval model
- computer vision
- information retrieval
- context sensitive
- bag of words
- test collection
- document level
- topological relations
- vector space model
- mixture model
- relevance model
- statistical language models
- pseudo relevance feedback
- keywords
- language models for information retrieval
- smoothing methods
- query terms
- text classification
- pairwise
- search engine