Sign inGet started
Paper · arXiv

HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies

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 m...

AuthorsYoungrae Kim, Yejin Jang, Eunho Kim et al.
Primary categorycs.CV
Published16 October 2026
Last updated at source16 October 2026
cs.CVcs.AI
Embed this entry
<iframe src="https://silytics.si/embed/item/0fb195fa-c467-4b22-a95b-6bd48f845136" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Popularity, last 7 days

0 now. Counts as reported by the source, snapshotted daily by Silytics.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 25 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.