PeopleofSuperintelligence

Researcher

Gui-Song Xia

Also known as G.-S. Xia, Guisong Xia, Gui-song Xia, Gui‐Song Xia, Xia Gui-Song, 夏桂松

Gui-Song Xia is a computer-vision researcher at Wuhan University whose work applies machine learning to aerial scene classification and object detection. He earned bachelor's and master's degrees at Wuhan University and completed a computer-vision PhD at Télécom Paris in 2011. He coauthored AID, DOTA, the RoI Transformer and ReDet for aerial image understanding and detection. In March 2026, he coauthored a physics-driven deep-learning paper for matching fragments of ancient bamboo slips. Since December 2024, he serves as executive dean of Wuhan University's School of Artificial Intelligence and as deputy director of the National Engineering Research Center for Multimedia Software, a role he has held since December 2020.

Born
1983
Works
439

Years link to their sources. Publication numbers from OpenAlex, as of 22 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2005–2007

    Wuhan University degrees

    He earns a bachelor's degree in electronic and information engineering at Wuhan University in 2005 and a master's degree in signal and information processing there in 2007.

  2. 2011

    A computer-vision PhD

    He completes a PhD in computer vision at Télécom Paris in 2011.

  3. 2012–2019

    Research at Wuhan's state lab

    From November 2012 to October 2019, he works at Wuhan University's State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing.

  4. 2016–2017

    AID for aerial scenes

    In August 2016, he coauthors AID, a large-scale dataset for aerial scene classification with more than 10,000 images. IEEE Transactions on Geoscience and Remote Sensing publishes the paper in July 2017.

  5. 2018–2019

    DOTA and the RoI Transformer

    In 2018, he coauthors DOTA, a large-scale aerial object-detection dataset with 2,806 images. In 2019, he coauthors the RoI Transformer, which learns spatial transformations from oriented bounding-box annotations for aerial object detection.

  6. 2021

    ReDet and event-based SAI

    In 2021, he coauthors ReDet, which encodes rotation equivariance and rotation invariance for aerial object detection. Also in 2021, he coauthors Event-Based Synthetic Aperture Imaging With a Hybrid Network, a CVPR oral paper selected as a Best Paper Candidate.

  7. March 2026

    Physics-driven bamboo-slip rejoining

    In March 2026, he coauthors Rejoining fragmented ancient bamboo slips with physics-driven deep learning. The paper introduces WisePanda, a physics-driven framework that generates synthetic training pairs for matching fragments.

  8. Since December 2024

    Executive dean at Wuhan

    Since December 2020, he serves as deputy director of Wuhan University's National Engineering Research Center for Multimedia Software. Since December 2024, he serves as executive dean of Wuhan University's School of Artificial Intelligence.

Career

  1. Since 2012Wuhan UniversityComputer Vision Researcher, Executive Dean

Education

  1. 2011Télécom ParisPhD
  2. 2007Wuhan UniversityMaster’s degree
  3. 2005Wuhan UniversityBachelor’s degree

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Wuhan 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.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Wuhan 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.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Wuhan 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.
  4. 5 of the 25 people with the most-cited recent papers also lead on career citationsIncludes Wuhan University. 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.

Colleagues

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

Sources and credits

Photo: We have no published photo of Gui-Song Xia yet. Send us a free-licensed photo.

  1. Wuhan University Xia Gui-Song--Home--Home jszy.whu.edu.cn. Checked 22 October 2026.
  2. Wuhan University Xia Gui-Song--Home--Home jszy.whu.edu.cn. Checked 22 October 2026.
  3. [1608.05167] AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification arxiv.org. Checked 22 October 2026.
  4. CVPR 2018 Open Access Repository openaccess.thecvf.com. Checked 22 October 2026.
  5. CVPR 2019 Open Access Repository openaccess.thecvf.com. Checked 22 October 2026.
  6. CVPR 2021 Open Access Repository openaccess.thecvf.com. Checked 22 October 2026.
  7. DVS-Group | E-SAI dvs-whu.cn. Checked 22 October 2026.
  8. Rejoining fragmented ancient bamboo slips with physics-driven deep learning | Nature Communications nature.com. Checked 22 October 2026.