Metraipolis › archive › dc_3d6d6408d032
HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies — arXiv:2610.22895
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22895
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:43:02.965Z
- SHA-256 of the archived text
aa55169fb24d985f50dfe5213b584b4205cdeefc5d2596411dc21ec1b337e863- Stable URL of this page
https://metraipolis.com/documento/dc_3d6d6408d032
How to cite
HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies — arXiv:2610.22895 — arXiv (en), https://arxiv.org/abs/2610.22895 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d6d6408d032 (Metraipolis archive dc_3d6d6408d032, sha256 aa55169fb24d985f50dfe5213b584b4205cdeefc5d2596411dc21ec1b337e863)
BibTeX
@misc{dc3d6d6408d032,
title = {HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies — arXiv:2610.22895},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22895},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d6d6408d032; sha256 aa55169fb24d985f50dfe5213b584b4205cdeefc5d2596411dc21ec1b337e863},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22895. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Physical reasoning about humans in videos has largely focused on everyday interactions, where contact, pressure, pose, and motion support embodied perception and contact-aware applications. Still, short and forceful properties like impact events remain relatively underexplored, despite their relevance to broader understanding of how abrupt physical events affect the human body. To fill this gap, we introduce human-centric impact localization, a new task that localizes target physical impacts temporally within a video and spatially on the human body. We further present HAPACT, a HumAn-centric imPACT dataset and benchmark built from movie clips, containing over 2.8K video-query pairs with more than 20K fine-grained human-annotated frames. We built HAPACT around viewer-grounded annotation, text-conditioned localization, and supervision at frame-level temporal and SMPL-X-based spatial granularity. To demonstrate the effectiveness of our benchmark, we conduct extensive evaluations of existing methods, employing video moment retrieval models for temporal localization and human-scene contact models for spatial localization. For the spatial task, we propose a text-conditioned baseline by reformulating localization as query-guided body-region selection. Benchmark results show that physical impact localization remains challenging for existing methods, motivating HAPACT as a dedicated benchmark to support physical impact reasoning in videos. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.22895 — 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 2026-10-19T08:39:10.133Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).