About Me

Zhongwei Qiu is currently working as an algorithm expert at Alibaba DAMO Academy, under the leadership of Dr. Le Lu. He is also a postdoctoral researcher at the College of Computer Science and Technology at Zhejiang University, collaborating with Prof. Fei Wu.

He received his Ph.D. degree from the University of Science and Technology Beijing (USTB), supervised by Prof. Dongmei Fu, co-supervised by Dr. Jianlong Fu from Microsoft Research Asia (MSRA). Before that, he received his B.S. degree in Automation from USTB in 2018. He was a visiting researcher at the University of Sydney (USYD) from July 2022 to July 2023, supervised by Dr. Chang Xu.

His research interest is primarily focused on computer vision, multimodal learning, and artificial intelligence, including Human-Centric Visual Perception and Generation(2D/3D Human Pose and Shape Estimation, Human Motion and Video Generation), Low-level Vision and Generation(Video Super-Resolution, NeRF, Diffusion Model), the applications of AI for Healthcare and Science, and so on.

We have $\color{red}{opening~positions}$ for $\color{red}{research~interns}$ (undergraduate, master, Ph.D., and gap year students are all welcomed). Please drop me an e-mail (qiuzhongwei.qzw@alibaba-inc.com) if you are interested.

🎓︎ Educations

2022.07 - 2023.08, Visiting Research Student, The University of Sydney, Sydney, Australia.
2018.06 - 2024.01, Ph.D. student in Control Science and Engineering, University of Science and Technology Beijing, Beijing China.
2014.09 - 2018.06, Bachelor of Engineering in Automation, University of Science and Technology Beijing, Beijing China.

🔥 News

2024.10: 🎉🎉 1 papers are accepted by TVCG.
2024.09: 🎉🎉 1 papers are accepted by NeurIPS 2024.

📝 Publications

MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field

Zijiang Yang, Zhongwei Qiu, Chang Xu, Dongmei Fu.

TVCG [paper]
Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective

Meijun Wang, Yu Meng, Zhongwei Qiu, Chao Zheng, Yan Xu, Xiaorui Peng, Jiao Gao.

NeurIPS 2024
IHCSurv: Effective Immunohistochemistry Priors for Cancer Survival Analysis in Gigapixel Multi-stain Whole Slide Images

Yejia Zhang, Hanqing Chao, Zhongwei Qiu, Wenbin Liu, Yixuan Shen, Nishchal Sapkota, Pengfei Gu, Danny Z Chen, Le Lu, Ke Yan, Dakai Jin, Yun Bian, Hui Jiang

MICCAI 2024 [paper]
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

Junkun Yuan, Xinyu Zhang, Hao Zhou, Jian Wang, Zhongwei Qiu, Zhiyin Shao, Shaofeng Zhang, Sifan Long, Kun Kuang, Kun Yao, Junyu Han, Errui Ding, Lanfen Lin, Fei Wu, Jingdong Wang.

NeurIPS 2023 [paper]
Stable Diffusion is Unstable

Chengbin Du, Yanxi Li, Zhongwei Qiu, Chang Xu.

NeurIPS 2023 [paper]
PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers

Zhongwei Qiu, Yang Qiansheng, Jian Wang, Haocheng Feng, Junyu Han, Errui Ding, Chang Xu, Dongmei Fu, Jingdong Wang

CVPR 2023 [paper]
Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge

Zhongwei Qiu, Kai Qiu, Jianlong Fu, Dongmei Fu

Pattern Recognition [paper]
Learning Degradation-robust Spatiotemporal Frequency-Transformer for Video Super-Resolution

Zhongwei Qiu, Huan Yang, Jianlong Fu, Daochang Liu, Chang Xu, Dongmei Fu

TPAMI [paper] [code]
DMIS: Dynamic Mesh-based Importance Sampling for Training Physics-Informed Neural Networks

Zijiang Yang, Zhongwei Qiu, Dongmei Fu

AAAI 2023 [paper] [code]
Learning spatiotemporal frequency-transformer for compressed video super-resolution

Zhongwei Qiu, Huan Yang, Jianlong Fu, Dongmei Fu

ECCV 2022 [paper] [code]
IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation

Zhongwei Qiu, Qiansheng Yang, Jian Wang, Dongmei Fu

ACM MM 2022 oral [paper]
Dynamic Graph Reasoning for Multi-person 3D Pose Estimation

Zhongwei Qiu, Qiansheng Yang, Jian Wang, Dongmei Fu

ACM MM 2022 [paper]
DGCN: Dynamic graph convolutional network for efficient multi-person pose estimation

Zhongwei Qiu, Kai Qiu, Jianlong Fu, Dongmei Fu

AAAI 2020 [paper]
Learning recurrent structure-guided attention network for multi-person pose estimation

Zhongwei Qiu, Kai Qiu, Jianlong Fu, Dongmei Fu

ICME 2019 oral [paper]

👨‍💼 Work Experience

2021 - 2023, Research Intern, Baidu VIS, Beijing, China.
2018.07 - 2021.02, Research Intern, Microsoft Research Asia, Beijing, China.

🛠 Projects

AI Coach for freestyle skiing, work with XiaoIce at MSRA.
Video Super-Resolution, work at MSRA. The technology of FTVSR has been shipped to Microsoft Edge Browser.

🎖 Honors and Awards

2023.11 Scholarship from Baosteel Education Foundation
2023.05 CVPR 2023 Student Scholarship, CVPR
2022.12 Scholarship from Zenith Steel Group
2022.12 Star of Academic, University of Science and Technology Beijing
2022.12 Excellent Graduate Student, University of Science and Technology Beijing
2022.10 ECCV 2022 Student Scholarship, ECCV
2022.10 ACM Multimedia 2022 Student Scholarship, ACM Multimedia
2021.12 Star of Tomorrow, Microsoft Research Asia
2021.02 Star of Tomorrow, Microsoft Research Asia
2019.12 Silver Medal (10/1300+) in RSNA Intracranial Hemorrhage Detection, RSNA-Kaggle
2018.09 The 2nd place of ChinaMM 2018 JD AI Fashion-Challenge, JD.com
2018.06 Excellent Graduation Thesis, University of Science and Technology Beijing
2018.06 Outstanding Graduate, University of Science and Technology Beijing

💬 Invited Talks

2022.10, “IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation” at ACM Multimedia 2022 (online), Lisbon, Portugal.
2019.07, “Learning recurrent structure-guided attention network for multi-person pose estimation” at ICME 2019, Shanghai, China.

📖 Academic Service

Conference Reviewer

ICLR: 2025, 2024
CVPR: 2024, 2023
ICML: 2024, 2023
NeurIPS: 2024, 2023, 2022
ACM MM: 2024, 2023, 2022, 2021
AAAI: 2025, 2024, 2023
MICCAI: 2024
ICASSP: 2023
ICME: 2023,2022,2021,2020,2019

Journal Reviewer

TVCG, TMM, TCSVT