PeopleofSuperintelligence

Researcher

Qingming Huang

Also known as 黄庆明

Qingming Huang is a computer vision researcher whose work includes the CenterNet object detector and 2025 research on self-supervised video learning and provable robustness. He earned computer science and computer engineering degrees at Harbin Institute of Technology, held research and engineering posts in Singapore, and joined the University of Chinese Academy of Sciences as a professor in 2003. The National Science Fund for Distinguished Young Scholars of China supported him in 2010, and he received the State Council's Special Government Allowance in 2011. He served as a vice dean at the University of Chinese Academy of Sciences in 2015. As of October 2026, he is a Chair Professor at the University of Chinese Academy of Sciences and an adjunct research professor at the Institute of Computing Technology, Chinese Academy of Sciences.

Works
888
Citations
34,814
h-index
83
Rankings
#92 by cited papers
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 1984–1994

    Computer science at Harbin

    He earns a B.S. in computer science in 1988 and a Ph.D. in computer engineering in 1994 at Harbin Institute of Technology.

  2. 1994–2003

    Research and engineering in Singapore

    From 1994 to 1995, he lectures at Harbin Institute of Technology, then holds a postdoctoral fellowship at the National University of Singapore from 1995 to 1996. He joins Singapore's Institute for Infocomm Research in November 1996, serves as a member of research staff through May 2002, and becomes a principal engineer at Vislog Technology Pte Ltd from June 2002 to May 2003.

  3. Since 2003

    Professor at UCAS

    He joins the University of Chinese Academy of Sciences as a professor in May 2003.

  4. 2010

    A Young Scholars grant

    The National Science Fund for Distinguished Young Scholars of China supports his work in 2010.

  5. 2011

    State Council allowance

    He receives the Special Government Allowance of the State Council in 2011.

  6. 2015

    Vice dean at UCAS

    In October 2015, he serves as a vice dean at the University of Chinese Academy of Sciences.

  7. 2019–2025

    CenterNet, T-CoRe and AUCPro

    In 2019, he coauthors CenterNet: Keypoint Triplets for Object Detection, whose method represents each object as a keypoint triplet and improves precision and recall. At CVPR 2025, he coauthors When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning, which proposes T-CoRe for self-supervised video representation. In June 2025, he coauthors AUCPro: AUC-Oriented Provable Robustness Learning, published in IEEE Transactions on Pattern Analysis and Machine Intelligence.

  8. As of October 2026

    Chair Professor at UCAS

    As of October 2026, he is Chair Professor in the School of Computer Science and Technology at the University of Chinese Academy of Sciences and an adjunct research professor at the Institute of Computing Technology, Chinese Academy of Sciences. His research covers multimedia computing, image/video processing, pattern recognition, and computer vision.

Career

  1. Since 2004Chinese Academy of SciencesAdjunct research professor
  2. Since 2003University of Chinese Academy of SciencesProfessor, Vice dean
  3. 2024–2026Jiangxi Normal University
  4. 2022–2025Harbin Engineering University
  5. 2019–2026Peng Cheng Laboratory
  6. 2012–2015Beijing University of Technology
  7. 2002–2003Vislog Technology Pte LtdPrincipal engineer
  8. 1996–2002Science and Engineering Research CouncilMember of research staff
  9. 1995–1996National University of SingaporePostdoctoral fellow
  10. 1994–1995Harbin Institute of TechnologyLecturer

Education

  1. 1994Harbin Institute of TechnologyPh.D.
  2. 1988Harbin Institute of TechnologyB.S.

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. CenterNet: Keypoint Triplets for Object Detection2019 · IEEE/CVF International Conference on Computer Vision (ICCV) · 4,066 citationsWith Qi Tian
  2. Cascaded Partial Decoder for Fast and Accurate Salient Object Detection2019 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 1,209 citations
  3. F³Net: Fusion, Feedback and Focus for Salient Object Detection2020 · Proceedings of the AAAI Conference on Artificial Intelligence · 1,136 citations
  4. The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking2018 · Lecture notes in computer science · 1,083 citationsWith Qi Tian
  5. Hedged Deep Tracking2016 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 734 citationsWith Jongwoo Lim and Ming-Hsuan Yang

From OpenAlex, as of 21 October 2026.

  1. Universities keep AI researchers for a median of 6 years, compared with 2 years at frontier labsIncludes Chinese Academy of Sciences. Across 15,811 dated work stays (6,529 people), median role tenure runs from 6 years at universities to 2 years at frontier labs. We compare all five organization types, starting decades from the 1970s to the 2020s, and the organizations that keep people longest.
  2. People shaping AI work at a median of 3 organizations over a career: 3 for university starters and institute and lab starters, versus 2 for company startersIncludes Chinese Academy of Sciences. Across 6,853 people shaping AI with a dated work role, we estimate a median of 3 parent organizations over a career (mean 3.6), comparing role groups, starting sectors and starting decades from the 1950s to 2020–2026.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Chinese Academy of Sciences. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes Chinese Academy of Sciences. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Qingming Huang yet. Send us a free-licensed photo.

  1. 黄庆明-中国科学院大学-UCAS people.ucas.edu.cn. Checked 20 October 2026.
  2. Qiming Huang----Visual Information Processing and Learning (VIPL) vipl.ict.ac.cn. Checked 20 October 2026.
  3. Qingming Huang scce.ucas.ac.cn. Checked 20 October 2026.
  4. [1904.08189] CenterNet: Keypoint Triplets for Object Detection arxiv.org. Checked 20 October 2026.
  5. CVPR 2025 Open Access Repository openaccess.thecvf.com. Checked 20 October 2026.
  6. Publications | Qianqian Xu qianqianxu010.github.io. Checked 20 October 2026.