PeopleofSuperintelligence

Researcher

Gül Varol

Gül Varol is a computer vision researcher whose work covers video understanding, 3D human motion and sign languages. She completed a PhD in the WILLOW team of Inria Paris and École Normale Supérieure in 2019, with work that included long-term temporal convolutions for action recognition in 2016 and the SURREAL dataset of synthetic humans in 2017. As a postdoc at Oxford she worked with Andrew Zisserman, and she co-authored the BOBSL British Sign Language dataset in 2021 and the TEMOS text-to-motion model in 2022. She served as a Program Chair of ECCV 2024 and received the ECVA Young Researcher Award 2025 in September 2026. She is a computer vision researcher in the IMAGINE group at École des Ponts ParisTech, a Hi!Paris Fellow and an ELLIS Scholar.

Timeline

  1. 2015–2019

    PhD in the WILLOW team

    After BS and MS degrees at Boğaziçi University, she joins the WILLOW project team of Inria Paris and École Normale Supérieure in May 2015. Co-advised by Ivan Laptev and Cordelia Schmid, she defends her PhD thesis in May 2019.

  2. 2016–2017

    Long-term convolutions and SURREAL

    In 2016, she posts a paper with Ivan Laptev and Cordelia Schmid on long-term temporal convolutions (LTC), video networks whose longer temporal extent improves the accuracy of action recognition. In 2017, she is first author of the CVPR paper "Learning from Synthetic Humans", which introduces SURREAL, a dataset of more than 6 million synthetic frames of people with ground-truth pose, depth maps and segmentation masks.

  3. 2019–2020

    Oxford postdoc and thesis awards

    In September 2019, she joins VGG at the University of Oxford as a postdoctoral researcher working with Andrew Zisserman, and announces that she will join the IMAGINE team at École des Ponts ParisTech in fall 2020. Her thesis receives the AFRIF 2019 PhD thesis award and the ELLIS 2020 PhD Award.

  4. 2021

    The BOBSL sign language dataset

    In 2021, she coauthors the BBC-Oxford British Sign Language dataset (BOBSL) with Samuel Albanie, Andrew Zisserman and colleagues, a large-scale video collection of British Sign Language with baselines for sign recognition, alignment and translation. The team makes the dataset public in November 2021.

  5. 2022

    TEMOS text-to-motion model

    In 2022, she coauthors TEMOS with Mathis Petrovich and Michael J. Black, a text-conditioned generative model that uses variational autoencoder training to produce diverse 3D human motions from textual descriptions. The paper appears at ECCV 2022.

  6. 2024

    Program Chair of ECCV 2024

    In 2024, she serves as one of the six Program Chairs of ECCV 2024, together with Aleš Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky and Torsten Sattler. She defends her habilitation thesis in November 2024.

  7. September 2026

    ECVA Young Researcher Award

    In September 2026, she receives the ECVA Young Researcher Award 2025.

  8. As of October 2026

    Researcher in the IMAGINE group

    She is a computer vision researcher in the IMAGINE group at École Nationale des Ponts et Chaussées (ENPC), part of Institut Polytechnique de Paris, a Hi!Paris Fellow and an ELLIS Scholar. Her research interests cover vision and language applications, including video understanding, 3D human motions and sign languages.

Career

  1. NowÉcole des Ponts ParisTechComputer Vision Researcher
  2. 2019–2020University of OxfordPostdoctoral Researcher

Education

  1. 2019InriaPhD
  2. 2019École Normale SupérieurePhD
  3. Boğaziçi UniversityBS

From the biography.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes École des Ponts ParisTech. 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 École des Ponts ParisTech. 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 École des Ponts ParisTech. 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 École des Ponts ParisTech. 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 Gül Varol yet. Send us a free-licensed photo.

  1. Gül Varol gulvarol.github.io. Checked 21 October 2026.
  2. Long-term Temporal Convolutions for Action Recognition arxiv.org. Checked 21 October 2026.
  3. Learning from Synthetic Humans di.ens.fr. Checked 21 October 2026.
  4. BBC-Oxford British Sign Language Dataset arxiv.org. Checked 21 October 2026.
  5. TEMOS: Generating diverse human motions from textual descriptions arxiv.org. Checked 21 October 2026.
  6. ECCV 2024 Organizers eccv2024.ecva.net. Checked 21 October 2026.
  7. Gül Varol | European Laboratory for Learning and Intelligent Systems ellis.eu. Checked 21 October 2026.