Skip to content

HKU-IDS Scholar

(Member, HKU IDS Seminar Committee)

Dr Yanchao YANG
Assistant Professor
HKU Musketeers Foundation Institute of Data Science and
Department of Electrical and Electronic Engineering, HKU
 About Me

Dr Yanchao Yang is an Assistant Professor in the Department of Electrical and Electronic Engineering (EEE) and the HKU Musketeers Foundation Institute of Data Science (HKU-IDS). Before joining HKU, he was a Postdoctoral Research Fellow at Stanford University with Prof. Leonidas J. Guibas at the Geometric Computation Group. He received his Ph.D. from the University of California, Los Angeles (UCLA), working with Prof. Stefano Soatto. Earlier, he obtained his Master’s and Bachelor’s degrees from KAUST and USTC, respectively. He researches at the intersection of computer vision, machine learning, and robotics, with a long-term goal in developmental embodied intelligence. He currently focuses on self-supervised and semi-supervised techniques that allow autonomous agents to learn perception and representation at low-annotation regimes for physical interactions in open environments.

Current Research Project

Dr Yang’s latest effort is to revolutionize scene representations for embodied intelligence by leveraging information-theoretic tools. The team of Dr Yang is constantly looking for talents with the ambition to build fundamentals for autonomous agents so that they can learn from unlimited data streams toward intelligent interactions with the physical world. This quest is related but not limited to computer vision and graphics, machine learning, communication and information theory, multimodal data mining, robotics, and human-machine interaction. Dr Yang’s team loves to work with potential collaborators who have solid mathematical and algorithmic skills.

Selected Publications
  • Yang Zheng, Yanchao Yang*, Kaichun Mo, Jiaman Li, Tao Yu, Yebin Liu, Karen Liu, Leonidas J Guibas. GIMO: Gaze-Informed Human Motion Prediction in Context. European Conference on Computer Vision (ECCV), 2022
  • Yuefan Shen*, Yanchao Yang*, Mi Yan, He Wang, Youyi Zheng, Leonidas J Guibas. Domain Adaptation on Point Clouds via Geometry-Aware Implicits. Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

  • Hanxiang Ren*, Yanchao Yang*, He Wang, Bokui Shen, Qingnan Fan, Youyi Zheng, C Karen Liu, Leonidas J Guibas. ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation. Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

  • Chuanyu Pan*, Yanchao Yang*, Kaichun Mo, Yueqi Duan, Leonidas J Guibas. Object Pursuit: Building a Space of Objects via Discriminative Weight Generation. International Conference on Learning Representations (ICLR), 2022

  • Yanchao Yang, Brian Lai, Stefano Soatto. DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping. Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

  • Yanchao Yang, Stefano Soatto. FDA: Fourier Domain Adaptation for Semantic Segmentation. Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

  • Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto. Phase Consistent Ecological Domain Adaptation. Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

  • Yanchao Yang, Yutong Chen, Stefano Soatto. Learning to Manipulate Individual Objects in an Image. Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

  • Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto. Unsupervised Moving Object Detection via Contextual Information Separation. Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

  • Yanchao Yang, Alex Wong, Stefano Soatto. Dense Depth Posterior (DDP) from Single Image and Sparse Range. Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Research Interests
Computer Vision, Machine Learning, Representation Learning, Self-Supervised Learning, Geometric Processing, Robotics, and Human-Machine Interaction.