视觉智能

研究方向

  • 视觉人脸分析：人脸对齐、年龄估计、人脸合成等任务

  • 三维人脸重建：研究基于三维重建的数字人生成技术

  • 基于机理驱动的动态建模：深度学习与机理学习融合，面向通用和可解释的动态建模算法


    • 代表性工作：
    [1] Zhu C, Wan X, Li J, et al. Occlusion-robust Face Alignment using A Viewpoint-invariant Hierarchical Network Architecture[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022：11112-11121. (Oral presentation)
    [2] Zhu C, Li X, Li J, et al. Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2021: 11751-11760.
    [3] Zhu C, Liu H, Yu Z, et al. Towards omni-supervised face alignment for large scale unlabeled videos[C]//Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2020, 34(07): 13090-13097. (Spotlight paper)
    [4] Zhu C, Li X, Li J, et al. Spatial-temporal knowledge integration: robust self-supervised facial landmark tracking[C]//Proceedings of the 28th ACM International Conference on Multimedia (ACM MM). 2020: 4135-4143.