Boyuan Jiang(姜博源)

Senior Researcher at Tencent Youtu Lab.

prof_pic.jpeg

I am a senior researcher at Tencent Youtu Lab, where I work on computer vision and machine learning. Recently, I am working for developing Text-to-Image model of Tencent Cloud.

I got my B.A. from the Harbin Institute of Technology(HIT) in 2017 and got my M.A. degree from the Zhejiang University(ZJU) in 2020. I have ever worked at NetEase, SenseTime and Hikvision as research intern and joined Tencent Youtu Lab in 2020.

news

10/2024 We released FluxFit, a virtual try-on work based on FLUX.1-dev.
02/2024 One paper about fast identity-preserved personalization accepted by CVPR’24.
12/2023 One paper about video action recognition accepted by AAAI’24.
09/2023 One paper about video frame interpolation accepted by IEEE Transactions on Image Processing.
07/2022 One paper about image colorization accepted by ECCV’22.
03/2022 One paper about video frame interpolation accepted by CVPR’22.
03/2021 Our Team Imagination is the winner of CVPR NTIRE 2021 Challenge on Video Spatial-Temporal Super-Resolution.
12/2020 One paper about action recognition accepted by AAAI’21.
04/2020 I joined Tencent Youtu Lab.
03/2020 I graduated from Zhejiang University.
02/2020 One paper about domain adaption accepted by CVPR’20.
07/2019 One paper about action recognition accepted by ICCV’19.
11/2018 One paper about unsupervised domain adaption accepted by AAAI’19.

selected publications

  1. ColorFormer: Image Colorization via Color Memory assisted Hybrid-attention Transformer
    Ji, Xiaozhong*, Jiang, Boyuan*, Luo, Donghao, Tao, Guangpin, Chu, Wenqing, Xie, Zhifeng, Wang, Chengjie, and Tai, Ying
    European Conference on Computer Vision (ECCV) 2022
  2. IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
    Kong, Lingtong*, Jiang, Boyuan*, Luo, Donghao, Chu, Wenqing, Huang, Feiyue, Tai, Ying, Wang, Chengjie, and Yang, Jie
    Computer Vision and Pattern Recognition (CVPR) 2022
  3. Learning Comprehensive Motion Representation for Action Recognition
    Wu, Mingyu*, Jiang, Boyuan*, Luo, Donghao, Yan, Junchi, Wang, Yabiao, Tai, Ying, Wang, Chengjie, Li, Jilin, Huang, Feiyue, and Yang, Xiaokang
    AAAI Conference on Artificial Intellige (AAAI) 2021
  4. Stm: Spatiotemporal and motion encoding for action recognition
    Jiang, Boyuan, Wang, MengMeng, Gan, Weihao, Wu, Wei, and Yan, Junjie
    International Conference on Computer Vision (ICCV) 2019