PeopleofSuperintelligence

Researcher

Lianwen Jin

Also known as 金连文

Lianwen Jin is a professor at South China University of Technology whose research connects scene text recognition with multimodal AI for historical documents. He earned a B.S. from the University of Science and Technology of China in 1991 and a Ph.D. from SCUT in 1996, then coauthored ABCNet in 2020 and OCRBench in 2023. He became an IAPR Fellow in 2024 and coauthored DocLayLLM in 2025 and HisDoc-OCR in 2026. As of October 2026, he is a professor at SCUT and serves as president of the Guangdong Image and Graphics Association.

Now at
South China University of Technology and Guangdong Image and Graphics Association
Works
478
Citations
15,109
h-index
65
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 1991–1996

    Degrees from USTC and SCUT

    He earns a B.S. from the University of Science and Technology of China in 1991 and a Ph.D. from South China University of Technology in 1996.

  2. 2014–2024

    IEEE and CSIG committee chairs

    He chairs the IEEE SPS Guangzhou Chapter from 2014 to 2016 and the Chinese Society of Image and Graphics’ Technical Committee on Document Analysis and Recognition from 2017 to 2024.

  3. 2020

    ABCNet text spotting

    In 2020, he coauthors ABCNet, a real-time network that spots arbitrarily shaped scene text with parameterized Bezier curves. On Total-Text, ABCNet runs over ten times faster than recent state-of-the-art methods with competitive recognition accuracy.

  4. 2023

    OCRBench for multimodal models

    In 2023, he coauthors OCRBench, a benchmark for evaluating OCR in large multimodal models. It covers 29 datasets and includes scene-text and document question answering, key information extraction, text recognition and handwritten math recognition.

  5. 2024

    An IAPR Fellowship

    In 2024, he becomes an IAPR Fellow for contributions to document image analysis and recognition, particularly scene-text detection and recognition.

  6. 2025–2026

    DocLayLLM and HisDoc-OCR

    At AIPT in May 2025, he hosts the opening ceremony at South China University of Technology. In 2025, he coauthors DocLayLLM, a multimodal extension of large language models for text-rich document understanding. In 2026, he coauthors HisDoc-OCR, which restores visual grounding for Chinese historical-document OCR.

  7. As of October 2026

    Professor and lab director

    As of October 2026, he is a professor at the College of Electronic and Information Engineering at South China University of Technology.

  8. As of October 2026

    President of Guangdong association

    As of October 2026, he serves as president of the Guangdong Image and Graphics Association.

Career

  1. Since 1998South China University of TechnologyProfessor
  2. NowGuangdong Image and Graphics AssociationPresident
  3. 2017–2024China Society of Image and GraphicsChair

Education

  1. 1996South China University of TechnologyPh.D.
  2. 1991University of Science and Technology of ChinaB.S.

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

Most-cited works

  1. MORAN: A Multi-Object Rectified Attention Network for scene text recognition2019 · Pattern Recognition · 510 citations
  2. ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network2020 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 466 citationsWith Chunhua Shen
  3. Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection2017 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 359 citations
  4. Fourier Contour Embedding for Arbitrary-Shaped Text Detection2021 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 321 citations
  5. Curved scene text detection via transverse and longitudinal sequence connection2019 · Pattern Recognition · 318 citations

From OpenAlex, as of 21 October 2026.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes South China University of Technology. 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 South China University of Technology. 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. 5 of the 25 people with the most-cited recent papers also lead on career citationsIncludes South China University of Technology. We compare citations to 2023–2025 papers with career citations and h-index, after correcting reviewed publication-date errors: who leads, when they started and where they work.
  4. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes South China University of Technology. 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 with dated positions at the same organization in the same years.

Sources and credits

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

  1. Lianwen Jin - Professor, South China University of Technology dlvc-lab.net. Checked 20 October 2026.
  2. ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network arxiv.org. Checked 20 October 2026.
  3. OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models arxiv.org. Checked 20 October 2026.
  4. Chronological List of IAPR Fellows – International Association for Pattern Recognition iapr.org. Checked 20 October 2026.
  5. 2026 3rd International Conference on Advanced Image Processing Technology (AIPT 2026) icaipt.org. Checked 20 October 2026.
  6. HisDoc-OCR: Restoring Visual Grounding in MLLMs for Chinese Historical Document OCR - ACL Anthology aclanthology.org. Checked 20 October 2026.