PeopleofSuperintelligence

Researcher

Bineng Zhong

Also known as 钟必能

Bineng Zhong is a computer-vision researcher whose work spans image super-resolution and visual object tracking. He earned bachelor’s, master’s and doctoral degrees in computer science at Harbin Institute of Technology in 2004, 2006 and 2010, and worked as a research fellow at two Chinese Academy of Sciences institutes in 2007–2008. He served as a professor at Huaqiao University from 2010 to 2020 and visited Northeastern University from September 2017 to September 2018. His papers include the 2018 Residual Dense Network, a 2021 Siamese relation network, ODTrack in 2024, SGLATrack in 2025 and ETCTrack in 2026. As of October 2026, he is a professor at Guangxi Normal University’s School of Computer Science and Engineering.

Now at
Guangxi Normal University
Badges

Timeline

  1. 2004–2010

    Degrees and research fellowship

    He earns bachelor’s, master’s and doctoral degrees in computer science at Harbin Institute of Technology in 2004, 2006 and 2010. From 2007 to 2008, he works as a research fellow at the Institute of Automation and Institute of Computing Technology, Chinese Academy of Sciences.

  2. 2010–2020

    Professor at Huaqiao University

    He serves as a professor in Huaqiao University’s School of Computer Science and Technology from 2010 to 2020.

  3. September 2017–September 2018

    Visiting scholar at Northeastern

    He is a visiting scholar at Northeastern University in Boston from September 2017 to September 2018.

  4. 2018

    Residual Dense Network

    At CVPR in 2018, he coauthors “Residual Dense Network for Image Super-Resolution” with Yulun Zhang, Yapeng Tian, Yu Kong and Yun Fu. The network uses dense feature fusion to combine local and global features for super-resolution.

  5. 2021

    A Siamese tracking network

    At CVPR in 2021, he coauthors “Learning To Filter: Siamese Relation Network for Robust Tracking.” Its Relation Detector learns to filter distractors from the background, and its Refinement Module integrates the detector into a Siamese framework for accurate tracking.

  6. 2024

    ODTrack for video tracking

    In 2024, he coauthors ODTrack, a video-level tracking pipeline that connects frames through online token propagation. The system compresses a target’s localization features into a token sequence for frame-to-frame association.

  7. 2025–2026

    SGLATrack and ETCTrack

    At CVPR in 2025, he coauthors “Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking.” SGLATrack disables representation-similar layers and retains one optimal layer for real-time UAV tracking. At CVPR in 2026, he coauthors “An Efficient Token Compression Framework for Visual Object Tracking”; ETCTrack compresses historical template tokens. The ETCTrack-B224 version uses 60% fewer template tokens and 21.4% fewer MACs, with a 0.4% drop in accuracy.

  8. As of October 2026

    Professor at Guangxi Normal

    He is a professor in the School of Computer Science and Engineering at Guangxi Normal University. His research interests include pattern recognition, machine learning and computer vision.

Career

  1. NowGuangxi Normal UniversityProfessor
  2. 2017–2018Northeastern UniversityVisiting scholar
  3. 2010–2020Huaqiao UniversityProfessor
  4. 2007–2008Chinese Academy of SciencesResearch fellow

Education

  1. 2010Harbin Institute of TechnologyDoctoral degree
  2. 2006Harbin Institute of TechnologyMaster's degree
  3. 2004Harbin Institute of TechnologyBachelor's degree

From the biography.

  1. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes Bineng Zhong. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.
  2. 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.
  3. 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.
  4. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Northeastern University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.

Colleagues

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

Sources and credits

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

  1. 2026 4th International Conference on Internet of Things and Cloud Computing Technology (IoTCCT 2026) iotcct.org. Checked 20 October 2026.
  2. CVPR 2018 Open Access Repository openaccess.thecvf.com. Checked 20 October 2026.
  3. CVPR 2021 Open Access Repository openaccess.thecvf.com. Checked 20 October 2026.
  4. ODTrack: Online Dense Temporal Token Learning for Visual Tracking | Proceedings of the AAAI Conference on Artificial Intelligence ojs.aaai.org. Checked 20 October 2026.
  5. CVPR 2025 Open Access Repository openaccess.thecvf.com. Checked 20 October 2026.
  6. CVPR 2026 Open Access Repository openaccess.thecvf.com. Checked 20 October 2026.