Metraipolis › archive › dc_69cdd67945ef
VidParse: Online Parsing of Egocentric Procedures Like a Pro — arXiv:2608.27562
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27562
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:32:54.485Z
- SHA-256 of the archived text
c8f4a71a5674ceade8746d42ffcb37f086a798e81d74724519cecf2fe8564b05- Stable URL of this page
https://metraipolis.com/documento/dc_69cdd67945ef
How to cite
VidParse: Online Parsing of Egocentric Procedures Like a Pro — arXiv:2608.27562 — arXiv (en), https://arxiv.org/abs/2608.27562 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69cdd67945ef (Metraipolis archive dc_69cdd67945ef, sha256 c8f4a71a5674ceade8746d42ffcb37f086a798e81d74724519cecf2fe8564b05)
BibTeX
@misc{dc69cdd67945ef,
title = {VidParse: Online Parsing of Egocentric Procedures Like a Pro — arXiv:2608.27562},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27562},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69cdd67945ef; sha256 c8f4a71a5674ceade8746d42ffcb37f086a798e81d74724519cecf2fe8564b05},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27562. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Translating continuous, noisy egocentric video streams into discrete, temporally ordered action steps is fraught with visual challenges. Heavy ego-motion, transient occlusions, and the high intra-class variability of unscripted human-object interactions cause standard frame-level online temporal models to struggle, often resulting in severe over-segmentation and structural collapse. To bridge the gap between unstable low-level perception and high-level procedural logic, we present VidParse, an online, training-free framework that treats activity understanding as a graph-constrained inference problem. Rather than relying on learned temporal filters, we dynamically identify semantic transitions using a temporal similarity matrix over manipulation-anchored features, which are extracted from frozen foundation models to prioritize foreground hand-object interactions. A beam search decoder then leverages an induced procedural task graph to explicitly enforce valid action transitions and prune impossible trajectories. By anchoring robust visual segments to hard procedural constraints, our approach preserves long-range state transitions and achieves up to a 10x improvement in complex multi-step parsing accuracy over strong online baselines, all without requiring a single gradient update. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.27562 — 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 2026-10-17T11:10:05.256Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).