Metraipolis › archive › dc_af7323f5301d

A Framework for Egocentric and Exocentric Procedural Understanding via Temporal Segmentation and Semantic Abstraction — arXiv:2610.00069

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00069
License (as archived)
CC0-1.0
Archived
2026-10-06T12:07:40.045Z
SHA-256 of the archived text
ca1b60a4061734b6c334065949b886b1607e6b9f800faddeee4a6d682d86a26e
Stable URL of this page
https://metraipolis.com/documento/dc_af7323f5301d

How to cite

A Framework for Egocentric and Exocentric Procedural Understanding via Temporal Segmentation and Semantic Abstraction — arXiv:2610.00069 — arXiv (en), https://arxiv.org/abs/2610.00069 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af7323f5301d (Metraipolis archive dc_af7323f5301d, sha256 ca1b60a4061734b6c334065949b886b1607e6b9f800faddeee4a6d682d86a26e)
BibTeX
@misc{dcaf7323f5301d,
  title = {A Framework for Egocentric and Exocentric Procedural Understanding via Temporal Segmentation and Semantic Abstraction — arXiv:2610.00069},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00069},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af7323f5301d; sha256 ca1b60a4061734b6c334065949b886b1607e6b9f800faddeee4a6d682d86a26e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00069. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon ego/exo data contains rich procedural evidence, but are redundant, noisy, and costly to process or retain. We propose a compact framework that converts continuous multimodal workplace video into a structured Procedural State Memory, implemented as a Work Environment Model (WEM). Inspired by event segmentation theory, we detect boundaries using changes in visual context, location, motion, narration, gaze/object interaction, and optional exocentric workspace evidence, rather than fixed windows or visual novelty alone. Each segment is abstracted into an evidence-linked event card containing actor, interval, location, action, objects/tools, pre/post state, confidence, and provenance. These event cards incrementally update the WEM, enabling compact, auditable documentation and retrieval under on-premise privacy constraints. We instantiate the design with frozen DINOv2 and VJEPA-2 encoders and a local language model, and outline evaluation criteria for segmentation quality, memory compression, retrieval fidelity, and long-horizon QA.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.00069 — 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 2026-10-06T10:21:28.016Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).