Research
|
My current research interests include computer vision and machine learning.
I am focusing on Human-centric 3D vision, and Intelligent agent interacting with human in 3D world.
|
News
|
[2025.02]
One paper accepted to CVPR 2025 as Highlight, focusing on 3D human object intraction.
[2024.02]
One paper accepted to CVPR 2024 as Highlight, focusing on 3D human motion generation.
[2023.11]
One paper accepted to TPAMI, a comprehensive survey on 3D human motion generation.
[2023.07]
One paper accepted to ICCV 2023.
|
|
EMO-X: Efficient Multi-Person Pose and Shape Estimation in One-Stage
Haohang Jian*,
Jinlu Zhang*,
Junyi Wu,
Zhigang Tu
Arxiv, 2025
Paper
Abstract
Our EMO-X leverages the superior global modeling capability of Mamba and designs a local bidirectional scan mechanism for skeleton-aware local refinement. Notably, it achieves a significant reduction in computational complexity, requiring 69.8% less inference time compared to state-of-the-art (SOTA) methods, while outperforming most of them in accuracy.
|
|
OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition
Shihao Cheng*,
Jinlu Zhang*,
Yue Liu,
Zhigang Tu
Arxiv, 2025
Paper
Abstract
We propose OwlSight, a biomimetic-inspired framework with whole-stage illumination enhancement to interact with action classification for accurate dark video human action recognition.
|
|
Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation
Yijie Yang*,
Jinlu Zhang*,
Jiaxu Zhang,
Zhigang Tu
Arxiv, 2024
Paper/
Code
Abstract
In this work, we propose Expressive Keypoints that incorporates hand and foot details to form a fine-grained skeletal representation, to improve the discriminative ability for existing models in discerning intricate human actions.
|
|
InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing
Jinlu Zhang ,
Yixin Chen,
Zan Wang,
Jie Yang,
Yizhou Wang,
Siyuan Huang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025 Highlight
Project page/
Paper
Abstract
In this work, we propose a novel zero-shot 3D HOI generation framework without training on specific datasets, leveraging the knowledge from large-scale pre-trained models.
|
|
Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
Zan Wang,
Yixin Chen,
Baoxiong Jia,
Puhao Li,
Jinlu Zhang ,
Jingze Zhang,
Tengyu Liu,
Yixin Zhu,
Wei Liang,
Siyuan Huang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024 Highlight
Project page/
Paper/
Code
Abstract
In this work, we introduce a novel two-stage framework that employs scene affordance as an intermediate representation, effectively linking 3D scene grounding and conditional motion generation. Our framework comprises an Affordance Diffusion Model (ADM) for predicting explicit affordance map and an Affordance-to-Motion Diffusion Model (AMDM) for generating plausible human motions.
|
|
Human Motion Generation: A Survey
Wentao Zhu, Xiaoxuan Ma, Dongwoo Ro, Hai Ci, Jinlu Zhang, Jiaxin Shi,
Feng Gao, Qi Tian, Yizhou Wang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
Paper
Abstract
A comprehensive survey of recent advances in human motion generation, covering the technical evolution, key challenges, and future directions in this rapidly developing field.
|
|
PHRIT: Parametric Hand Representation with Implicit Template
Zhisheng Huang, Yujin Chen, Di Kang, Jinlu Zhang ,
Zhigang Tu
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Paper
Abstract
We propose PHRIT, a novel approach for parametric hand mesh modeling with an implicit template that combines the advantages of both parametric meshes and implicit representations. Our method represents deformable hand shapes using signed distance fields (SDFs) with part-based shape priors, utilizing a deformation field to execute the deformation.
|
|
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
Jinlu Zhang ,
Zhigang Tu ,
Jianyu Yang ,
Yujin Chen ,
Junsong Yuan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Paper/
Video/
Code/
Bibtex
Abstract
We propose MixSTE (Mixed Spatio-Temporal Encoder), which has a temporal transformer to separately model the temporal motion of each joint and a spatial transformer to learn inter-joint spatial correlation.
|
|
Uncertainty-Aware 3D Human Pose Estimation from Monocular Video
Jinlu Zhang ,
Yujin Chen ,
Zhigang Tu
ACM International Conference on Multimedia (ACM MM), 2022
Paper
Abstract
We propose an uncertainty-aware method to quantify and optimize the depth and 2D detection input respectively.
|
Experience
|
Research Intern at BigAI, working with Yixin Chen and Siyuan Huang.
|
Sep, 2023 - Feb, 2025 |
Research Intern at Tencent, working with Wei Zhuo.
|
Jan, 2022 - Jan, 2023 |
Cooperation Project of WHU & Tencent in real-time super-resolution.
|
Dec, 2021 - May, 2022
|
Research Intern at Huawei (Suzhou).
|
Jul, 2019 - Oct, 2019
|
Services & Activities
|
Conference Reviewer: CVPR'22/23/25, ICCV'23/25, ECCV'24, ICML'24, NeurIPS'24.
|
Journal Reviewer of: TPAMI, TIP, TSCVT.
|
Awards & Scholarships
|
National Scholarship of Wuhan University
|
Oct, 2022 |
1st Runner-up in ICCV2021 MMVRAC Challenge Track 2&3. [Link]
|
Sep, 2021 |
Top 10 first-year graduate students scholarship of WHU LIESMARS.
|
Nov, 2020 |
|
Doctor of Computer Applied Technology
CFCS, School of Computer Science, Peking University, China.
Advisor: Prof. Yizhou Wang
2023 - Now
|
|
Master of Computer Applied Technology
State Key Laboratory at Wuhan University, China.
Advisor: Prof. Zhigang Tu and Prof. Junsong Yuan
2020 - 2023
|
|
Bachelor Degree of Computer Science and Technology
Computer Science, Shandong University, China.
2016 - 2020,
with Honours degree
|
|