From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models.
Rongjie LiSongyang ZhangDahua LinKai ChenXuming HePublished in: CoRR (2024)
Keyphrases
- language model
- graph theory
- language modeling
- graph matching
- graph structure
- directed graph
- weighted graph
- graph databases
- spoken term detection
- input image
- graph mining
- out of vocabulary
- document retrieval
- probabilistic model
- n gram
- speech recognition
- information retrieval
- computer vision
- language modelling
- image regions
- retrieval model
- query expansion
- video sequences
- statistical language models
- connected components
- ad hoc information retrieval
- language models for information retrieval
- context sensitive
- vector space model
- pseudo relevance feedback
- web graph
- test collection
- query terms
- structured data
- bayesian networks
- language model for information retrieval
- relevance model
- document ranking
- broadcast news
- query specific
- retrieval effectiveness
- web search