PulseAugur
EN
LIVE 09:02:56

New model PACT jointly learns human pose, contacts, and forces from video

By PulseAugur Editorial · [1 sources] ·

Researchers have developed PACT, a novel end-to-end model designed to jointly learn human pose, contact points, and interaction forces from monocular video. This approach integrates visual pose reconstruction with contact and force estimation, aiming to improve joint reasoning and reduce error propagation. PACT utilizes a temporal transformer and physics-based supervision, and a new dataset called ForceWall has been created to facilitate training and evaluation of contact force estimation from real-world climbing videos. AI

IMPACT This research could advance the accuracy of human motion analysis in video, with potential applications in sports analytics, robotics, and virtual reality.

RANK_REASON This is a research paper describing a new model and dataset. [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 model PACT jointly learns human pose, contacts, and forces from video

How we ranked this

Signal score
14 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is a research paper describing a new model and dataset. [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, model release, 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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Rikhat Akizhanov (MBZUAI), Yangsong Zhang (MBZUAI), Nikolai Kaliazin (MBZUAI), Peter Wolf (ETH Z\"urich), Yoshihiko Nakamura (MBZUAI), Pascal Fua (EPFL), Fabio Pizzati (MBZUAI), Ivan Laptev (MBZUAI) ·

    PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video

    arXiv:2610.00451v1 Announce Type: cross Abstract: Human motion, environmental contacts, and interaction forces are governed by common physical laws, yet existing approaches typically separate visual pose reconstruction from contact and force estimation. This separation limits joi…

RELATED ENTITIES

RELATED TOPICS