# From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

> Research article (2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024) · cited 33× · AI/ML

**Wikidata**: [openalex:W4402727824](https://www.wikidata.org/wiki/openalex:W4402727824)  
**Source**: https://4ort.xyz/entity/from-pixels-to-graphs-open-vocabulary-scene-graph-generation-with-vision-language-models