PeopleofSuperintelligence

Researcher

Mikhail Sirotenko

Mikhail Sirotenko is a computer vision researcher whose work spans fashion image segmentation, accessible scene understanding, and video modeling. He helped organize an apparel-segmentation challenge in 2019 and coauthored Fashionpedia in 2020. In 2023, he joined SANPO's core team and coauthored VideoGLUE and VideoPoet; VideoPoet won an ICML 2024 Best Paper Award. He also coauthored a 128-frame video masked autoencoder method in 2024 and MINERVA, a video reasoning benchmark, in 2025. As of October 2026, he is Head of Engineering at Sequen.

Now at
Sequen

Timeline

  1. 2019

    Organizing iMat Fashion

    At CVPR 2019, he helps organize the iMaterialist-Fashion competition for apparel instance segmentation and fine-grained attribute classification.

  2. 2020

    Fashionpedia image labels

    In 2020, he coauthors Fashionpedia, which pairs a fashion ontology with images annotated for instance segmentation and fine-grained attributes.

  3. October 2023

    SANPO for human navigation

    In October 2023, he joins SANPO's core team for an outdoor egocentric video dataset that supports scene understanding and navigation.

  4. 2023–2024

    VideoGLUE and VideoPoet

    In 2023, he coauthors VideoGLUE, which evaluates video foundation models on action recognition, temporal localization, and spatiotemporal localization. Google Research introduces VideoPoet in December 2023; its 2024 proceedings list Sirotenko among its authors.

  5. 2024

    An ICML Best Paper

    VideoPoet wins an ICML Best Paper Award in 2024, with Sirotenko among its coauthors.

  6. December 2024

    Video masked autoencoders

    In December 2024, he coauthors a method that extends video masked autoencoders to 128 frames by reconstructing selected tokens during decoding.

  7. 2025

    MINERVA for video reasoning

    In 2025, he coauthors MINERVA, a video reasoning dataset that gives each question five answer choices and hand-crafted reasoning traces.

  8. As of October 2026

    Engineering at Sequen

    As of October 2026, he is Head of Engineering at Sequen, a company for enterprise AI and search.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  2. The United States employs an estimated 48% of people shaping AIWe 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.
  3. 43% of living people shaping AI work outside their country of birthWe estimate that 43% of living people shaping AI work outside their country of birth (520 of 1,198 people with known birth and employment countries).
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionWe 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.

Sources and credits

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

  1. FGVC6 - iMat Fashion 2019 sites.google.com. Checked 21 October 2026.
  2. Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset research.google. Checked 21 October 2026.
  3. SANPO: A Scene understanding, Accessibility, Navigation, Pathfinding, & Obstacle avoidance dataset research.google. Checked 21 October 2026.
  4. VideoGLUE: Video General Understanding Evaluation of Foundation Models arxiv.org. Checked 21 October 2026.
  5. VideoPoet: A large language model for zero-shot video generation research.google. Checked 21 October 2026.
  6. VideoPoet: A Large Language Model for Zero-Shot Video Generation proceedings.mlr.press. Checked 21 October 2026.
  7. ICML 2024 Awards icml.cc. Checked 21 October 2026.
  8. Extending video masked autoencoders to 128 frames research.google. Checked 21 October 2026.
  9. MINERVA: Evaluating Complex Video Reasoning openaccess.thecvf.com. Checked 21 October 2026.
  10. About Sequen | Built by Enterprise AI & Search Experts sequen.ai. Checked 21 October 2026.