PulseAugur
EN
LIVE 10:23:48

New HAPACT benchmark targets physical impact localization in videos

By PulseAugur Editorial · [1 sources] ·

Researchers have introduced HAPACT, a new benchmark and dataset designed to improve the localization of human-centric physical impacts in videos. This benchmark, derived from movie clips, focuses on identifying the temporal and spatial aspects of forceful events affecting the human body. The dataset comprises over 2.8K video-query pairs with more than 20K annotated frames, utilizing viewer-grounded annotation and text-conditioned localization. Initial evaluations using existing video moment retrieval and human-scene contact models indicate that physical impact localization remains a challenging task, highlighting the need for HAPACT to advance research in this area. AI

IMPACT This benchmark could drive advancements in video understanding and physical reasoning for AI systems.

RANK_REASON The cluster contains a research paper introducing a new benchmark and dataset for a specific AI task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New HAPACT benchmark targets physical impact localization in videos

How we ranked this

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains a research paper introducing a new benchmark and dataset for a specific AI task. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Youngrae Kim, Yejin Jang, Eunho Kim, Youjin Sung, Kun-Woo Song, Sangpil Kim, Sang Ho Yoon ·

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

    arXiv:2610.22895v1 Announce Type: cross Abstract: 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 lik…

RELATED ENTITIES

RELATED TOPICS