SpatialRGPT: Grounded Spatial Reasoning in Vision Language Model.
An-Chieh ChengHongxu YinYang FuQiushan GuoRuihan YangJan KautzXiaolong WangSifei LiuPublished in: CoRR (2024)
Keyphrases
- language model
- spatial reasoning
- language modeling
- n gram
- spatial relations
- retrieval model
- computer vision
- query expansion
- probabilistic model
- information retrieval
- speech recognition
- mixture model
- language modelling
- document retrieval
- temporal reasoning
- test collection
- context sensitive
- statistical language models
- topological relations
- qualitative spatial reasoning
- word clouds
- smoothing methods
- translation model
- query specific
- image processing
- unsupervised learning