Email: jensen dot zhoujh at gmail dot com

Jensen (Jinghao) Zhou

Jensen (Jinghao) Zhou


Email: jensen dot zhoujh at gmail dot com

I am a second-year Ph.D. student at University of Oxford supervised by Prof. Christian Rupprecht and Prof. Philip Torr. I am a part of both the Visual Geometry Group as well as Torr Vision Group. Previously, I completed my bachelor degree at Northwestern Polytechnical University in 2021.

I like building multi-modal generative models and self-supervised general-purpose models. I had fun researching artificial intelligence at Google (2023), Microsoft (2022), ByteDance (2021), JHU (2021), and SenseTime (2020).

News 🎉

  • Jan. 2022 - dBOT gets accepted by ICLR 2024.
  • Feb. 2023 - xCLIP gets accepted by CVPR 2023.
  • Jan. 2022 - iBOT gets accepted by ICLR 2022.
  • Dec. 2021 - The code and pre-trained models of iBOT are released.


Full Publications: Google Scholar

  • Scene-Conditional 3D Object Stylization and Composition

    Jinghao Zhou, Tomas Jakab, Philip Torr, Christian Rupprecht
    Tech report, 2023

    arXiv / project page / code
  • Exploring Target Representations for Masked Autoencoders

    Xingbin Liu*, Jinghao Zhou*, Tao Kong
    ICLR, 2024

    arXiv / code
  • Non-Contrastive Learning Meets Language-Image Pre-Training

    Jinghao Zhou, Li Dong, Zhe Gan, Lijuan Wang, Furu Wei
    CVPR, 2023

  • iBOT: Image BERT Pre-Training with Online Tokenizer

    Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, Tao Kong
    ICLR, 2022

    arXiv / camera-ready / code / press
  • Real-Time Visual Object Tracking via Few-Shot Learning

    Jinghao Zhou, Bo Li, Peng Wang, Peixia Li, Weihao Gan, Wanli Ouyang
    Bachelor thesis 🎓, 2021

  • Discriminative and Robust Online Learning for Siamese Visual Tracking

    Jinghao Zhou, Peng Wang, Haoyang Sun
    AAAI, 2020

    arXiv / camera-ready / code


Multi-Modal Generative Models, Self-Supervised Learning, General-Purpose Models, Visual Object Tracking, etc.


  • Research Intern
    Apr. 2020 - Mar. 2021