Grounded Entity Biographies（GEB）：用实体传记增强长视频记忆

View PDF HTML (experimental)

Abstract:Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions and text-derived entities can leave physical identity unresolved: different objects may share a description, while observations of the same object remain disconnected across events. Retrieving relevant events therefore does not necessarily recover the "biography" of the particular entity a question concerns. To address this, we introduce Grounded Entity Biographies (GEB), a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographies while preserving the context of each moment. During question answering, the biography is retrieved alongside episodic evidence, allowing the model to follow an entity through events using identity links established during memory construction. Evaluations across four benchmarks, including day-long and week-long recordings, demonstrate improvements over prior memory frameworks in both multiple-choice and open-ended question answering. On EgoLifeQA, GEB achieves 72.0% accuracy, 4.4 percentage points above the best published result. Ablations show that grounded identity association and biography reading both contribute to the gains, which additional descriptions alone do not fully recover.

Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR); Machine Learning (cs.LG)
Cite as:	arXiv:2609.38155 [cs.CV]
	(or arXiv:2609.38155v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2609.38155 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hui Ren [view email]
[v1] Tue, 29 Sep 2026 17:59:01 UTC (1,513 KB)