streamhoi-interaction-aware-temporal-memory-adapta

name	streamhoi-interaction-aware-temporal-memory-adapta
description	Skill generated from arXiv paper 2607.20174: StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation
metadata	{"arxiv":{"id":"2607.20174","title":"StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation","authors":["Zejing Rao","Haoxian Zhang","Xiaoqiang Liu","Yiping Meng","Guoxin Zhang","Pengfei Wan","Fan Tang","Tong-Yee Lee"],"published":"2026-07-22","categories":["cs.CV","cs.AI"],"url":"https://arxiv.org/abs/2607.20174","utility":0.9}}

StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation

arXiv: 2607.20174
Published: 2026-07-22
Authors: Zejing Rao, Haoxian Zhang, Xiaoqiang Liu, Yiping Meng, Guoxin Zhang, Pengfei Wan, Fan Tang, Tong-Yee Lee
Categories: cs.CV, cs.AI
Utility: 0.90

Key Innovation

Existing human--object interaction (HOI) video generation methods are largely limited to offline short-video generation with complex driving conditions, making them unsuitable for real-time interactive applications. We present \emph{StreamHOI}, a low-latency streaming framework for long-duration HOI video generation. Instead of converting heavily conditioned HOI pipelines into streaming systems, we study how an image-to-video streaming generator should organize historical memory to preserve inte...

Potential Application

This paper presents advancements that could be applied to enhance agent capabilities in the areas of cs.CV, cs.AI.

References

• arXiv: https://arxiv.org/abs/2607.20174