Home Biography Education Research
Wanli Ouyang, Ph.D, IEEE Senior Member.
Associate Professor at the University of Sydney
I'm with MMlab and SIGMA lab
SIGMA lab, School of Electrical and Information Engineering,
The University of Sydney,
Sydney, Australia



Wanli Ouyang obtained Ph.D from the Dept. of Electronic Engineering , the Chinese University of Hong Kong. He is now an associate professor at the University of Sydney. His research interests include deep learning and its application to computer vision and pattern recognition, image and video processing.

CV PDF Download Wanli Ouyang's Full CV      View Wani Ouyang's LinkedIn ProfileView Wanli Ouyang's LinkedIn Profile      View Wani Ouyang's Google Scholar Citations View Wanli Ouyang's Google Scholar Citations

Back To Top

Information for potential Postdoctoral Fellow, Master and Ph.D. students and Final Year Program students

I moved to the School of Electrical and Information Engineering, University of Sydney as an associate professor on 2017. If you are interested in my research topic and this university, please feel free to contact me after reading the information available here .


AI 2000 Most Influential Scholars Honorable Mention in Computer Vision (only 3 recipients in Australia)


My recent talk on 'From Manual Design to Automatic Deep Learning'

My recent tutorial on 'Deep learning in object detection' at PRCV 2019

My recent talk on ‘Structured deep learning for visual localization and recognition’

My talk ‘Modeling deep structures for 3D scene understanding’ at ACCV 2018 workshop

My talk ‘Modeling deep structures for using high performance images’ at ACCV 2018 workshop

Good resources on Paper Writing

How to do good research on computer vision (Chinese)
Making Data meaningful
Slides on "How to get your paper rejected." By Prof. Ming-Hsuan Yang from UC Merced
Chinese blog on how to publish a top journal

Good advices for Research Students

How to write a good review?
How to be good CVPR reviewer? A good Area Chair? A good author?
Three Sins of Authors in Computer Science and Math
How to give research talk (Simon Peyton Jones, co-creator of the C-- programming language)
How to write great research paper(Simon Peyton Jones, co-creator of the C-- programming language)
How to read paper(Harry Shum)
如何写/审AI领域的论文 VALSE Webinar
研究生导师:这种学生,才是我眼中的科研好苗子!(Advice in Chinese)

Chef's Recommendation on Papers

Rui Zhao Wanli Ouyang, and Xiaogang Wang, "Unsupervised Salience Learning for Person Re-identification", Proc. IEEE CVPR 2013 (CVPR/ICCV most influential paper)
Wanli Ouyang, Xiaogang Wang, "Joint Deep Learning for Pedestrian Detection", Proc. IEEE ICCV 2013 (CVPR/ICCV most influential paper)
Dongzhan Zhou, Xinchi Zhou, Wenwei Zhang, Chen Change Loy, Shuai Yi, Xuesen Zhang, Wanli Ouyang, “EcoNAS: Finding Proxies for Economical Neural Architecture Search”, Proc. CVPR, 2020.

Our recent survey on object detection:
Liu, Li, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, and Matti Pietikäinen, "Deep learning for generic object detection: A survey," IJCV, accepted, 2019. [Full Text]

A new back-bone deep model design (performs better than ResNet and DenseNet):
Shuyang Sun, Jiangmiao Pang, Jianping Shi, Shuai Yi, Wanli Ouyang, "FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction," NuerIPS. (Previously called NIPS), 2018. [Full Text] [ Source code ]

The first end-to-end deep video compression model:
Guo Lu, Wanli Ouyang, Dong Xu, Xiaoyun Zhang, Chunlei Cai, Zhiyong Gao, "DVC: An End-to-end Deep Video Compression Framework," In Proc. CVPR 2019. [Full Text] [Source code]

Details on our wining entry in ImageNet 2016 challenge on object detection:
Xingyu Zeng (equal contribution), Wanli Ouyang (equal contribution), Junjie Yan, Hongsheng Li, Tong Xiao, Kun Wang, Yu Liu, Yucong Zhou, Bin Yang, Zhe Wang, Hui Zhou, Xiaogang Wang, "Crafting GBD-Net for Object Detection," IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), accepted, 2017. [Full Text] [Project page & code ] [ Source code ]

The first work modeling deformation in deep CNN, used for pedestrian detection:
Wanli Ouyang, Hui Zhou, Hongsheng Li, Quanquan Li, Junjie Yan, Xiaogang Wang, "Jointly learning deep features, deformable parts, occlusion and classification for pedestrian detection," IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), 40(8):1874-1887, 2018. [Full Text] [Source code]

Extend our work on modeling deformation for generic object detection. This new deformation handling layer can be placed anywhere.
Wanli Ouyang, Xingyu Zeng, Xiaogang Wang, et al, "DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks," IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), accepted, 2016. [Full Text] [Project]

The first cascade network for generic object detection.
Wanli Ouyang, Kun Wang, Xin Zhu, Xiaogang Wang. "Chained Cascade Network for Object Detection", Proc. ICCV, 2017. [Full Text] [Source code]

A simple and effective multi-scale feature operation. Showing and solving the initialization problem in existing multi-branch networks, e.g. Inception V2-V5, Hourglass, ResNxt, etc.
Wei Yang, Shuang Li, Wanli Ouyang, Hongsheng Li, XiaogangWang. "Learning Feature Pyramids for Human Pose Estimation", Proc. ICCV, 2017. [Full Text] [Source code]

The first work on structured feature learning.
X. Chu, Wanli Ouyang , H. Li, and X. Wang. "Structured feature learning for pose estimation", In Proc. CVPR 2016. [Full Text] [Project and dataset ] [Spotlight talk] [Source code ] [Supplementary ]

The first Fully Convolutional Network for visual tracking.
Lijun Wang, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu, "Visual Tracking with Fully Convolutional Networks", In Proc. ICCV 2015. [Full Text] [Project and source code ]

Journal Papers

Back To Top

Conference Papers

Back To Top