{"slug": "relateanything-real-time-open-vocabulary-relation-prediction-from-any-inputs", "title": "RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs", "summary": "A new system called RelateAnything performs real-time open-vocabulary relation prediction from any inputs, according to the research announcement. The work targets a gap in scene-graph modeling, where models remain trained and evaluated on the fixed 50 or 56 predicates of a single annotation set even as open-vocabulary detection and promptable segmentation have moved the taxonomy out of the model and into the input. The system extends the open-vocabulary paradigm from detection and segmentation to relation prediction.", "body_md": "Open-vocabulary detection accepts any class list at inference, and promptable segmentation returns regions without class names: the taxonomy has left the model and become an input. Relation prediction has not. Scene-graph models are still trained and evaluated on the 50 or 56 predicates of one annot", "url": "https://wpnews.pro/news/relateanything-real-time-open-vocabulary-relation-prediction-from-any-inputs", "canonical_source": "https://aiflash.com/news/120845/", "published_at": "2026-09-16 17:30:00+00:00", "updated_at": "2026-09-16 17:41:08.437169+00:00", "lang": "en", "topics": ["computer-vision", "artificial-intelligence", "ai-research", "machine-learning"], "entities": ["RelateAnything"], "alternates": {"html": "https://wpnews.pro/news/relateanything-real-time-open-vocabulary-relation-prediction-from-any-inputs", "markdown": "https://wpnews.pro/news/relateanything-real-time-open-vocabulary-relation-prediction-from-any-inputs.md", "text": "https://wpnews.pro/news/relateanything-real-time-open-vocabulary-relation-prediction-from-any-inputs.txt", "jsonld": "https://wpnews.pro/news/relateanything-real-time-open-vocabulary-relation-prediction-from-any-inputs.jsonld"}}