Metraipolis › archive › dc_49972adfcb23
CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video — arXiv:2609.17688
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17688
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T16:16:48.573Z
- SHA-256 of the archived text
85cc8e64c5504565a32b42605c5f33e243cd657858ad74e80d65e9f469dbc39c- Stable URL of this page
https://metraipolis.com/documento/dc_49972adfcb23
How to cite
CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video — arXiv:2609.17688 — arXiv (en), https://arxiv.org/abs/2609.17688 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49972adfcb23 (Metraipolis archive dc_49972adfcb23, sha256 85cc8e64c5504565a32b42605c5f33e243cd657858ad74e80d65e9f469dbc39c)
BibTeX
@misc{dc49972adfcb23,
title = {CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video — arXiv:2609.17688},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17688},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49972adfcb23; sha256 85cc8e64c5504565a32b42605c5f33e243cd657858ad74e80d65e9f469dbc39c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17688. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Wearable assistants require episodic memory over egocentric video, yet current vision-language models face bounded frame budgets, growing visual-token costs, and long-context retrieval failures. Under these practical constraints, we study whether textual captions can serve as reusable episodic memory. We define the Episodic Memory Video Caption QA task and introduce CapMem, a human-annotated benchmark with 75 videos totaling 33.7 hours, and 1,000 multiple-choice questions across 16 scenarios. On long videos (>20 min), full-coverage CaptionQA with 30s and 60s caption windows outperforms direct VideoQA for 10/12 and 8/12 models, respectively. On the same video subset, a matched-frame control across six Qwen models retains mean accuracy gains of 3.22 and 2.55 points, respectively. Our caption-guided retrieve-and-verify harness further improves accuracy by up to 5.3 points. These results support the effectiveness of caption memory for episodic reasoning over long egocentric video. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.17688 — 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 2026-10-15T15:45:19.840Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).