PeopleofSuperintelligence

Researcher

Yoichi Sato

Yoichi Sato is a computer vision researcher whose work links human activity, gaze sensing and first-person video. He studied engineering at the University of Tokyo and robotics at Carnegie Mellon before becoming a professor at the Institute of Industrial Science in 2010. His work includes a 2018 model for predicting gaze from headcam footage and Ego4D, a large-scale dataset and benchmark suite for first-person perception. He co-chaired CVPR 2023, became an IAPR Fellow in 2024, and his lab started BioSkillDX in 2025 to develop AI for life-science experiments. As of October 2026, he is a professor at the Institute of Industrial Science at the University of Tokyo.

Works
469
Citations
13,444
h-index
63
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 1990–1997

    A robotics PhD at Carnegie Mellon

    He earns a B.S. degree from the University of Tokyo in 1990, then M.S. and PhD degrees in robotics from Carnegie Mellon University's School of Computer Science in 1993 and 1997.

  2. 2010

    Professor at the Institute

    He becomes a professor at the Institute of Industrial Science at the University of Tokyo in 2010.

  3. 2018

    Predicting gaze from headcam video

    In 2018, he coauthors an ECCV paper that learns from headcam footage to predict where a user will look next. Its model combines a visual saliency map with an attention map based on earlier gaze and head movement.

  4. 2022

    Ego4D for first-person vision

    He coauthors Ego4D, a CVPR 2022 dataset and benchmark suite for first-person visual perception. It includes 3,670 hours of daily-life video from 931 participants across 74 locations and nine countries.

  5. 2023

    General co-chair of CVPR

    He serves as General Co-Chair of CVPR 2023.

  6. 2024

    An IAPR fellowship

    He becomes an IAPR Fellow in 2024 for contributions to computer vision and service to IAPR.

  7. August 2025–July 2030

    AI for life-science experiments

    In August 2025, his lab begins BioSkillDX, a K Program project to develop AI technologies for acquiring tacit knowledge in life-science research and to build a dataset of experimental procedures.

  8. As of October 2026

    Professor at the University of Tokyo

    As of October 2026, he is a professor at the Institute of Industrial Science at the University of Tokyo. His research covers human behavior understanding, egocentric vision, gaze sensing and physics-based vision.

Career

  1. Since 2010University of TokyoProfessor
  2. 2008–2010Japan Aerospace Exploration Agency
  3. 2002–2004Nagoya Institute of Technology
  4. 1993–1996Carnegie Mellon University

Education

  1. 1990University of TokyoB.S.

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

  1. People shaping AI work at a median of 3 organizations over a career: 3 for university starters and institute and lab starters, versus 2 for company startersIncludes University of Tokyo. Across 6,853 people shaping AI with a dated work role, we estimate a median of 3 parent organizations over a career (mean 3.6), comparing role groups, starting sectors and starting decades from the 1950s to 2020–2026.
  2. Universities keep AI researchers for a median of 6 years, compared with 2 years at frontier labsIncludes University of Tokyo. Across 15,811 dated work stays (6,529 people), median role tenure runs from 6 years at universities to 2 years at frontier labs. We compare all five organization types, starting decades from the 1970s to the 2020s, and the organizations that keep people longest.
  3. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University of Tokyo. 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.
  4. The United States employs an estimated 48% of people shaping AIIncludes University of Tokyo. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.

Colleagues

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

Sources and credits

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

  1. Yoichi Sato sites.google.com. Checked 20 October 2026.
  2. Snapshots of the Future: Tool Learns to Predict User's Gaze in Headcam Footage - Institute of Industrial Science, the University of Tokyo iis.u-tokyo.ac.jp. Checked 20 October 2026.
  3. Ego4D: Around the World in 3,000 Hours of Egocentric Video openaccess.thecvf.com. Checked 20 October 2026.
  4. Alphabetical List of IAPR Fellows – International Association for Pattern Recognition iapr.org. Checked 20 October 2026.
  5. Y. Sato Laboratory | Sato Lab./Sugano Lab. ut-vision.org. Checked 20 October 2026.
  6. SATO Yoichi Professor - Institute of Industrial Science, the University of Tokyo iis.u-tokyo.ac.jp. Checked 20 October 2026.