PeopleofSuperintelligence

Researcher

Heng Fan

Heng Fan is a computer vision researcher at the University of North Texas whose work centers on visual object tracking and the benchmarks used to measure it. With his doctoral advisor Haibin Ling, he built the PTAV and C-RPN trackers and in 2018 released LaSOT, a densely annotated benchmark of 1,400 video sequences and more than 3.5 million frames. After completing a computer science PhD at Stony Brook University in 2021, he coauthored SwinTrack, a fully attentional Transformer tracker, and later the VastTrack and GSOT3D benchmarks for broad-category and 3D tracking. Today he is an assistant professor in UNT's Department of Computer Science and Engineering, and his team won first place in both 2D and 3D tracking at the MICCAI 2026 STIR Challenge in September 2026.

Timeline

  1. 2013–2015

    Studies at Huazhong Agricultural University

    He earns a B.S. in computer science and technology from Huazhong Agricultural University in 2013. In 2015, he and Jinhai Xiang of the university's College of Informatics publish "Robust tracking based on local structural cell graph" in the Journal of Visual Communication and Image Representation.

  2. 2017

    Parallel tracking and verifying

    In 2017, he and Haibin Ling present PTAV, a tracking framework that runs a fast tracker and a verifier on two separate threads, borrowing from parallel tracking and mapping in visual SLAM. The verifier checks results only when the tracker asks and corrects it when needed.

  3. 2018

    The LaSOT tracking benchmark

    In 2018, he is first author of LaSOT, a single-object tracking benchmark of 1,400 manually annotated video sequences with more than 3.5 million frames, enriched with natural-language descriptions of the targets. In December 2018, he and Ling propose Siamese Cascaded RPN (C-RPN), which cascades region proposal networks from deep to shallow layers of a Siamese network.

  4. 2021

    A PhD at Stony Brook

    He completes a Ph.D. in computer science at Stony Brook University in 2021, advised by Haibin Ling, and moves to the University of North Texas.

  5. December 2021

    SwinTrack, a Transformer tracker

    In December 2021, he coauthors SwinTrack with Liting Lin, Zhipeng Zhang, Yong Xu and Haibin Ling, a fully attentional tracker that uses the Transformer architecture for both representation learning and feature fusion. On LaSOT, SwinTrack sets a new record with a 0.713 SUC score.

  6. 2021–2023

    A top 2% scientists listing

    From 2021 to 2023, he appears on the Stanford University and Elsevier list of the world's top 2% scientists.

  7. 2024

    VastTrack and GSOT3D benchmarks

    In March 2024, he coauthors VastTrack, a benchmark of 50,610 sequences and 4.2 million frames covering target objects from 2,115 classes. GSOT3D follows in December 2024, with 620 sequences, 123K frames and 54 object categories for generic 3D single object tracking on point clouds, RGB images and depth.

  8. As of October 2026

    Assistant professor at UNT

    He is an assistant professor in the Department of Computer Science and Engineering at the University of North Texas and affiliated faculty in its Department of Data Science. His algorithms and large-scale data platforms for visual understanding serve autonomous vehicles, visual surveillance, medical imaging analysis and robotics. In September 2026, his team wins first place in both 2D and 3D tracking at the MICCAI 2026 STIR Challenge.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

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 Heng Fan yet. Send us a free-licensed photo.

  1. Homepage for Heng Fan hengfan2010.github.io. Checked 19 October 2026.
  2. Jinhai Xiang--Home-- Heng Fan, Jinhai Xiang*, Honghong Liao, etc. Robust tracking based on local structural cell graph faculty.hzau.edu.cn. Checked 19 October 2026.
  3. [1708.00153] Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking arxiv.org. Checked 19 October 2026.
  4. [1809.07845] LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking arxiv.org. Checked 19 October 2026.
  5. [1812.06148] Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking arxiv.org. Checked 19 October 2026.
  6. Ling Group haibinling.github.io. Checked 19 October 2026.
  7. [2112.00995] SwinTrack: A Simple and Strong Baseline for Transformer Tracking arxiv.org. Checked 19 October 2026.
  8. Faculty | University of North Texas ci.unt.edu. Checked 19 October 2026.
  9. [2403.03493] VastTrack: Vast Category Visual Object Tracking arxiv.org. Checked 19 October 2026.
  10. [2412.02129] GSOT3D: Towards Generic 3D Single Object Tracking in the Wild arxiv.org. Checked 19 October 2026.