Metraipolis › archive › dc_0a18deeaefb7

Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision — arXiv:2609.07099

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07099
License (as archived)
CC0-1.0
Archived
2026-10-16T15:11:39.571Z
SHA-256 of the archived text
03a506c199fea5ba53e72794dc8a2f16ed6ad643223f82fe88e40474cd0880b5
Stable URL of this page
https://metraipolis.com/documento/dc_0a18deeaefb7

How to cite

Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision — arXiv:2609.07099 — arXiv (en), https://arxiv.org/abs/2609.07099 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0a18deeaefb7 (Metraipolis archive dc_0a18deeaefb7, sha256 03a506c199fea5ba53e72794dc8a2f16ed6ad643223f82fe88e40474cd0880b5)
BibTeX
@misc{dc0a18deeaefb7,
  title = {Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision — arXiv:2609.07099},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07099},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0a18deeaefb7; sha256 03a506c199fea5ba53e72794dc8a2f16ed6ad643223f82fe88e40474cd0880b5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07099. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present our submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, which ranked first in the large-model division and second in the <=2B division. The task requires a wearable assistant to decide after each eight-second segment of egocentric video whether to intervene or remain silent. Our approach has two main components. First, we reformulate intervention timing as single-token classification. Rather than generating either $interrupt$<utterance> or $silent$, the model predicts yes or no, and we derive the decision from the renormalised probabilities of these two tokens. This formulation improved macro-F1 by 0.249 and G-mean by 0.30 over free-form generation. Second, because labelled data were limited to the released validation set, we generated additional supervision using a tool-calling video agent that inspects each clip and assigns intervention timestamps. A narration-only alternative was four times larger and ten times cheaper, but transferred worse than supervision from an unrelated real corpus, suggesting that visual grounding is more important than annotation volume for this task.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.07099 — 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 2026-10-16T14:49:57.185Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).