photo

Email: jensen dot zhoujh at gmail dot com


Bio | Publications | Projects | Interests | Experiences

Jinghao (/dʒɪŋhaw/) Zhou | Jensen

Jinghao (/dʒɪŋhaw/) Zhou | Jensen

alt-text

Email: jensen dot zhoujh at gmail dot com


I am a first-year Ph.D. student at University of Oxford supervised by Prof. Philip Torr and Dr. Christian Rupprecht. Previously, I completed my bachelor degree at Northwestern Polytechnical University in 2021.

I like building general-purpose models in the context of self-supervised learning and multi-modality learning. I had fun researching artificial intelligence at Microsoft, ByteDance, JHU, and SenseTime.

News 🎉

  • Feb. 2023 - xCLIP gets accepted by CVPR 2023.
  • Nov. 2022 - The code and pre-trained models of dBOT are released.
  • Jan. 2022 - iBOT gets accepted by ICLR 2022.
  • Dec. 2021 - The code and pre-trained models of iBOT are released.
  • Nov. 2019 - DROL gets accepted by AAAI 2020.

Publications

Full Publications: Google Scholar

  • Non-Contrastive Learning Meets Language-Image Pre-Training

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

    arXiv
  • Exploring Target Representations for Masked Autoencoders

    Xingbin Liu*, Jinghao Zhou*, Tao Kong, Xianming Lin, Rongrong Ji
    Tech report, 2022

    arXiv / code
  • 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

    arXiv
  • Discriminative and Robust Online Learning for Siamese Visual Tracking

    Jinghao Zhou, Peng Wang, Haoyang Sun
    AAAI, 2020

    arXiv / camera-ready / code

Projects

  • Information Fusion and Multi-dimention Vision on Wheeled Soccer Robot
    slide / code

Interests

Self-Supervised Learning, Multi-Modality Learning, General-Purpose Models, Few-Shot Learning, Visual Object Tracking, etc.

Experiences