Visual Genome: densely grounded scene graphs and language

What changed

Collected region descriptions, object/attribute/relationship annotations and question-answer pairs grounded to natural images, canonicalizing language concepts with WordNet to support structured vision-language research.

Scientific scope

Collected region descriptions, object/attribute/relationship annotations and question-answer pairs grounded to natural images, canonicalizing language concepts with WordNet to support structured vision-language research. Reuses images from existing datasets and inherits scene-graph/WordNet ideas; new contribution is the dense annotation resource and grounding pipeline. Dataset annotations are not complete formal truth about all scenes or evidence that models attain comprehensive understanding.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Reuses images from existing datasets and inherits scene-graph/WordNet ideas; new contribution is the dense annotation resource and grounding pipeline. Dataset annotations are not complete formal truth about all scenes or evidence that models attain comprehensive understanding.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction