About Me


I am a Researcher with Wormpex AI Research working on AI in Retail. My R&D experience covers Computer Vision, Deep Learning, and Robotics. Before that I was an Algorithm Scientist with Aibee and a Research Scientist with Adobe Research. I obtained my Ph.D degree from Stevens Institute of Technology, advised by Dr. Gang Hua. Before that I obtained my B.E. degree from the University of Science and Technology of China (USTC) in 2010.

[Google Scholar]

Updates:

  • 05/2021: Our paper on Human Pose Estimation and Tracking with GNN is accepted to CVPR 2021
  • 12/2020: Our paper on any-precision NN is accepted to AAAI 2021
  • 07/2020: One paper on the robotic wheelchair we built when I was doing my PhD is accepted to Transactions on Human-Robot Interaction (THRI)
  • 09/2019: Serve as area chair for WACV 2020
  • 08/2019: One paper on efforts towards interpretable face recognition is accepted to ICCV 2019 as oral!
  • 04/2018: The deep learning based face detection and recognition technology I made major contribution to at Adobe had been shipped in Adobe Photoshop, Lightroom, Premiere Pro! Feeling really happy.
  • 10/18/2017: Our face detection technology has been shipped in Photoshop October 2017 release!

Selected Publications:

  • Learning Dense Facial Correspondences In Unconstrained Images,
    Ronald Yu, Shunsuke Saito, Haoxiang Li, Duygu Ceylan, Hao Li,
    IEEE International Conference on Computer Vision (ICCV), 2017
    [Paper]
  • VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation,
    Chuang Gan, Yandong Li, Haoxiang Li, Chen Sun, Boqing Gong,
    IEEE International Conference on Computer Vision (ICCV), 2017
    [Paper] [Github (Code & Data)]
  • Probabilistic Elastic Part Model: A Pose-Invariant Representation for Real-world Face Verification,
    Haoxiang Li, Gang Hua,
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017
  • An Egocentric Computer Vision based Co-Robot Wheelchair,
    Haoxiang Li, Mohammed Kutbi, Xin Li, Changjiang Cai, Philippos Mordohai, Gang Hua,
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016
    [Paper] [Bibtex]
  • A Multi-Level Contextual Model For Person Recognition in Photo Albums ,
    Haoxiang Li, Jonathan Brandt, Zhe Lin, Xiaohui Shen, Gang Hua,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
    [Paper] [Bibtex]
  • Labeled Faces in the Wild: A Survey ,
    Erik Learned-Miller, Gary B. Huang, Aruni RoyChowdhury, Haoxiang Li, and Gang Hua,
    book chapter in Advances in Face Detection and Facial Image Analysis, Springer, 2016
    [Draft]
  • A Convolutional Neural Network Cascade for Face Detection ,
    Haoxiang Li, Zhe Lin, Xiaohui Shen, Jonathan Brandt, Gang Hua,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    [Paper] [Bibtex] [FAQ for Implementation]
  • Efficient Boosted Exemplar-based Face Detection ,
    Haoxiang Li, Zhe Lin, Jonathan Brandt, Xiaohui Shen, Gang Hua,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
    [Paper] [ROC Curves on FDDB] [PR Curve on AFW] [Poster] [Bibtex]
  • Probabilistic Elastic Matching for Pose Variant Face Verification ,
    Haoxiang Li, Gang Hua, Zhe Lin, Jonathan Brandt, Jianchao Yang,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013
    [Paper] [Notes for Reproducing] [Bibtex]

Please refer to my google scholar page for a full list.

Patents:

I have 5 US patents issued and 4 more pending.

Interns:

If you are interested in collaboration, please send email me at mr.pppoe AT gmail.com.