Jingzhong Lin (林靖众)

I am a Ph.D. student at East China Normal University (ECNU), where I am privileged to be advised by Prof. Gaoqi He. I received my M.S. degree in Computer Science from ECNU in 2023.

My research interests lie at the intersection of Computer Vision and Computer Graphics, with a primary focus on multi-modal conditioned human motion modeling.

Email  /  GitHub  /  Google Scholar

Jingzhong Lin
Publications
ReactDance Logo ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation
Jingzhong Lin, Xinru Li, Yuanyuan Qi, Bohao Zhang, Wenxiang Liu, Kecheng Tang, Wenxuan Huang, Xiangfeng Xu, Bangyan Li, Changbo Wang, Gaoqi He
ICLR, 2026

ReactDance enables fine-grained duet interaction via hierarchical latent representations and ensures long-term coherence through temporal alignment.

PCMG: Psychology-driven Personality-consistent Text-to-Motion Generation
Yuanyuan Qi, Jingzhong Lin, Xinru Li, Weiliang Meng, Changbo Wang, Gaoqi He
ICME, 2026

A text-to-motion framework that integrates OCEAN personality traits and Laban-based guidance to generate psychologically consistent and personality-distinct human motions.

EmoDiffGes: Emotion-Aware Co-Speech Gesture Generation with Progressive Synergistic Diffusion
Xinru Li, Jingzhong Lin, Bohao Zhang, Yuanyuan Qi, Changbo Wang, Gaoqi He
Pacific Graphics (PG), 2025
BibTex

EmoDiffGes, a diffusion-based framework unifying dynamic emotion conditioning and part-aware synergistic modeling.

Regulatory Focus Theory Induced Micro-Expression Analysis via Structured Representation Learning
Bohao Zhang, Haoxin Xu, Jingzhong Lin, Changbo Wang, Gaoqi He
ACM MM, 2025
BibTex

Ac4AU, an apex-free network for action unit detection that addresses data leakage concerns raised in CD6ME and eliminates the need for manually annotated apex frames.

Open Source Projects
Open Source
ResearchFlow
Local Knowledge Workflow
ResearchFlow: Semi-automated Local Research Knowledge Base and Research Assistant
Maintainer: Jingzhong Lin

ResearchFlow is an open-source workflow for building a local, reusable research knowledge base and connecting it with AI-assisted ideation, coding, and writing workflows.

Academic Service

Reviewer for: ICCV, CVPR, AAAI.


Template adapted from Kaifeng Zhao's website.