I am currently a PhD student at the University of Washington advised by Prof. Dieter Fox.

Before that, I received my M.S. degree in Control Science and Technology from Tsinghua University in 2017 advised by Prof. Xiangyang Ji and my bachelor's degree in Automation from Tsinghua University in 2014. I also worked with Dr. Jifeng Dai as a research intern at Microsoft Research Asia for 18 months.

My research focuses on computer vision and deep learning, with an emphasis on providing better algorithms for machines to understand the world. My current work is to extract more information from RGB images, like accurately estimating object poses using RGB images.



  • Our paper DeepIM has been accepted by ECCV 2018 as oral! Code is released on Github and awarded one of the 12 best papers in ECCV 2018. An extended version is published in IJCV.
  • Our paper Deformable ConvNets has been accepted by ICCV 2017. Code is released on Github. There is also a cool third-party improvement showing the best single-model performance on the COCO dataset.
  • Awarded Excellent Graduates of Beijing.
  • Our paper FCIS has been accepted by CVPR 2017 as a spotlight! Check out the code on Github
  • We won first prize in MS COCO segmentation challenge 2016.
  • Our paper R-FCN has been accepted by the NIPS 2016 conference, and the code is released on Github.
  • Our paper Inst-FCN has been accepted by the ECCV 2016 conference.


Google Scholar
(+ indicates equal contribution)

DeepIM: Deep Iterative Matching for 6D Pose Estimation
Yi Li, Gu Wang, Xiangyang Ji, Yu Xiang, Dieter Fox
In International Journal of Computer Vision (IJCV), 2020
In European Conference on Computer Vision (ECCV), 2018 (oral).
PDF, Bibtex, Code Poster Slides Project Page IJCV PDF
Deformable Convolutional Networks
Jifeng Dai+, Haozhi Qi+, Yuwen Xiong+, Yi Li+, Guodong Zhang+, Han Hu, and Yichen Wei
In International Conference on Computer Vision (ICCV), 2017 (oral).
PDF, Bibtex, Code
Fully Convolutional Instance-aware Semantic Segmentation
Yi Li+, Haozhi Qi+, Jifeng Dai, Xiangyang Ji, and Yichen Wei
In Computer Vision and Pattern Recognition (CVPR), 2017 (spotlight)
PDF, Bibtex, Code Visualize Results, Slides
R-fcn: Object detection via region-based fully convolutional networks
Jifeng Dai, Yi Li, Kaiming He, Jian Sun
In Advances in Neural Information Processing Systems (NIPS), 2016
PDF, Bibtex, Code, Poster
Instance-sensitive fully convolutional networks
Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, Jian Sun
In European Conference on Computer Vision (ECCV), 2016
PDF, Bibtex, Poster

Honor and Awards

  • Reviewer of AAAI, CVPR, ICCV, and ECCV since 2018
  • Outstanding 2017 Master's Thesis by the Chinese Institute of Electronics (ranked 10th in China)
  • Outstanding 2017 Graduate Student in Beijing
  • Outstanding 2016 Intern in MSRA
  • 2013 National Scholarship
  • 2012 Tsinghua Alumni Zheng Geru Scholarship