← Wednesday, September 30, 2026Models & trainingPaper

Grounded Entity Biographies link the same objects across long videos

huggingface.co by Hui Ren et al. Editor score 8/10

GEB groups visually grounded observations of individual objects into retrievable biographies and supplements episodic evidence during question answering; it reports 72.0% on EgoLifeQA, 4.4 points above the best published result. Identity-linked memory offers a concrete way to retrieve long-range visual context.

What

Grounded Entity Biographies (GEB) groups visually grounded observations of the same physical entity across clips into retrievable long-video memory.

Method

During question answering, the system retrieves an entity biography alongside episodic evidence, using identity links formed during memory construction.

Why it matters

Linking object identity across events helps models answer questions about long videos when descriptions alone cannot distinguish or connect physical instances.

Read on huggingface.co → Code · 20 stars

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.