Siyuan Qiao

CCVL Research Group, Johns Hopkins University

I am currently a Ph.D. student in the Department of Computer Science, Johns Hopkins University, advised by Bloomberg Distinguished Professor Alan Yuille. Before joining Johns Hopkins University, I obtained my B.Sc. degree in 2016 from Shanghai Jiao Tong University.

My research interest is computer vision with focuses on image recognition with limited data, object detection, and instance segmentation. I’ve been really fortunate to have worked with great research scientists in YITU, Baidu IDL, Adobe, and Google.

I’ll join Google as a Research Scientist after graduation.

news

Feb 28, 2021 3 papers accepted to CVPR 2021.
Dec 10, 2020 Check out our ViP-DeepLab on Depth-aware Video Panoptic Segmentation.
Jun 3, 2020 Check out our DetectoRS: 55.7% box AP, 48.5% mask AP, and 50.0% PQ on COCO.

selected publications

  1. CVPR
    ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
    Qiao, Siyuan, Zhu, Yukun, Adam, Hartwig, Yuille, Alan, and Chen, Liang-Chieh
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2021
    PDF Code Video
  2. CVPR
    DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
    Qiao, Siyuan, Chen, Liang-Chieh, and Yuille, Alan
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2021
    PDF Code
  3. CVPR Oral
    Neural Rejuvenation: Improving deep network training by enhancing computational resource utilization
    Qiao, Siyuan, Lin, Zhe, Zhang, Jianming, and Yuille, Alan L
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019
    PDF Code
  4. CVPR Spotlight
    Few-shot image recognition by predicting parameters from activations
    Qiao, Siyuan, Liu, Chenxi, Shen, Wei, and Yuille, Alan L
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018
    PDF Code