Xintong Han

I am a computer vision tech lead at Huya Inc as of August 2019. Before that, I spent one wonderful year at Malong Technologies as a research scientist.

I obtained my Ph.D. degree at the Department of Electrical and Computer Engineering of the University of Maryland, College Park under the supervision of Prof. Larry S. Davis. Prior, I got my B.S. degree from Shanghai Jiao Tong University in China advised by Prof. Weiyao Lin.

I am looking for highly motivated researchers, engineers and interns working on exciting computer vision and graphics projects based in Shenzhen/Guangzhou. If you are interested, please send me an email.

  • Email: xintong@umd.edu; hanxintong@huya.com

    • news

  • [Sep. 2020] PGNet accepted by ACCV 2020 as an oral paper.
  • [Jul. 2020] MakeItTalk accepted by SIGGRAPH Asia 2020.
  • [Nov. 2019] Three papers accepted by AAAI 2020.
  • [Aug. 2019] Joined Huya Inc as a computer vision tech lead.
  • [Jun. 2019] One oral paper and one poster paper accepted by ICCV 2019.

    • publication

    Learning 3D Face Reconstruction with a Pose Guidance Network.
    Pengpeng Liu, Xintong Han, Michael Lyu, Irwin King, Jia Xu
    Asian Conference on Computer Visionn (ACCV), 2020. Oral. [pdf]
    MakeItTalk: Speaker-Aware Talking Head Animation.
    Yang Zhou, Dingzeyu Li, Xintong Han, Evangelos Kalogerakis, Eli Shechtman and Jose Echevarria
    SIGGRAPH Asia, 2020. [pdf]
    iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection.
    Chenfan Zhuang, Xintong Han, Weilin Huang and Matthew R. Scott
    AAAI Conference on Artificial Intelligence (AAAI), 2020. [pdf]
    Channel Interaction Networks for Fine-Grained Image Categorization.
    Yu Gao, Xintong Han, Weilin Huang and Matthew R. Scott
    AAAI Conference on Artificial Intelligence (AAAI), 2020. [pdf]
    Generate, Segment and Refine: Towards Generic Manipulation Segmentation.
    Peng Zhou, Bor-Chun Chen, Xintong Han, Mahyar Najibi, Abhinav Shrivastava, Ser-Nam Lim and Larry S. Davis
    AAAI Conference on Artificial Intelligence (AAAI), 2020. [pdf]
    Compatible and Diverse Fashion Image Inpainting.
    Xintong Han, Zuxuan Wu, Weilin Huang, Matthew R. Scott and Larry S. Davis
    International Conference on Computer Vision (ICCV), 2019. Oral. [pdf][supp]
    ClothFlow: A Flow-Based Model for Clothed Person Generation.
    Xintong Han, Xiaojun Hu, Weilin Huang and Matthew R. Scott
    International Conference on Computer Vision (ICCV), 2019. [pdf][supp]
    Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning.
    Xun Wang, Xintong Han, Weilin Huang, Dengke Dong and Matthew R. Scott
    Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [pdf][code]
    DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation.
    Zuxuan Wu, Xintong Han, Yen-Liang Lin, Mustafa Gkhan Uzunbas, Tom Goldstein, Ser Nam Lim, and Larry Davis
    European Conference on Computer Vision (ECCV), 2018. [pdf]
    VITON: An Image-based Virtual Try-on Network.
    Xintong Han, Zuxuan Wu, Zhe Wu, Ruichi Yu, and Larry Davis
    Conference on Computer Vision and Pattern Recognition (CVPR), 2018. Spotlight. [pdf] [code]

    [Note: the dataset used in this paper is no longer available due to copyright infringements. For those who have already downloaded the data, please do not use or distribute it.]

    Learning Rich Features for Image Manipulation Detection.
    Peng Zhou, Xintong Han, Vlad Morariu, and Larry Davis
    Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [pdf][code]
    NISP: Pruning Networks Using Neuron Importance Score Propagation.
    Ruichi Yu, Ang Li, Chun-Fu Chen, Jui-Hsin Lai, Vlad Morariu, Xintong Han, Mingfei Gao, Ching-Yung Lin, and Larry Davis
    Conference on Computer Vision and Pattern Recognition (CVPR), 2018. Spotlight. [pdf]
    Automatic Spatially-aware Fashion Concept Discovery.
    Xintong Han, Zuxuan Wu, Phoenix Huang, Xiao Zhang, Menglong Zhu, Yuan Li, Yang Zhao, and Larry Davis
    International Conference on Computer Vision (ICCV), 2017. [pdf] [dataset]
    Learning Fashion Compatibility with Bidirectional LSTMs.
    Xintong Han, Zuxuan Wu, Yu-Gang Jiang, and Larry Davis
    ACM Multimedia, 2017. Oral. [pdf] [dataset] [code]
    Two-Stream Neural Networks for Tampered Face Detection.
    Peng Zhou*, Xintong Han*, Vlad Morariu,, and Larry Davis (* equal contribution)
    Conference on Computer Vision and Pattern Recognition, Workshop on Media Forensics (CVPRW), 2017. [pdf]
    Son of Zorn's Lemma: Targeted Style Transfer Using Instance-aware Semantic Segmentation.
    Carlos Castillo, Soham De, Xintong Han, Bharat Singh, Abhay Kumar Yadav, and Tom Goldstein
    International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017. Oral. [pdf]
    VRFP: On-the-fly Video Retrieval using Web Images and Fast Fisher Vector Products
    Xintong Han*, Bharat Singh*, Vlad Morariu, and Larry Davis (* equal contribution)
    IEEE Transaction on Multimedia (TMM), 2017. [pdf]
    Presented at the WebVision workshop CVPR 2017 .
    Machine Learning-based Early Termination in Prediction Block Decomposition for VP9
    Xintong Han, Yunqing Wang, Yaowu Xu, and Jim Bankoski
    IS&T/SPIE Electronic Imaging, 2016. [pdf]
    Selecting Relevant Web Trained Concepts for Automated Event Retrieval
    Bharat Singh*, Xintong Han*, Zhe Wu, Vlad Morariu, and Larry Davis (* equal contribution)
    International Conference on Computer Vision (ICCV), 2015. [pdf]
    Tree-Based Visualization and Optimization for Image Collection
    Xintong Han, Chongyang Zhang, Weiyao Lin, Mingliang Xu, Bin Sheng, and Tao Mei
    IEEE Transactions on Cybernetics, 2015. [pdf]
    PSPGC: Part-Based Seeds for Parametric Graph-Cuts
    Bharat Singh, Xintong Han, Zhe Wu, and Larry Davis
    Asian Conference on Computer Vision (ACCV), 2014. [pdf]