Assistant Professor
Department of Computer Science, Fuzhou University
Email: jinszhang at fzu.edu.cn
目前正在招收2026级硕士研究生，对人体三维重建、运动生成、图像生成与编辑、具身智能等感兴趣的同学请联系我。
邮箱：jinszhang@fzu.edu.cn
I am currently an Assistant Professor with the College of Computer and Data Science, Fuzhou University. I received my Ph.D. degree in Computer Science and Technology from Tianjin University in 2025, under the supervision of Prof.Kun Li. My research interest area is human-centric modeling, understanding and generation, including human reconstruction, motion generation, human image generation and editing, and embody-AI.Education
Aug. 2021 - Jun. 2025, Ph.D Student in College of intelligence and computing, Tianjin University
Oct. 2023 - Dec. 2024, Visiting student in [IGARASHI Lab], University of Tokyo
Jun. 2022 - Dec. 2022, Visiting student in [Sigma Lab], Tsinghua University
Aug. 2018 - Jul. 2021, Master Student in Tianjin International Engineering Institute, Tianjin University
Aug. 2014 - Jul. 2018, Bachelor of Engineering in School of Mathematics, Tianjin University
Publications
|
LoGAvatar: Local Gaussian Splatting for human avatar modeling from monocular video
|
|
AI System Facilitates People with Blindness and Low Vision in Interpreting and Experiencing Unfamiliar Environments
|
|
SpeechAct: Towards Generating Whole-body Motion from Speech
|
|
DualAvatar: Robust Gaussian Splatting Avatar with Dual Representation
|
|
SMixNet: Style mixture network for exemplar-based image translation
|
|
Multi-scale information transport generative adversarial network for human pose transfer
|
|
Towards Grouping in Large Scenes with Occlusion-aware Spatio-temporal Transformers
|
|
PISE: Person Image Synthesis and Editing with Decoupled GAN
|
|
PoNA: Pose-guided Non-local Attention for Human Pose Transfer
|
|
Human Pose Transfer by Adaptive Hierarchical Deformation
|
High-Quality Animatable Dynamic Garment Reconstruction from Monocular Videos
Xiongzheng Li, Jinsong Zhang, Yu-Kun Lai, Jingyu Yang, Kun Li
In IEEE T-CSVT 2023 [Project Page]
MH-HMR: Human mesh recovery from monocular images via multi-hypothesis learning
Haibiao Xuan, Jinsong Zhang, Yu-Kun Lai, Kun Li
In CAAI TRIT 2023 [Project Page]
Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning
Haibiao Xuan, Xiongzheng Li, Jinsong Zhang, Hongwen Zhang, Yebin Liu, Kun Li
In ICCV 2023 [Project Page]
High-Fidelity Human Avatars from a Single RGB Camera
Hao Zhao, Jinsong Zhang, Yu-Kun Lai, Zerong Zheng, Yingdi Xie, Yebin Liu, Kun Li
In CVPR 2022 [Project Page]
Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing
Xiaokun Sun, Qiao Feng, Xiongzheng Li,Jinsong Zhang, Yu-Kun Lai, Jingyu Yang, Kun Li
In CVPR 2023 [Project Page]
MHPro: Multi-Hypothesis Probabilistic Modeling for Human Mesh Recovery
Haibiao Xuan, Jinsong Zhang, Kun Li
In CICAI 2022 (oral) [Project Page]
Learning to Infer Inner-Body under Clothing from Monocular Video
Xiongzheng Li, Jing Huang, Jinsong Zhang, Xiaokun Sun, Haibiao Xuan, Yu-Kun Lai, Yingdi Xie, Jingyu Yang, Kun Li
In TVCG 2022 [Project Page]
STATE: Learning Structure and Texture Representations for Novel View Synthesis
Xinyi Jing, Qiao Feng, Yu-Kun Lai, Jinsong Zhang, Yuanqiang Yu, Kun Li
In CVM 2022 [Project Page]
Service
- As an reviewer of journals: TIP, TVCG, TMM, TCSVT
- As an reviewer of conferences: CVPR, ICCV, ACMMM, CICAI