PeopleofSuperintelligence

Researcher

Huisheng Wang

Huisheng Wang is a computer vision researcher at Google whose work spans video coding, representation learning, multimodal generation, dense prediction, and accessibility. With Antonio Ortega and Ngai-Man Cheung, he won a 2006 EURASIP Best Paper award for adaptive scalable video coding, and in 2021 he coauthored a self-supervised contrastive method for learning visual representations from unlabeled videos. In 2023, he coauthored the Integrated Multimodal Perception model and the VideoGLUE evaluation protocol and provided leadership support to Google's Project Guideline accessibility platform. His work from 2023 to 2025 included the VideoPoet language model, which won an ICML 2024 Best Paper award, the PolyMaX dense-prediction model, the VideoPrism visual encoder, and the SANPO dataset for outdoor human navigation.

Timeline

  1. 2006

    EURASIP Best Paper award

    With Antonio Ortega and Ngai-Man Cheung, he wins the 2006 EURASIP Journal on Advances in Signal Processing Best Paper award for work on adaptive scalable video coding using Wyner-Ziv techniques.

  2. 2021

    Learning from unlabeled video

    In 2021, he coauthors Spatiotemporal Contrastive Video Representation Learning at CVPR, a self-supervised method to learn spatiotemporal visual representations from unlabeled videos.

  3. 2023

    Integrated Multimodal Perception and VideoGLUE

    He coauthors two 2023 papers: Integrated Multimodal Perception (IMP), a multimodal multi-task training and modeling approach combining alternating gradient descent and mixture-of-experts, and VideoGLUE, an experiment protocol evaluating the video understanding capabilities of foundation models.

  4. 2023

    Project Guideline support

    At Google in 2023, he provides leadership support to Project Guideline, an open-sourced computer vision accessibility platform.

  5. 2023–2024

    VideoPoet wins an ICML award

    Wang coauthors VideoPoet, a decoder-only transformer language model for zero-shot video generation that processes multimodal inputs including images, videos, text, and audio; the paper wins an ICML 2024 Best Paper award.

  6. 2024

    PolyMaX for dense prediction

    At WACV 2024, he coauthors PolyMaX, a mask-transformer model for general dense prediction tasks such as semantic segmentation, depth estimation, and surface normal prediction.

  7. 2024

    VideoPrism for video understanding

    In 2024, he coauthors VideoPrism, a foundational visual encoder for video understanding pretrained on 36 million video-text pairs and 582 million video clips.

  8. 2025

    The SANPO dataset

    He coauthors SANPO at WACV 2025, a large-scale egocentric video dataset of 701 stereo videos designed for dense prediction in outdoor human navigation environments.

  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.

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 Huisheng Wang yet. Send us a free-licensed photo.

  1. Antonio Ortega, Dept. of EE-Systems, USC sipi.usc.edu. Checked 22 October 2026.
  2. Spatiotemporal Contrastive Video Representation Learning openaccess.thecvf.com. Checked 22 October 2026.
  3. Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception arxiv.org. Checked 22 October 2026.
  4. VideoGLUE: Video General Understanding Evaluation of Foundation Models arxiv.org. Checked 22 October 2026.
  5. Open sourcing Project Guideline: A platform for computer vision accessibility technology research.google. Checked 22 October 2026.
  6. VideoPoet: A large language model for zero-shot video generation research.google. Checked 22 October 2026.
  7. VideoPoet: A Large Language Model for Zero-Shot Video Generation research.google. Checked 22 October 2026.
  8. ICML 2024 Awards icml.cc. Checked 22 October 2026.
  9. WACV 2024 Open Access Repository openaccess.thecvf.com. Checked 22 October 2026.
  10. VideoPrism: A foundational visual encoder for video understanding research.google. Checked 22 October 2026.
  11. SANPO: A Scene Understanding, Accessibility and Human Navigation Dataset openaccess.thecvf.com. Checked 22 October 2026.