Metraipolis › archive › dc_1529d424fa63
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies — arXiv:2609.38155
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38155
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:30:08.469Z
- SHA-256 of the archived text
ae5173c92b6f18d1248014533f54f0461a932349f18e7e2f49a3a4d126b864f2- Stable URL of this page
https://metraipolis.com/documento/dc_1529d424fa63
How to cite
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies — arXiv:2609.38155 — arXiv (en), https://arxiv.org/abs/2609.38155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1529d424fa63 (Metraipolis archive dc_1529d424fa63, sha256 ae5173c92b6f18d1248014533f54f0461a932349f18e7e2f49a3a4d126b864f2)
BibTeX
@misc{dc1529d424fa63,
title = {Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies — arXiv:2609.38155},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38155},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1529d424fa63; sha256 ae5173c92b6f18d1248014533f54f0461a932349f18e7e2f49a3a4d126b864f2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.38155 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:54.073Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).