PeopleofSuperintelligence

Researcher

Du Tran

Du Tran is a computer vision researcher whose work builds AI methods for understanding video. He completed a BSc in information technology at Ho Chi Minh City University of Science, an MSc in computer science at the University of Illinois at Urbana-Champaign, and a PhD in computer science at Dartmouth in 2016; he joined Facebook in 2016. His papers introduced C3D and R(2+1)D, and later work covered efficient video classification, multimodal training, open-world segmentation, and long-video representation. He was a Research Scientist at Google in 2024; as of October 2026, he is a Staff Research Scientist and Tech Lead there.

Now at
Google
Works
62
Citations
18,179
h-index
28
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2014

    C3D for video features

    In 2014, he coauthors a paper that introduces C3D, a 3D convolutional network for learning spatiotemporal video features. Its learned features outperform state-of-the-art methods on four benchmarks.

  2. 2016

    Dartmouth PhD and Facebook

    He completes a computer science PhD at Dartmouth and joins Facebook in 2016. His other degrees are an MSc in computer science from the University of Illinois at Urbana-Champaign and a BSc in information technology from Ho Chi Minh City University of Science.

  3. 2018

    R(2+1)D for action recognition

    At CVPR in 2018, he coauthors A Closer Look at Spatiotemporal Convolutions for Action Recognition and introduces the R(2+1)D block, which factorizes 3D filters into spatial and temporal operations.

  4. 2019

    Channel-separated nets and Gradient Blending

    In 2019, he coauthors Channel-Separated Convolutional Networks, which reduces computation in video classification by separating channel and spatiotemporal interactions. Also in 2019, he coauthors a multimodal training study that introduces Gradient Blending to balance modalities with different overfitting rates.

  5. 2021

    UVO open-world benchmark

    In 2021, he coauthors UVO, a benchmark for open-world, class-agnostic object segmentation in videos.

  6. 2024

    Research scientist at Google

    In 2024, he is a Research Scientist at Google, working on computer vision and machine learning.

  7. 2025

    SEAL for long videos

    In 2025, he coauthors SEAL, a long-video representation that decomposes videos into scene, object, and action tokens and balances token relevance with diversity.

  8. As of October 2026

    Staff research scientist at Google

    As of October 2026, he is a Staff Research Scientist and Tech Lead at Google. His earlier roles include Research Lead and Manager at Samsung Research America, Staff Research Scientist at Meta AI, and Researcher at NTU.

Career

  1. Since 2024GoogleResearch Scientist
  2. 2016–2024MetaStaff Research Scientist
  3. 2011–2013Nanyang Technological UniversityResearcher
  4. Samsung Research AmericaResearch Lead and Manager

Education

  1. 2016Dartmouth CollegePhD
  2. Ho Chi Minh City University of ScienceBSc
  3. University of Illinois Urbana-ChampaignMSc

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

  1. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Du Tran. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  2. Google had the most people shaping AI every year from 2014 to 2025Includes Google. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  3. Google has the highest combined h-index among AI organizationsIncludes Google. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  4. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Google. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.

Colleagues

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

Sources and credits

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

  1. [1412.0767] Learning Spatiotemporal Features with 3D Convolutional Networks arxiv.org. Checked 21 October 2026.
  2. Cancer Surgeon and Computer Scientist Win Fulbrights | Dartmouth home.dartmouth.edu. Checked 21 October 2026.
  3. Du Tran | Home dutran.github.io. Checked 21 October 2026.
  4. CVPR 2018 Open Access Repository openaccess.thecvf.com. Checked 21 October 2026.
  5. [1904.02811] Video Classification with Channel-Separated Convolutional Networks arxiv.org. Checked 21 October 2026.
  6. [1905.12681] What Makes Training Multi-Modal Classification Networks Hard? arxiv.org. Checked 21 October 2026.
  7. ICCV 2021 Open Access Repository openaccess.thecvf.com. Checked 21 October 2026.
  8. LAMM Workshop sites.google.com. Checked 21 October 2026.
  9. CVPR 2025 Open Access Repository openaccess.thecvf.com. Checked 21 October 2026.