PeopleofSuperintelligence

Researcher

Guanbin Li

Also known as Li Guanbin, 李冠彬

Guanbin Li is a computer-vision researcher at Sun Yat-sen University whose work spans visual saliency, video analysis, neural radiance fields and vision-language navigation. He earned bachelor's and master's degrees at Sun Yat-sen, completed a computer science PhD at the University of Hong Kong in 2016 under Yizhou Yu, and developed deep image-saliency models with Yu in 2015 and 2016. A 2018 paper he coauthored used a flow-guided encoder for video; later work addressed domain adaptation and neural radiance fields for non-static scenes. He coauthored a 2025 CVPR paper on long-horizon vision-language navigation and DreamShot, a 2026 video-diffusion framework for controllable multi-shot storyboard synthesis. Since April 2026, he has been a professor and vice dean at Sun Yat-sen University's School of Computer Science and Engineering, with research interests in computer vision, machine learning and medical image analysis.

Works
358
Citations
16,866
h-index
64
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. By 2016

    Degrees at two universities

    By 2012, he earns bachelor's and master's degrees in computer science and technology at Sun Yat-sen University. He completes a computer science PhD at the University of Hong Kong in 2016 under adviser Yizhou Yu.

  2. 2015–2016

    Deep models for visual saliency

    With Yizhou Yu, he introduces a visual-saliency model based on multiscale deep CNN features in 2015. Their 2016 deep contrast network detects salient objects with pixel-level and segment-wise streams.

  3. 2018

    Flow-guided video saliency

    He and his coauthors present a flow-guided recurrent neural encoder for video salient-object detection in 2018. The model combines optical-flow motion information with sequential feature evolution encoded in LSTM networks.

  4. 2019

    Research associate professor and domain adaptation

    He is a research associate professor in Sun Yat-sen University's School of Data and Computer Science in 2019. With his coauthors, he presents Larger Norm More Transferable at ICCV 2019, a parameter-free adaptive feature-norm approach to unsupervised domain adaptation.

  5. 2024

    Professorship and NeRF-HuGS

    He becomes a professor at Sun Yat-sen University's School of Computer Science and Engineering in May 2024. At CVPR 2024, he coauthors NeRF-HuGS, which combines hand-crafted heuristics with segmentation models to separate static scenes from transient distractors such as moving objects and shadows. The paper is an oral presentation and a Best Paper Candidate.

  6. 2025

    Long-horizon vision-language navigation

    He coauthors a CVPR 2025 paper that introduces Long-Horizon Vision-Language Navigation, a task for long-term planning and consistent decisions across consecutive subtasks.

  7. 2026

    Controllable storyboards with DreamShot

    In 2026, he coauthors DreamShot, a video-generative storyboard framework that uses video-diffusion priors to synthesize controllable multi-shot sequences.

  8. Since April 2026

    Professor and vice dean

    In April 2026, he becomes vice dean at Sun Yat-sen University's School of Computer Science and Engineering. He is a professor there, and his current research interests include computer vision, machine learning and medical image analysis.

Career

  1. Since 2019Sun Yat-sen UniversityResearch Associate Professor, Professor
  2. 2024–2026Peng Cheng Laboratory
  3. 2023–2025Guangdong Province Key Laboratory of Information Security Technology
  4. 2021–2025Shenzhen Research Institute of Big Data
  5. 2021–2025Chinese University of Hong Kong, Shenzhen

Education

  1. 2016University of Hong KongPhD
  2. Sun Yat-sen UniversityBachelor's and master's degrees

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

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Sun Yat-sen University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Sun Yat-sen University. 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.
  3. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Sun Yat-sen 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.
  4. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Sun Yat-sen University. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

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

  1. Guanbin Li (李冠彬) guanbinli.com. Checked 22 October 2026.
  2. VISAPP 2019 - EventChairs visapp.scitevents.org. Checked 22 October 2026.
  3. Visual Saliency Based on Multiscale Deep Features openaccess.thecvf.com. Checked 22 October 2026.
  4. Deep Contrast Learning for Salient Object Detection openaccess.thecvf.com. Checked 22 October 2026.
  5. Flow Guided Recurrent Neural Encoder for Video Salient Object Detection openaccess.thecvf.com. Checked 22 October 2026.
  6. Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation openaccess.thecvf.com. Checked 22 October 2026.
  7. 李冠彬 | 中山大学计算机学院 cse.sysu.edu.cn. Checked 22 October 2026.
  8. NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation openaccess.thecvf.com. Checked 22 October 2026.
  9. NeRF-HuGS - CVPR 2024 Oral sysu-hcp.net. Checked 22 October 2026.
  10. Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method openaccess.thecvf.com. Checked 22 October 2026.
  11. DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior arxiv.org. Checked 22 October 2026.
  12. 专家评委库 - 琶洲算法大赛 aicompetition-pz.com. Checked 22 October 2026.