World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
37
Citations
8539
World Ranking
10526
National Ranking
4408

Overview

Tomas Pfister is affiliated with Google in the United States and has contributed extensively to the field of computer science with a focus on artificial intelligence. Their research spans multiple subfields including artificial intelligence, computer vision and pattern recognition, signal processing, management science and operations research, and epidemiology.

Their main topics of work include:

  • Domain Adaptation and Few-Shot Learning
  • Topic Modeling
  • Natural Language Processing Techniques
  • Multimodal Machine Learning Applications
  • Machine Learning and Data Classification
  • Anomaly Detection Techniques and Applications
  • Time Series Analysis and Forecasting

Pfister has published extensively in several venues, with a strong presence on arXiv and in major conferences:

  • arXiv (Cornell University)
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • npj Digital Medicine
  • 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Recent publications include:

  • "Learning to Prompt for Continual Learning," 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • "A Simple Semi-Supervised Learning Framework for Object Detection," 2020, arXiv (Cornell University)
  • "Temporal Fusion Transformers for interpretable multi-horizon time series forecasting," 2021, International Journal of Forecasting
  • "Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding," 2022, Proceedings of the AAAI Conference on Artificial Intelligence
  • "TabNet: Attentive Interpretable Tabular Learning," 2021, Proceedings of the AAAI Conference on Artificial Intelligence

Frequent co-authors working alongside Pfister include:

  • Sercan Ö. Arık
  • Chunliang Li
  • Jinsung Yoon
  • Chen-Yu Lee
  • Zizhao Zhang

Pfister's body of work includes 173 publications predominantly in computer science, with 115 specifically focusing on artificial intelligence and 40 addressing computer vision and pattern recognition. Their research covers diverse applications and techniques, reflecting a multidisciplinary approach spanning theory and applied machine learning. This range indicates an active role in advancing methods related to learning frameworks, interpretable models, and forecasting techniques.

Best Publications

  • Learning from Simulated and Unsupervised Images through Adversarial Training

    Ashish Shrivastava;Tomas Pfister;Oncel Tuzel;Joshua Susskind

  • Temporal Fusion Transformers for interpretable multi-horizon time series forecasting

    Bryan Lim;Sercan Ömer Arik;Nicolas Loeff;Tomas Pfister

  • CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

    Chun-Liang Li;Kihyuk Sohn;Jinsung Yoon;Tomas Pfister

  • TabNet: Attentive Interpretable Tabular Learning.

    Sercan Ömer Arik;Tomas Pfister

  • A Spontaneous Micro-expression Database: Inducement, collection and baseline

    Xiaobai Li;Tomas Pfister;Xiaohua Huang;Guoying Zhao

  • Flowing ConvNets for Human Pose Estimation in Videos

    Tomas Pfister;James Charles;Andrew Zisserman

  • Towards Reading Hidden Emotions: A Comparative Study of Spontaneous Micro-Expression Spotting and Recognition Methods

    Xiaobai Li;Xiaopeng Hong;Antti Moilanen;Xiaohua Huang

  • Learning to Prompt for Continual Learning

    Unknown

  • Recognising spontaneous facial micro-expressions

    Tomas Pfister;Xiaobai Li;Guoying Zhao;Matti Pietikainen

  • A Simple Semi-Supervised Learning Framework for Object Detection.

    Kihyuk Sohn;Zizhao Zhang;Chun-Liang Li;Han Zhang

  • DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning

    Unknown

  • PseudoSeg: Designing Pseudo Labels for Semantic Segmentation

    Yuliang Zou;Zizhao Zhang;Han Zhang;Chun-Liang Li

  • Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

    Unknown

  • Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos

    Tomas Pfister;Karen Simonyan;James Charles;Andrew Zisserman

  • Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting

    Bryan Lim;Sercan O. Arik;Nicolas Loeff;Tomas Pfister

  • Consistency-Based Semi-supervised Active Learning: Towards Minimizing Labeling Cost

    Mingfei Gao;Zizhao Zhang;Guo Yu;Sercan Ömer Arik

  • TabNet: Attentive Interpretable Tabular Learning

    Sercan O. Arik;Tomas Pfister

  • Learning from Simulated and Unsupervised Images through Adversarial Training

    Ashish Shrivastava;Tomas Pfister;Oncel Tuzel;Josh Susskind

  • Distilling Effective Supervision From Severe Label Noise

    Zizhao Zhang;Han Zhang;Sercan O. Arik;Honglak Lee

  • Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding

    Unknown

  • Differentiating spontaneous from posed facial expressions within a generic facial expression recognition framework

    Tomas Pfister;Xiaobai Li;Guoying Zhao;Matti Pietikainen

  • Flowing ConvNets for Human Pose Estimation in Videos

    Tomas Pfister;James Charles;Andrew Zisserman

  • Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval

    Unknown

  • Personalizing Human Video Pose Estimation

    James Charles;Tomas Pfister;Derek Magee;David Hogg

  • Domain-Adaptive Discriminative One-Shot Learning of Gestures

    Tomas Pfister;James Charles;Andrew Zisserman

  • Learning and Evaluating Representations for Deep One-Class Classification

    Kihyuk Sohn;Chun-Liang Li;Jinsung Yoon;Minho Jin

  • Automatic and Efficient Human Pose Estimation for Sign Language Videos

    James Charles;Tomas Pfister;Mark Everingham;Andrew Zisserman

  • Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the US

    Estee Y Cramer;Evan L Ray;Velma K Lopez;Johannes Bracher

  • Data Valuation using Reinforcement Learning

    Jinsung Yoon;Sercan Arik;Tomas Pfister

Frequent Co-Authors

Andrew Zisserman
Andrew Zisserman University of Oxford
Kihyuk Sohn
Kihyuk Sohn Google (United States)
Matti Pietikäinen
Matti Pietikäinen University of Oulu
Guoying Zhao
Guoying Zhao University of Oulu
David C. Hogg
David C. Hogg University of Leeds
Honglak Lee
Honglak Lee University of Michigan–Ann Arbor
Pradeep Ravikumar
Pradeep Ravikumar Carnegie Mellon University
Been Kim
Been Kim Google (United States)
Oncel Tuzel
Oncel Tuzel Apple (United States)
Xiang Zhang
Xiang Zhang University of Hong Kong

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 can open up flexible pathways to a computer science career. For students seeking affordable education, cheap online college classes make it possible to gain foundational skills without significant debt. This helps many learners from diverse backgrounds start their academic journey.

Concerned about past academic performance? Some online graduate schools with low gpa requirements offer ways for students to continue their studies, even if their undergraduate GPA isn’t high. Such programs ensure that motivated candidates still have a path forward.

Additionally, those interested in the intersection of technology and sustainability may consider high-paying jobs with an environmental science degree. Explore how computer science skills can complement fields like environmental science by reviewing high-paying jobs with environmental science degree.

For individuals seeking faster entry into the field, a 2-year computer science degree online can accelerate your path to employment and career advancement, making online education a smart choice for many aspiring professionals.

Best Scientists Citing Tomas Pfister

Trending Scientists