Jing HAO

I'm pursuing my Ph.D. degree in the University of HongKong, Faculty of Dentistry (Ranking 3rd in the world), specializing in Medical AI and MLLM, supervised by Prof. Kuo Feng Hung and Prof. Tsoi, James Kit Hon.

Previously, I worked as a Computer Vision Engineer on Baidu VIS from 2022.07 to 2024.08. I received my M.S. degree in Huazhong University of Science and Technology (HUST, 2022), and B.S. degree in Chinese University of Mining and Technology (CUMT, 2020).

My research interests span the area of computer vision, self-supervised pre-training, multimodal large language model (mllm), and AI4Science.

 /   /   /   / 

profile photo
News

  • [Nov.2024] One paper SemiT-SAM has been accepted to MICCAI 2024 Workshop !
  • [Oct.2024] One paper GEM has been accepted to TMM !
  • [Oct.2024] I got 6th place in ToothFairy2 : Semi-supervised Teeth Segmentation hold on MICCAI2024 !
  • [Sep.2024] One paper FullAnno has been released in Arxiv !
  • [July.2024] I got the firm offer from HKU, and had been a formal Ph.D. student !
  • [July.2024] One paper METR has been accepted to Neural Networks !
  • [Aug.2023] I have received my IELTS scores 7(6)!
  • Publications

    See full list at Google Scholar. (* indicates equal contribution, # indicates corresponding author)

    dise SemiT-SAM: Building a Visual Foundation Model for Tooth Instance Segmentation on Panoramic Radiographs
    Jing Hao, Moyun Liu, Lei He, Lei Yao, James Kit Hon Tsoi, Kuo Feng Hung
    [paper] [dataset] [code] | Github stars
    MICCAI 2024 Workshop

    We participated in the challenge of “MICCAI STS 2024: Panoramic X-ray Images”, and ranked 6th among all submitted teams.

    dise FullAnno: A Data Engine for Enhancing Image Comprehension of MLLMs
    Jing Hao, Yuxiang Zhao, Song Chen, Yanpeng Sun, Qiang Chen, Jingdong Wang
    [paper]
    Arxiv. preprint

    We designed a FullAnno system, which is a data engine that can generate large-scale, high-quality, and fine-grained image caption datasets automatically.

    dise A semi-supervised transformer-based deep learning framework for automated tooth segmentation and identification on panoramic radiographs
    Jing Hao, Lun M Wong, Zhiyi Shan, Qi Yong H. Ai, Xieqi Shi, James Kit Hon Tsoi, Kuo Feng Hung #
    [paper] [code] | Github stars
    Diagnostics, 2024 (JCR Q1, IF=3.0)

    This study proposed a novel semi-supervised transformer-based framework designed for automated tooth segmentation and identification on panoramic radiographs.

    dise T-Mamba: A unified framework with Long-Range Dependency in dual-domain for 2D & 3D Tooth Segmentation
    Jing Hao, Yonghui Zhu, Lei He, Moyun Liu, Kuo Feng Hung
    [paper] [dataset] [code] | Github stars
    Submitted to IEEE JBHI

    T-Mamba is the first work to introduce frequency-based features into vision mamba, its flexibility allows it to process both 2D and 3D tooth data without the need for separate modules.

    dise GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models
    Jing Hao, Moyun Liu, Jinrong Yang, Kuo Feng Hung
    [paper] [dataset] [code] | Github stars
    IEEE Transactions on Multimedia (TMM), 2024 (JCR Q1, IF=8.4)

    The first to propose exploring to the solution of glass surface segmentation by fully harnessing the capabilities of existing VFMs.

    dise Language-aware Multiple Datasets Detection Pretraining for DETRs
    Jing Hao, Song Chen
    [paper] [code] | Github stars
    Neural Networks, 2024 (JCR Q1, IF=7.9)

    A strong framework for utilizing Multiple datasets to pretrain DETR-like detectors without the need for manual label spaces integration.

    dise Simple Parameter-free Self-attention Approximation
    YuwenZhai*, Jing Hao*, Liang Gao, Xinyu Li, Yiping Gao, Shumin Han
    [paper]
    ICLR Tiny Paper, 2023

    A self-attention approximation without training parameters which captures global spatial features with linear complexity.

    dise A Stronger Stitching Algorithm for Fisheye Images based on Deblurring and Registration
    Jing Hao, Jingming Xie, Jinyuan Zhang, Moyun Liu
    [paper]
    IEEE Sensors Letters, 2023

    A stronger stitching algorithm for fisheye images by combining the traditional image processing method with deep learning.

    dise A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images
    Moyun Liu, Jingming Xie, Jing Hao, Yang Zhang, Xuzhan Chen, Youping Chen
    [paper]
    Computers in Industry, 2022, (JCR Q1, IF=8.2)

    A signs recognition framework based on convolutional neural networks (CNNs) for weld images.

    Competition

  • The 6th place in ToothFairy2 : Semi-supervised Teeth Segmentation hold on MICCAI2024
  • Certificate

    Services

  • Reviewer for IEEE Transactions on Circuits and Systems for Video Technology
  • Reviewer for IEEE Signal Processing Letters
  • Reviewer for Applied Intelligence
  • Education & Experience

    dise The University of Hong Kong (HKU)
    2024.09 - now
    Ph.D Student, Faculty of Dentistry (Ranking 3rd in the world)
    Clinical Artificial Intelligence
    dise Baidu VIS
    2022.07 - 2024.08
    Computer Vision Engineer
    dise Huazhong University of Science and Technology (HUST)
    2020.09 - 2022.06
    Master Student, School of Mechanical Science and Engineering
    dise China University of Mining and Technology (CUMT)
    2016.09 - 2020.06
    Undergraduate Student, School of Mechanical and Electrical Engineering

    Selected Awards & Honors

  • National Scholarship (2018)
  • First-class Scholarship in HUST (2021)
  • First-class Scholarship in CUMT (2019)
  • Second-class Scholarship in CUMT (2017)
  • Outstanding student in CUMT (2018)
  • Excellent Student Leader in Jiangsu Province (2019)
  • Excellent Young Volunteer in Xuzhou City (2019)