Metraipolis › archive › dc_fc8e18f68e02
EgoPhys: Estimating Peak Contact Force and Mechanical Work from Egocentric Manipulation Video — arXiv:2610.11347
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11347
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:30:29.468Z
- SHA-256 of the archived text
6f016dd6adce53f49a7695374efb6940b6be3f88b8704a0a0c7c56aac67df2cd- Stable URL of this page
https://metraipolis.com/documento/dc_fc8e18f68e02
How to cite
EgoPhys: Estimating Peak Contact Force and Mechanical Work from Egocentric Manipulation Video — arXiv:2610.11347 — arXiv (en), https://arxiv.org/abs/2610.11347 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc8e18f68e02 (Metraipolis archive dc_fc8e18f68e02, sha256 6f016dd6adce53f49a7695374efb6940b6be3f88b8704a0a0c7c56aac67df2cd)
BibTeX
@misc{dcfc8e18f68e02,
title = {EgoPhys: Estimating Peak Contact Force and Mechanical Work from Egocentric Manipulation Video — arXiv:2610.11347},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11347},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc8e18f68e02; sha256 6f016dd6adce53f49a7695374efb6940b6be3f88b8704a0a0c7c56aac67df2cd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11347. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Physically grounded manipulation of articulated objects requires understanding both the maximum forces encountered during contact and the work performed as their parts move. Peak contact force and mechanical work quantify these complementary aspects, but estimating them from egocentric video is challenging because physical interaction cues are local and indirect. Moreover, peak force is associated with brief contact events, whereas mechanical work depends on force-motion coupling throughout the contact duration. To address these challenges, we propose EgoPhys, an RGB-only framework comprising Contact-Aware Spatial Aggregation (CASA) and Target-Specific Multi-Expert Temporal Routing (TMTR). CASA integrates appearance and geometry features to emphasize interaction-relevant cues, while TMTR models semantic, event, and motion cues with specialized temporal experts and routes them separately for force and work prediction. On the test split from Hoi! dataset, EgoPhys substantially improves predictions of peak force and mechanical work, achieving MAEs of \(5.205 \pm 0.584\) $N$ and $0.894 \pm 0.081$ $J$, respectively. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.11347 — 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 2026-10-09T05:55:07.310Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).