Home Knowledge Base HOI

HOI

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Diagnosis of Human Object Interaction Detectors for Real World Educational Applications

arXiv:2606.02789v1 Announce Type: new Abstract: Human-object interaction (HOI) recognition is critical for automatically analyzing student behavior in complex educational environments. Although state-of-the-art (SOTA) HOI detectors perform well on benchmark datasets, their performance often degrades when deployed in real-world training environments due to domain-specific objects, occlusions, and complex visual conditions. In this paper, we introduce a diagnosis-driven framework that...

arXiv CS 7d ago

ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detection

Announce Type: replace Abstract: Open-vocabulary human-object interaction (HOI) detection requires recognizing interaction phrases that may not appear as annotated categories during training. Recent vision-language HOI detectors improve semantic transfer by matching human-object features with text embeddings, but their predictions are often dominated by object affordance and phrase-level co-occurrence. As a result, a model may predict \textit{cut cake} from the presence of a knife and a cake...

arXiv CS 8d ago

Dex2HOI: Dexterous Bimanual Two-Object Interaction Generation

Announce Type: new Abstract: Recent advances in 4D Human-Object Interaction (HOI) generation have enabled increasingly realistic motion synthesis, particularly for single-object manipulation. Yet current research overlooks an inherent property of human behavior: people naturally coordinate both hands and manipulate multiple objects simultaneously. To address this gap, we present Dex2HOI, a unified diffusion model for single- and two-object HOI synthesis from text.

arXiv CS 9d ago

CHOIR: Contact-aware 4D Hand-Object Interaction Reconstruction

Announce Type: replace Abstract: We ask whether everyday open-world monocular videos can be turned into reusable 4D interaction primitives: articulated hand motion, object shape with 6D pose over time, and the when/where of contact. Such a capability would enable scalable mining of real interactions and, beyond reconstruction, support scene-aware synthesis and planning. However, reconstructing hand-object interaction (HOI) from challenging monocular videos remains difficult: methods often...

arXiv CS 9d ago

Recovering Physically Plausible Human-Object Interactions from Monocular Videos

Announce Type: new Abstract: In this paper, we propose RePHO, a method to reconstruct physically plausible human-object interactions (HOI) from monocular videos. While existing kinematic-based approaches produce visually plausible motion, they often result in physically implausible artifacts such as interpenetration and object floating. To overcome these issues, we introduce a physics-guided reconstruction framework.

arXiv CS 5d ago

Police arrest man after Tesla rams parked vehicle in latest drug-driving case

Hong Kong police have arrested a driver who crashed his car into a parked vehicle in Tai Kok Tsui and tested positive for ketamine, marking at least the fourth suspected drug-driving case in less than a week. The accident occurred at around noon on Sunday on Hoi Fai Road outside the Olympian City 3 shopping centre where the 30-year-old’s Tesla car struck the rear of a stationary vehicle before veering onto the pavement.

South China Morning Post 3d ago

GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors

arXiv:2606.05160v1 Announce Type: new Abstract: Scaling humanoid loco-manipulation requires robot-compatible demonstrations across diverse objects, whole-body motions, and scene geometries, but teleoperation and motion capture are difficult to scale because each collection depends on physical setups, instrumented actors, and robot operation. We present GRAIL, a digital generation pipeline that remains fully virtual until deployment: it composes 3D assets, simulator-ready scenes, and priors...

arXiv CS 6d ago

Thank God for Pope Leo. He’s the leader our world desperately needs | Arwa Mahdawi

Even for nonbelievers like me, the pope has become a reassuring – and all too rare – voice of moral clarityDo you remember the early 2000s, when Silicon Valley buzzed with idealism and tech bros told us they were going to save the world? “Don’t be evil” was Google’s unofficial motto; it’s 2004 IPO prospectus declared that doing “good things for the world” was more important than “short term gains”. Mark Zuckerberg similarly wrote in Facebook’s 2012 IPO letter that the social network was...

The Guardian UK 7d ago

Boo York, Boo York! Trump gets wake-up call in city that never sleeps

The TOI correspondent from Washington: In New York City, few traditions are more sacred than complaining about traffic and berating politicians. Donald Trump, the first US President to attend an NBA final, managed to trigger both on Monday night.

Times of India 1d ago

Hong Kong star Chow Yun Fat reunites with former child co-star Xie Miao after 32 years

Hong Kong star Chow Yun Fat reunites with former child co-star Xie Miao after 32 years The pair first appeared together in the 1994 film God Of Gamblers Return and reunited during promotions for Xie Miao's upcoming action movie. Hong Kong star Chow Yun Fat recently reunited with former child co-star Xie Miao more than three decades after the pair first worked together on the 1994 film God Of Gamblers Return. The reunion took place during promotional activities for Xie's upcoming action film...

Channel News Asia 6d ago