World's Best Scientists 2026 revealed!
Award Badge
Best Scientists
2025
Award Badge
Computer Science
USA
2026

D-Index & Metrics

Best Scientists

D-Index
168
Citations
243493
World Ranking
924
National Ranking
546

Computer Science

D-Index
169
Citations
255305
World Ranking
17
National Ranking
8

Research.com Recognitions

  • 2026 - Research.com Computer Science in United States Leader Award
  • 2025 - Research.com Best Scientists Award
  • 2025 - Research.com Computer Science in United States Leader Award
  • 2023 - Research.com Computer Science in United States Leader Award
  • 2022 - Research.com Computer Science in United States Leader Award

Overview

Trevor Darrell is affiliated with the University of California, Berkeley in the United States. Their research primarily focuses on various areas within computer science, particularly computer vision and artificial intelligence.

Their main fields of study include:

  • Computer Science

Within this domain, their subfields of specialization encompass:

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Control and Systems Engineering
  • Signal Processing
  • Radiology, Nuclear Medicine and Imaging

Trevor Darrell's work covers a range of topics, with notable emphasis on:

  • Multimodal Machine Learning Applications
  • Domain Adaptation and Few-Shot Learning
  • Human Pose and Action Recognition
  • Advanced Neural Network Applications
  • Advanced Image and Video Retrieval Techniques
  • Topic Modeling
  • Generative Adversarial Networks and Image Synthesis

Their publication record includes contributions in both conferences and open-access repositories. Frequent venues for their publications are:

  • arXiv (Cornell University)
  • 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Applied AI Letters
  • Lecture Notes in Computer Science

Recent papers authored or co-authored by Trevor Darrell include:

  • "A ConvNet for the 2020s" (2022), presented at the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • "Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning" (2021), published at the 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • "Early Convolutions Help Transformers See Better" (2021), available on arXiv (Cornell University)
  • "Tent: Fully Test-time Adaptation by Entropy Minimization" (2020), available on arXiv (Cornell University)
  • "Contrastive Test-Time Adaptation" (2022), presented at the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Trevor Darrell has frequently collaborated with several researchers, including:

  • Anna Rohrbach
  • Joseph E. Gonzalez
  • Roei Herzig
  • Amir Bar
  • Baifeng Shi

Best Publications

  • Fully convolutional networks for semantic segmentation

    Jonathan Long;Evan Shelhamer;Trevor Darrell

  • Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

    Ross Girshick;Jeff Donahue;Trevor Darrell;Jitendra Malik

  • Caffe: Convolutional Architecture for Fast Feature Embedding

    Yangqing Jia;Evan Shelhamer;Jeff Donahue;Sergey Karayev

  • Pfinder: real-time tracking of the human body

    C.R. Wren;A. Azarbayejani;T. Darrell;A.P. Pentland

  • Fully Convolutional Networks for Semantic Segmentation

    Evan Shelhamer;Jonathan Long;Trevor Darrell

  • Long-term recurrent convolutional networks for visual recognition and description

    Jeff Donahue;Lisa Anne Hendricks;Sergio Guadarrama;Marcus Rohrbach

  • Context Encoders: Feature Learning by Inpainting

    Deepak Pathak;Philipp Krahenbuhl;Jeff Donahue;Trevor Darrell

  • DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

    Jeff Donahue;Yangqing Jia;Oriol Vinyals;Judy Hoffman

  • Adversarial Discriminative Domain Adaptation

    Eric Tzeng;Judy Hoffman;Kate Saenko;Trevor Darrell

  • End-to-end training of deep visuomotor policies

    Sergey Levine;Chelsea Finn;Trevor Darrell;Pieter Abbeel

  • Region-Based Convolutional Networks for Accurate Object Detection and Segmentation

    Ross Girshick;Jeff Donahue;Trevor Darrell;Jitendra Malik

  • Deep Domain Confusion: Maximizing for Domain Invariance

    Eric Tzeng;Judy Hoffman;Ning Zhang;Kate Saenko

  • Adapting visual category models to new domains

    Kate Saenko;Brian Kulis;Mario Fritz;Trevor Darrell

  • The pyramid match kernel: discriminative classification with sets of image features

    K. Grauman;T. Darrell

  • CyCADA: Cycle-Consistent Adversarial Domain Adaptation

    Judy Hoffman;Eric Tzeng;Taesung Park;Jun-Yan Zhu

  • Curiosity-driven Exploration by Self-supervised Prediction

    Deepak Pathak;Pulkit Agrawal;Alexei A. Efros;Trevor Darrell

  • Long-Term Recurrent Convolutional Networks for Visual Recognition and Description

    Jeff Donahue;Lisa Anne Hendricks;Marcus Rohrbach;Subhashini Venugopalan

  • Integrated Person Tracking Using Stereo, Color, and Pattern Detection

    T. Darrell;G. Gordon;M. Harville;J. Woodfill

  • BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

    Fisher Yu;Haofeng Chen;Xin Wang;Wenqi Xian

  • Adversarial Feature Learning

    Jeff Donahue;Philipp Krähenbühl;Trevor Darrell

Frequent Co-Authors

Kate Saenko
Kate Saenko Boston University
Marcus Rohrbach
Marcus Rohrbach Facebook (United States)
Judy Hoffman
Judy Hoffman Georgia Institute of Technology
Jeff Donahue
Jeff Donahue DeepMind (United Kingdom)
Fisher Yu
Fisher Yu ETH Zurich
Anna Rohrbach
Anna Rohrbach Technical University of Darmstadt
Louis-Philippe Morency
Louis-Philippe Morency Carnegie Mellon University
Yangqing Jia
Yangqing Jia Alibaba Group (China)
Sergey Levine
Sergey Levine University of California, Berkeley

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

Pursuing a Computer Science degree in the USA opens up a variety of related online programs and fast-track career opportunities. Many students choose complementary or alternative pathways such as Data Science or Electrical Engineering to expand their skillsets and job prospects.

If affordability is a priority, you may want to consider what is the cheapest data science course in the US? This can help you kick-start your tech career without breaking the bank. Similarly, understanding electrical engineering online tuition costs can help you make informed decisions about specializing further.

For those looking to enter the workforce quickly, explore quick certifications that pay well. These credentials often require less time and money but can significantly boost your employability in the tech field.

If you are aiming for an advanced credential, learn about the fastest online master's degree options available. Such programs allow for efficient upskilling and can accelerate your professional growth in technology-driven industries.

Best Scientists Citing Trevor Darrell

Trending Scientists