Ph.D. student, Computer Science
Peking University
Curriculum Vitae


 

I’m a final year PhD student in the School of Computer Science at Peking University. Currently, I am a member of VMC lab under the supervision of Prof. Shiliang Zhang. Prior to that, I received my Bachelor degree (Electronic Information Engineering) in 2019 from University of Electronic Science and Technology of China. My research interests include Computer Vision and Machine Learning. Specifically, I am interested in building human-aware AI systems that can perceive and understand human beings, including Human Pose and Shape Estimation and Person Re-identification.

News

  • [2024.02] Two papers are accepted by CVPR 2024.
  • [2024.01] One paper is accepted by CJC 2024.
  • [2023.07] One paper is accepted by ACM MM 2023.
  • [2023.07] One paper is accepted by ICCV 2023.
  • [2023.02] One paper is accepted by TPAMI 2023.
  • [2022.08] One paper is accepted by IJCV 2022.
  • [2022.03] One paper is accepted by CVPR 2022.
  • [2021.09] One paper is accepted by NeurIPS 2021.
  • [2020.02] One paper is accepted by CVPR 2020.

Publications

  • LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model
    Dongkai Wang, Shiyu Xuan, Shiliang Zhang
    Conference on Computer Vision and Pattern Recognition. CVPR 2024.
    [coming soon]

  • Spatial-Aware Regression for Keypoint Localization
    Dongkai Wang, Shiliang Zhang
    Conference on Computer Vision and Pattern Recognition. CVPR 2024.
    [coming soon]

  • Deep Learning Based 2D Human Pose Estimation: Present and Future
    Jianing Li*, Dongkai Wang *, Shiliang Zhang (* indicates equal contribution)
    Chinese Journal of Computers. CJC 2024.
    [Paper]

  • HumVis: Human-Centric Visual Analysis System
    Dongkai Wang, Shiliang Zhang, Yaowei Wang, Yonghong Tian, Tiejun Huang, Wen Gao
    ACM International Conference on Multimedia. ACM MM 2023.
    [Paper] [Code]

  • 3D Human Mesh Recovery with Sequentially Global Rotation Estimation
    Dongkai Wang, Shiliang Zhang
    International Conference on Computer Vision. ICCV 2023.
    [Paper] [Code]

  • Contextual Instance Decoupling for Instance-Level Human Analysis
    Dongkai Wang, Shiliang Zhang
    IEEE Transactions on Pattern Analysis and Machine Intelligence. TPAMI 2023.
    [Paper] [Code]

  • Unsupervised Person Re-identification via Multi-label Classification
    Dongkai Wang, Shiliang Zhang
    International Journal of Computer Vision. IJCV 2022.
    [Paper]

  • Contextual Instance Decoupling for Robust Multi-Person Pose Estimation
    Dongkai Wang, Shiliang Zhang
    Conference on Computer Vision and Pattern Recognition. CVPR 2022.
    [Paper] [Code] Oral Presentation

  • Robust Pose Estimation in Crowded Scenes with Direct Pose-Level Inference
    Dongkai Wang, Shiliang Zhang, Gang Hua
    Conference on Neural Information Processing Systems. NeurIPS 2021.
    [Paper] [Code]

  • Unsupervised Person Re-identification via Multi-label Classification
    Dongkai Wang, Shiliang Zhang
    Conference on Computer Vision and Pattern Recognition. CVPR 2020.
    [Paper] [Code] Oral Presentation