I Know About "Up"! Enhancing Spatial Reasoning in Visual Language Models Through 3D Reconstruction.
Zaiqiao MengHao ZhouYifang ChenPublished in: CoRR (2024)
Keyphrases
- language model
- spatial reasoning
- spatial relations
- language modeling
- n gram
- probabilistic model
- document retrieval
- query expansion
- retrieval model
- spatial knowledge
- information retrieval
- topological relations
- language modelling
- speech recognition
- test collection
- temporal reasoning
- directional relations
- context sensitive
- vector space model
- mixture model
- high level
- computer vision
- statistical language models
- pseudo relevance feedback
- visual information
- visual features
- translation model
- similarity search
- low level
- image sequences
- language models for information retrieval