What's "up" with vision-language models? Investigating their struggle with spatial reasoning.
Amita KamathJack HesselKai-Wei ChangPublished in: CoRR (2023)
Keyphrases
- spatial reasoning
- language model
- language modeling
- n gram
- spatial relations
- probabilistic model
- document retrieval
- speech recognition
- information retrieval
- temporal reasoning
- language modelling
- query expansion
- retrieval model
- language models for information retrieval
- computer vision
- test collection
- statistical language models
- spatial knowledge
- smoothing methods
- directional relations
- pseudo relevance feedback
- context sensitive
- topological relations
- mixture model
- translation model
- relevance model
- document ranking
- bag of words
- spoken term detection
- machine learning
- search engine
- knn
- expectation maximization