Metraipolis › archive › dc_98a080f1f02c
DUGO: Dual-Scale Gaussian Memory for Online Temporal Action Localization in Egocentric Procedural Videos — arXiv:2610.41402
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41402
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T07:51:17.928Z
- SHA-256 of the archived text
0858dfb23aa4dc2e2647c373df3ee90f18ab30ddb2355448c19b4c75f7824fb0- Stable URL of this page
https://metraipolis.com/documento/dc_98a080f1f02c
How to cite
DUGO: Dual-Scale Gaussian Memory for Online Temporal Action Localization in Egocentric Procedural Videos — arXiv:2610.41402 — arXiv (en), https://arxiv.org/abs/2610.41402 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98a080f1f02c (Metraipolis archive dc_98a080f1f02c, sha256 0858dfb23aa4dc2e2647c373df3ee90f18ab30ddb2355448c19b4c75f7824fb0)
BibTeX
@misc{dc98a080f1f02c,
title = {DUGO: Dual-Scale Gaussian Memory for Online Temporal Action Localization in Egocentric Procedural Videos — arXiv:2610.41402},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41402},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98a080f1f02c; sha256 0858dfb23aa4dc2e2647c373df3ee90f18ab30ddb2355448c19b4c75f7824fb0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41402. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Online Temporal Action Localization (OnTAL) aims to detect and localize action instances from untrimmed streaming videos in real time. Unlike offline approaches, OnTAL models have no access to future frames and cannot go back and refine earlier predictions, which makes the task considerably harder given the strict real-time constraints and narrow temporal window available. Most existing OnTAL methods lean on either brief anchor-based context or a single-scale memory of past frames, which limits how well they can capture actions unfolding across multiple time scales or requiring long-range reasoning in Procedural Videos. To address these gaps, we present DUGO (Dual-Scale Encoding and Gaussian Memory Online), a new OnTAL framework that jointly models local motion dynamics and long-range temporal dependencies. At its core, DUGO uses a Dual-Scale Temporal Encoder, pairing depth-wise local representations with global self-attention so it can pick up both fine-grained temporal patterns and broader contextual cues. We also introduce a Gaussian Memory Bank, which represents action memory as stochastic, input-conditioned Gaussian prototypes, allowing for richer temporal memory through gated cross-attention applied at both the encoder and anchor-query stages. Extensive experiments on procedural egocentric datasets (EGTEA, EPIC-Kitchens-100) demonstrate that DUGO achieves state-of-the-art performance while also providing substantial improvements on non-egocentric benchmarks such as Muses. The project page is available at: this https URL Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.41402 — 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 2026-11-02T07:40:00.255Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).