Zhengxia Zou, Ph.D.
[Intern position]: I am hiring self-motivated graduate/undergraduate students. Intern positions are always available. Please email me with your CV if you are interested.
NEW (04/2023): Our paper on driving environment simulation got accepted to Nature Communications.
NEW (03/2023): Our paper on autonomous vehicle testing got accepted to Nature (cover)! Congratulations!
NEW (02/2023): One paper accepted to CVPR 2023 (featured in New Scientist (新科学人)).
NEW (01/2023): Our survey paper on object detection got accepted by Proceedings of the IEEE.
NEW (10/2022): I was listed in the top 2% scientists worldwide identified by Stanford University.
NEW (07/2022): One paper accepted to IEEE Transactions on Image Processing (TIP).
NEW (02/2022): One paper accepted to ICRA 2022.
NEW (12/2021): One paper accepted to AAAI 2022, oral presentation.
NEW (06/2021): Stylized Neural Painting launched as a new feature in two AI photo editors: REMINI ( Google Play | IOS App Store ) and 你我当年 ( XIAOMI App Sstore | IOS App Store ), with over 10M users worldwide.
NEW (02/2021): One paper accepted to CVPR 2021, oral presentation.
Research Highlights
- 50+ peer-reviewed publications, including 30+ top-tier journals and conferences ( Nature, Nat. Commun., Proc IEEE, TPAMI, TIP, CVPR, ICCV, AAAI, ... )
- 3000+ Google Scholar citations, 4000+ GitHub Stars/Forks
- Two papers selected in PaperWithCode "Top-10 Trending
Research" and "GitHub Trending Repositories"
- Featured in 10+ platforms with over 10M registered
users worldwide, including MCITY, REMINI, 你我当年, Justice, Heaven Mobile, Weights&Biases, REPLICATE AI, RUNWAYML...
- Covered by 30+ high-impact tech-media, including 新华社, 中央电视台, TheNextWeb, New Scientist, 机器之心, 量子位...
Selected Publications
Zhengxia Zou* (*Corresponding author), Zhenwei Shi, Yuhong Guo, and Jieping Ye (*Corresponding author). Object Detection in 20 Years: A Survey. Proceedings of the IEEE, Volumn 111, Issue 13, 2023. [1500+ citations], Most Popular Article of the PIEEE 2023. [PDF]
Extensively reviews the fast-moving research field of object detection in the light of technical evolution, spanning over a quarter-century's time (from the 1990s to 2022). A number of topics are covered in this paper, including milestone detectors, detection datasets, metrics, fundamental building blocks of detection systems, speed up techniques, and the recent state of the art detection methods. - High-impact citations: Stanford CS231n: Convolutional Neural Networks for Visual Recognition (2019-2023). - Media coverage: [PIEEE] Proceedings of the IEEE Paper Explores Object Detection's Evolution and Future Directions | [专知] 密歇根大学40页最新论文带你全面了解目标检测 - In other languages: English-to-Chinese (1) | English-to-Chinese (2)
Xintao Yan+, Zhengxia Zou+ (+equal contribution), Shuo Feng, Haojie Zhu, Haowei Sun, Henry X. Liu* (*Corresponding author). Learning Naturalistic Driving Environment with Statistical Realism. Nature Communications (featured image), 2023. Featured in Editors' Highlights. [PDF] [Github]
We develop NeuralNDE, a Transformer-based framework to learn multi-agent interaction behavior from real-world vehicle trajectory data. NeuralNDE can achieve both accurate safety-critical and normal driving statistics.
- Media coverage: [EurekAlert] [TechXplore] [Michigan News] World’s first realistic simulated driving environment based on ‘crash-prone’ Michigan intersection. | [量子位] 自动驾驶仿真系统登Nature子刊，准确建模事故率事故类型，全华人团队打造 | [MIT科技评论] 密西根大学团队开发高精度自然驾驶仿真算法，为自动驾驶开发提供仿真基础
Shuo Feng, Haowei Sun, Xintao Yan, Haojie Zhu, Zhengxia Zou, Shengyin Shen, Henry X. Liu* (*Corresponding author). Dense Reinforcement Learning for Safety Validation of Autonomous Vehicles. Nature (cover), 2023. [PDF] [Github]
One critical bottleneck that impedes the development and deployment of autonomous vehicles is the prohibitively high economic and time costs required to validate their safety in a naturalistic driving environment, owing to the rarity of safety-critical events. Here we report the development of an intelligent testing environment, where artificial-intelligence-based background agents are trained to validate the safety performances of autonomous vehicles in an accelerated mode, without loss of unbiasedness.
- Media coverage: [Nature News] Hazards help autonomous cars to drive safely. | [Nature Podcast] How to make driverless cars safer — expose them to lots of dangerous drivers | [Michigan Engineering] Simulated terrible drivers cut the time and cost of AV testing by a factor of one thousand
Rui Zhao, Wei Li, Zhipeng Hu, Lincheng Li* (*Corresponding author), Zhengxia Zou* (*Corresponding author), Zhenwei Shi, Changjie Fan. Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation. Accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023. [PDF]
- Featured apps: Justice Mobile (The first plausible solution for text-driven game characters auto-creation).
- Media coverage: [New Scientist (新科学人)] Character creator AI puts Barack Obama – or anyone – in a video game
Tianyang Shi+, Zhengxia Zou+
(+equal contribution), Zhenwei Shi, and Yi Yuan*
(*Corresponding author). Neural Rendering
for Game Character Auto-creation. IEEE Transactions
on Pattern Analysis and Machine Intelligence, 2022.
[PDF]
- Featured apps: Justice and Heaven Mobile, two MMO-RPGs with 10M+ players worldwide
- Media coverage: [CCTV经济信息联播]元宇宙应用渐热 记者走入“元宇宙” 体验个性化“捏脸”和动作捕捉 | [机器之心] 只需一张自拍，网易伏羲用这种方法直接生成「个人专属」游戏角色
Zhengxia Zou (*Corresponding author), Rui Zhao, Tianyang Shi, Shuang Qiu, and Zhenwei Shi. Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos. IEEE Transactions on Image Processing, 2022. In press. [PDF] [Project] [GitHub (2.0k☆)]
- Featured apps: Weights & Biases, a ML developer tool with 100,000+ practitioners
- Media coverage: [机器之心] 建造自己的“天空之城”，密歇根大学博士后的这项研究可以虚空造物、偷天换日 | [TNW] This open-source AI tool can make your video spectacular with...
Zhengxia Zou, Rusheng Zhang, Shengyin Shen, Gaurav Pandey, Punarjay Chakravarty, Armin Parchami, and Henry X. Liu (*Corresponding author). Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras. The International Conference on Robotics and Automation (ICRA), 2022. [PDF] [1min-DemoVideo]
- Featured apps: Deployed at a two-lane roundabout located at Ellsworth Rd. and State St., Ann Arbor, MI, USA, providing 7x24 real-time traffic flow monitoring for hazardous driving scenarios identification.
Jianqi Chen, Keyan Chen, Hao Chen, Wenyuan Li, Zhengxia Zou* (*Corresponding author), and Zhenwei Shi. Contrastive Learning for Fine-grained Ship Classification in Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 2022. [PDF]
Yinglin Duan, Yue Lin, Zhengxia Zou*
(*Corresponding author), Yi Yuan, Zhehui Qian, Bohan Zhang.
A Unified Framework for Real Time Motion Completion. AAAI
Conference on Artificial Intelligence (AAAI) 2022,
Oral Presentation.
[PDF]
Zhengxia Zou (*Corresponding author), Tianyang Shi, Shuang Qiu, Yi Yuan, and Zhenwei Shi. Stylized Neural Painting. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021, Oral Presentation. [PDF] [Project] [GitHub (1.5k☆)]
- Featured apps: REMINI and 你我当年, two photo editors with 10M+ users worldwide | RunwayML, a web-based video editor
- Media coverage: [新华社] 动动手，一起为春天中国“添彩” - 送您一支AI画笔, 为祖国春天涂抹万千风情 | [机器之心] 有了这支矢量神经风格画笔，无需GAN也可生成精美绘画 | [MarkTechPost] An Image-To-Painting Translation Method That Generates Painting Artworks With Controllable Styles
Zhengxia Zou (*Corresponding author), Tianyang Shi, Zhenwei Shi, and Jieping Ye. Adversarial Training for Solving Inverse Problems in Image Processing. IEEE Transactions on Image Processing, 2021. [PDF] [1min-DemoVideo] [Github]
Zhengxia Zou, and Zhenwei Shi (*Corresponding author). Random access memories: A new paradigm for target detection in high resolution aerial remote sensing images. IEEE Transactions on Image Processing, 2018.
Zhengxia Zou, and Zhenwei Shi (*Corresponding author). Ship Detection in Spaceborne Optical Image With SVD Networks. IEEE Transactions on Geoscience and Remote Sensing, 2016.
Zhenwei Shi, and Zhengxia Zou* (Corresponding author). Can a machine generate humanlike language descriptions for a remote sensing image? IEEE Transactions on Geoscience and Remote Sensing, 2017.
Zhengxia Zou, and Zhenwei Shi (*Corresponding author). Hierarchical suppression method for hyperspectral target detection. IEEE Transactions on Geoscience and Remote Sensing, 2015.
Teaching and Academic Activities
- Mathematical Foundations of Machine Learning. Spring 2023.
- Pattern Recognition. Spring 2023.
- Target Detection in Aerospace Engineering. Fall 2022.
- Remote Sensing (IF=5.349) Special Issue: "Pattern Recognition and Image Processing for Remote Sensing III". Deadline: 5 January 2024.
- Remote Sensing (IF=5.349) Special Issue: "Pattern Recognition and Image Processing for Remote Sensing II". Deadline: closed (30 June 2023).
- Remote Sensing (IF=5.349) Special Issue: "Advanced Learning Techniques for Remote Sensing Image Quality Improvement". Deadline: 31 August 2023.
- Remote Sensing (IF=5.349) Special Issue: "Computational Intelligence and Advanced Learning Techniques in Remote Sensing". Deadline: closed (31 July 2021).
- Senior Program Committee (SPC) member of IJCAI 2021.
- CVPR 2020, 2021, 2022 PC Member; NeurIPS 2019, 2020 PC Member; ICCV 2021 Reviewer; ICLR 2021 Reviewer; AAAI 2020, 2021 PC Member; ACCV 2020 PC Member; WACV 2021 PC Member.
- IEEE Transactions on Pattern Analysis and Machine Intelligence; IEEE Transactions on Image Processing; IEEE Signal Processing Magazine; IEEE Transactions on Geoscience and Remote Sensing; IEEE Signal Processing Letters; IEEE Geoscience and Remote Sensing Letters; Remote Sensing; Infrared Physics and Technology; International Journal of Remote Sensing; Electronics; Journal of Computational Methods in Sciences and Engineering; Journal of Marine Science and Technology; Computational Intelligence and Neuroscience; Journal of Spectroscopy; The Visual Computer; International Journal of Machine Learning and Cybernetics.
- Best Reviewer of Infrared Physics & Technology (2017).
- Physics informed remote sensing image synthesis and analysis. Invited talk at VALSE 2023, Wuxi, China. Jun 2023.
- Mixed reality for visual perception of unmanned systems. Invited talk at Kwai, Beijing, China. Feb 2023.
- Deep Learning: History, Methodology, and Applications. Invited talk at North China University of Technology, Beijing, China. Oct 2022
- Mixed reality for visual perception of unmanned systems. Invited talk at HIT-Webinar, Beijing, China. Oct 2022.
- Mixed reality and neural rendering for visual perception. Invited talk at BtyeDance, Mountain View, USA and Beijing, China. Jan 2022.
- Mixed reality and neural rendering for visual perception. Invited talk at OPPO Research Institute, Beijing, China. Jan 2022.
- Mixed reality and neural rendering for visual perception. Invited talk at NIO, Beijing, China. Dec 2021.
- Mixed reality and neural rendering for visual perception. Invited talk at Didi Chuxing, Beijing, China. Dec 2021.
- Stylized Neural Painting. TechBeat AI Talk. June 2021.
- Stylized Neural Painting. CVPR Oral. June 2021.
- Art-centric Neural Rendering and Augmented Reality. University of Texas, Austin. Dec 2020.
- Neural Rendering for Visual Editing and Visual Arts. Ocean University of China. Dec 2020.
- Object Detection in 20 Years. Didi Chuxing, Beijing, China. Jul 2019.
- Adversarial Training for Solving Inverse Problems. Didi Chuxing, Beijing, China. Jul 2019.
- Introduction to Deep Learning and Computer Vision - Past, Present and Future. M-Culture Salon, University of Michigan, Ann Arbor. Jan 2020.
- I was a summer exchange student at the University of Cambridge and the University of Oxford, U.K., in Jul 2017.