Picture of me.

Wenjie Yin (印文杰)

Machine Learning | Human Motion Analysis | Human Robot Collaboration | Gaming | SuperResolution

About me

I am currently a machine learning researcher at HUAWEI Singapore Researcher Centre. I was a postdoctoral fellow at the Division of Robotics, Perception and Learning at KTH Royal Institute of Technology, where I work on generative models and multimodal representation learning. My postdoctoral advisor is Danica Kragic. I obtained my Ph.D. degree in Computer Science at KTH Royal Institute of Technology, supervised by Mårten Björkman. During my PhD, I visited the National Institute of Informatics (NII) and had an internship at MSRA. Prior to that, I obtained my M.S. in Systems, Control and Robotics from KTH Royal Institute of Technology and a B.S. in Automation from Zhejiang University.

Research Interests

  • Human Motion Analysis: Motion understanding, Dance style transfer, Dance choreography
  • Human Agent Interaction: Human-human/robot interaction, group behaviors, Multimedia
  • Deep Learning: Generative models, Graph neural networks, Foundation Models
  • Selected Publications

      Human Motion Analysis
    LM2D: Lyrics- and Music-Driven Dance Synthesis
    Wenjie Yin*, Xuejiao Zhao*, Yi Yu, Hang Yin, Danica Kragic, Marten Bjorkman
    (under review)
    [PDF] [BibTex] [VIDEO]

    Scalable Motion Style Transfer with Constrained Diffusion Generation
    Wenjie Yin, Yi Yu, Hang Yin, Danica Kragic, Marten Bjorkman
    The 38th Annual AAAI Conference on Artificial Intelligence (AAAI2024)
    [PDF] [BibTex] [VIDEO]

    Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models
    Wenjie Yin, Ruibo Tu, Hang Yin, Danica Kragic, Hedvig Kjellström, Marten Bjorkman
    The 32th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)
    [PDF] [BibTex] [VIDEO]

    Multimodal Dance Style Transfer
    Wenjie Yin, Yi Yu, Hang Yin, Kim Baraka, Danica Kragic, Marten Bjorkman
    Journal of Machine Vision and Applications (MVAP)
    [PDF] [BibTex] [VIDEO]

    Graph-based Normalizing Flow for Human Motion Generation and Reconstruction
    Wenjie Yin, Hang Yin, Danica Kragic, Marten Bjorkman
    The 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)
    [PDF] [BibTex]

    Group behavior recognition using attention-and graph-based neural networks
    Fangkai Yang*, Wenjie Yin*, Tetsunari Inamura, Marten Bjorkman, Christopher Peters
    The 24th European Conference on Artificial Intelligence (ECAI 2020)
    [PDF] [BibTex]

      Human Agent Interaction
    Improving EEG-based Motor Execution Classification for Robot Control
    Sumeyra U. Demir Kanik, Wenjie Yin, Arzu Guneysu Ozgur, Ali Ghadirzadeh, Mårten Björkman, Danica Kragic
    The 24th International Conference on Human-Computer Interaction (HCII)
    [PDF] [BibTex]

    Human-centered collaborative robots with deep reinforcement learning
    Ali Ghadirzadeh, Xi Chen, Wenjie Yin, Zhengrong Yi, Mårten Björkman, Danica Kragic
    IEEE Robotics and Automation Letters (RAL)
    [PDF] [BibTex]

    Impact of trajectory generation methods on viewer perception of robot approaching group behaviors
    Fangkai Yang*, Wenjie Yin*, Mårten Björkman, Christopher Peters
    The 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)
    [PDF] [BibTex]

    Accurate targeting in robot-assisted TCM pulse diagnosis using adaptive sensor fusion
    Jingjing Luo, Chun Ouyang, Xiaokai Nie, Wenjie Yin, Hong Lu, Yuzhu Guo
    Periodicals of Engineering and Natural Sciences.
    [PDF] [BibTex]

      Other Topics
    Diffusion-based Time Series Data Imputation for Microsoft 365
    Fangkai Yang, Wenjie Yin, Lu Wang, Tianci Li, Pu Zhao, Bo Liu, Paul Wang, Bo Qiao, Yudong Liu, Marten Bjorkman, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang
    Proceedings of the ACM Transactions on Embedded Computing Systems
    [PDF] [BibTex]

    SmartTBD: Smart Tracking for Resource-constrained Object Detection
    Shihang Zhou, Alejandra Hernandez, Clara Gomez, Wenjie Yin, Marten Bjorkman
    Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2023)
    [PDF] [BibTex]

    Automated Underwater Pipeline Damage Detection using Neural Nets
    Shijia Jun*, Wenjie Yin*, Yipai Du*, John Folkesson
    ICRA 2019 Workshop on Underwater Robotics Perception
    [PDF] [BibTex]

    Services

      Program Committee
  • The first Multimodal Representation Learning Workshop at ICLR
  •   Conference Reviewers
  • IEEE International Conference on Robotics and Automation (ICRA)
  • ACM Multimedia (ACM-MM)
  •   Journal Reviewers
  • IEEE Transactions on Multimedia
  • International Journal of Human-Computer Interaction (IJHCI)
  • Imaging Science Journal
  • IEEE Robotics and Automation Letters (RA-L)
  • Supervised students

  • Zhen Han - In-game Voice2Face Model Distillation [2024.03-Present]
  • Dominykas Jogela - Group Dance Generation with Generative Models [2023.11-Present]
  • Qingyuan Yao - Lyric- and Music-driven Dance Generation [2023.03-2023.08]
  • Shihang Zhou - Distributed Object Detection and Tracking [2022.09-2023.06]
  • Yang Gao - Long-Term Pose-Based Trajectory Prediction for Pedestrians [2021.12-2023.12]
  • Jia Fu - Multimodal Machine Learning in Human Motion Analysis [2017.09-2022.09]
  • Teaching

      KTH Royal Institute of Technology
  • DD2421: Machine Learning (Fall 2019 – Autumn 2023)
  • DD2423: Image Analysis and Computer Vision (Fall 2018 – Autumn 2023)
  •   Zhejiang University
  • Java Programming (Fall 2016)
  • Hobbies

    Fitness
    (Power Lifting)
    Cat
    (2 Years Old)
    Drawing
    (My Supervisor)