World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
43
Citations
11203
World Ranking
7823
National Ranking
3383

Overview

Michael S. Ryoo is affiliated with Stony Brook University in the United States and has contributed extensively to the field of computer science, particularly in areas related to computer vision and artificial intelligence. Their research output spans multiple subfields, including computer vision and pattern recognition, artificial intelligence, signal processing, computer networks and communications, and biophysics.

The primary areas of research focus include:

  • Multimodal Machine Learning Applications
  • Human Pose and Action Recognition
  • Domain Adaptation and Few-Shot Learning
  • Advanced Neural Network Applications
  • Anomaly Detection Techniques and Applications
  • Generative Adversarial Networks and Image Synthesis
  • Video Analysis and Summarization

Among recent publications, notable works are:

  • "RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control" (2023, arXiv Cornell University)
  • "Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language" (2022, arXiv Cornell University)
  • "Self-supervised Video Transformer" (2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition [CVPR])
  • "Toward Collaborative Inferencing of Deep Neural Networks on Internet-of-Things Devices" (2020, IEEE Internet of Things Journal)
  • "MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection" (2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition [CVPR])

The publication venues in which Michael S. Ryoo most frequently publishes include:

  • arXiv (Cornell University)
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Lecture Notes in Computer Science
  • IEEE Internet of Things Journal

Collaborations form an important part of their research process, with frequent coauthors such as:

  • AJ Piergiovanni
  • Kumara Kahatapitiya
  • Anelia Angelova
  • Kanchana Ranasinghe
  • Jinghuan Shang

Michael S. Ryoo's work notably centers on applying deep learning and multimodal reasoning techniques to problems involving vision and language, robotic control, and video understanding. This multidisciplinary approach integrates advanced neural network models and adaptive learning strategies across a range of emerging technologies in artificial intelligence.

Best Publications

  • Human activity analysis: A review

    J.K. Aggarwal;M.S. Ryoo

  • Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities

    M. S. Ryoo;J. K. Aggarwal

  • Human activity prediction: Early recognition of ongoing activities from streaming videos

    M. S. Ryoo

  • Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

    Unknown

  • RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

    Unknown

  • Recognition of Composite Human Activities through Context-Free Grammar Based Representation

    M.S. Ryoo;J.K. Aggarwal

  • First-Person Activity Recognition: What Are They Doing to Me?

    Michael S. Ryoo;Larry Matthies

  • RT-1: Robotics Transformer for Real-World Control at Scale

    Unknown

  • Semantic Representation and Recognition of Continued and Recursive Human Activities

    M. S. Ryoo;J. K. Aggarwal

  • Learning to Anonymize Faces for Privacy Preserving Action Detection

    Zhongzheng Ren;Yong Jae Lee;Michael S. Ryoo

  • Pooled motion features for first-person videos

    M. S. Ryoo;Brandon Rothrock;Larry Matthies

  • An overview of contest on semantic description of human activities (SDHA) 2010

    M. S. Ryoo;Chia-Chih Chen;J. K. Aggarwal;Amit Roy-Chowdhury

  • Privacy-Preserving Human Activity Recognition from Extreme Low Resolution.

    Michael S. Ryoo;Brandon Rothrock;Charles Fleming;Hyun Jong Yang

  • Open-vocabulary Queryable Scene Representations for Real World Planning

    Unknown

  • Representation Flow for Action Recognition

    AJ Piergiovanni;Michael S. Ryoo

  • Stochastic Representation and Recognition of High-Level Group Activities

    M. S. Ryoo;J. K. Aggarwal

  • Robot-Centric Activity Prediction from First-Person Videos: What Will They Do to Me?

    M. S. Ryoo;Thomas J. Fuchs;Lu Xia;J. K. Aggarwal

  • Evolving Losses for Unsupervised Video Representation Learning

    AJ Piergiovanni;Anelia Angelova;Michael S. Ryoo

  • MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection

    Unknown

  • First-Person Animal Activity Recognition from Egocentric Videos

    Yumi Iwashita;Asamichi Takamine;Ryo Kurazume;M. S. Ryoo

  • Learning Latent Super-Events to Detect Multiple Activities in Videos

    AJ Piergiovanni;Michael S. Ryoo

  • Distributed Perception by Collaborative Robots

    Ramyad Hadidi;Jiashen Cao;Matthew Woodward;Michael S. Ryoo

  • Hierarchical Recognition of Human Activities Interacting with Objects

    M.S. Ryoo;J.K. Aggarwal

  • Detection of abandoned objects in crowded environments

    M. Bhargava;Chia-Chih Chen;M.S. Ryoo;J.K. Aggarwal

  • Stochastic representation and recognition of high-level group activities: Describing structural uncertainties in human activities

    M S Ryoo;J K Aggarwal

Frequent Co-Authors

Anelia Angelova
Anelia Angelova Google (United States)
Jake K. Aggarwal
Jake K. Aggarwal The University of Texas at Austin
Hyesoon Kim
Hyesoon Kim Georgia Institute of Technology
Larry Matthies
Larry Matthies Jet Propulsion Lab
Alexander Toshev
Alexander Toshev Apple (United States)
Yong Jae Lee
Yong Jae Lee University of Wisconsin–Madison
Song-Chun Zhu
Song-Chun Zhu Peking University
David J. Crandall
David J. Crandall Indiana University
Kris M. Kitani
Kris M. Kitani Carnegie Mellon University
Irfan Essa
Irfan Essa Georgia Institute of Technology

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online education in the field of computer science opens up a variety of pathways for diverse learners. For those who may have academic challenges, several universities for low gpa offer flexible admission policies and online learning opportunities, making a computer science degree more accessible.

If you are aiming to complete your studies quickly, consider accelerated computer science degree programs. These intensive options can help you earn your qualifications faster and kickstart your tech career sooner.

Tech skills are also applicable in related areas such as environmental science. Wondering about career options? Here’s what can you get with an environmental science degree, including roles in sustainability, research, and policy development.

For students interested in intertwining technology and sustainability, distance learning is also available for engineering fields. Discover the environmental engineering schools online to find budget-friendly options that connect both domains.

Best Scientists Citing Michael S. Ryoo

Trending Scientists