Jia Xu, Ph.D.


Email: jiaxu [at] cs.wisc.edu
Picture of Jia Xu

Biography

I am the Head of AI and General Manager at Huya Inc. I was a principal researcher and manager at Tencent AI Lab. Before returning to China, I worked as a senior research scientist in the Intel Visual Computing Lab, lead by the awesome Vladlen Koltun. I received my Ph.D. in Computer Sciences at the University of Wisconsin-Madison, with my thesis committee of Prof. Vikas Singh (advisor), Prof. Chuck Dyer, Prof. Jerry Zhu, Prof. Jude Shavlik, and Prof. Mark Craven. I was a visiting student in University of Toronto and in Toyota Technological Institute at Chicago, both working with the amazing Prof. Raquel Urtasun. Before graduate school, I obtained my B.S. degree from the Department of Computer Science and Technology at Nanjing University, China.

  • We are hiring motivated researchers/engineers/interns. If you work on computer vision, deep learning, speech recognition, or computer graphics, feel free to contact me.
  • What's New

  • Mar. 2021: Our Few-Shot Human Motion Transfer paper was accepted to CVPR 2021.
  • Sep. 2020: Our 3D Face Reconstruction paper was accepted to ACCV 2020 for full oral presentation.
  • Feb. 2020: Our Flow2Stereo paper was accepted to CVPR 2020. State-of-the-art self-supervised learning results for Optical Flow and Stereo Matching on KITTI 2012 and 2015.
  • Jun. 2019: Our SelFlow paper was selected in the CVPR Best Paper Finalist.
  • Mar. 2019: Our Self-Supervised Optical Flow Learning paper was selected for full oral presentation at CVPR 2019. This was the Winner entry of Sintel Optical Flow Benchmark from 11/2018 tp 11/2019.
  • Feb. 2019: Two papers were accepted to CVPR 2019. Congratulations to my interns Pengpeng and Jing, these are their very first CVPR papers!
  • Dec. 2018: Our DHER paper was accepted to ICLR 2019. Congratulations to team!
  • Nov. 2018: Our DDFlow paper was accepted to AAAI 2019 as oral presentation. Congratulations to my intern, Pengpeng! This is Pengpeng's very first paper published at a top tier conference.
  • Aug. 2018: Together with my intern Shiyu and collaborators at Tsinghua University, we won the Visual Doom AI Competition 2018.
  • Feb. 2018: Our Learning to See in the Dark paper was accepted to CVPR 2018.
  • July 2017: Our Fast Image Processing paper was accepted to ICCV 2017.
  • Feb. 2017: Our DCFlow paper was accepted to CVPR 2017. Winner on the Sintel Optical Flow Benchmark from 11/2016 to 11/2017.
  • Research Projects

    Optical Flow


  • Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching, CVPR 2020
  • SelFlow: Self-Supervised Learning of Optical Flow, CVPR 2019
  • DDFlow: Learning Optical Flow with Unlabeled Data Distillation, AAAI 2019
  • DCFlow: Accurate Optical Flow via Direct Cost Volume Processing, CVPR 2017
  • Fast Image Processing


  • Learning to See in the Dark, CVPR 2018
  • Fast Image Processing with Fully-Convolutional Networks, ICCV 2019
  • Semantic Segmentation


  • Learning to Segment Under Various Forms of Weak Supervision, CVPR 2015
  • Tell Me What You See and I will Show You Where It Is, CVPR 2014
  • Gaze-enabled Egocentric Video Summarization


  • Gaze-enabled Egocentric Video Summarization via Constrained Submodular Maximization, CVPR 2014
  • Structured Sparsity for Video Segmentation and Spectral Clustering


  • Spectral Clustering with a Convex Regularizer on Millions of Images, ECCV 2014
  • GOSUS: Grassmannian Online Subspace Updates with Structured-sparsity, ICCV 2013
  • Interactive Segmentation and Contour Completion


  • Incorporating Topological Constraints within Interactive Segmentation and Contour Completion via Discrete Calculus, CVPR 2012
  • Cosegmentation


  • Analyzing the Subspace Structure of Related Images: Concurrent Segmentation of Image Sets, ECCV 2012
  • Random Walks based Multi-Image Cosegmentation: : Quasiconvexity Results and GPU-based Solutions, CVPR 2012
  •  

    Computer Sciences | UW Home
    Locations of visitors to this page
    eXTReMe Tracker