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

D-Index & Metrics

Computer Science

D-Index
134
Citations
97907
World Ranking
88
National Ranking
4

Research.com Recognitions

  • 2026 - Research.com Computer Science in United Kingdom Leader Award
  • 2025 - Research.com Computer Science in United Kingdom Leader Award
  • 2023 - Research.com Computer Science in United Kingdom Leader Award
  • 2022 - Research.com Computer Science in United Kingdom Leader Award
  • 2019 - Fellow of the Royal Academy of Engineering (UK)
  • 2012 - Fellow of the International Association for Pattern Recognition (IAPR) For contributions to robust computer vision

Overview

Philip H. S. Torr is a researcher affiliated with the University of Oxford in the United Kingdom. Their scientific contributions primarily fall within the field of Computer Science, with a substantial focus on Computer Vision and Pattern Recognition as well as Artificial Intelligence.

Their body of work encompasses several key topics, including:

  • Domain Adaptation and Few-Shot Learning
  • Advanced Neural Network Applications
  • Multimodal Machine Learning Applications
  • Adversarial Robustness in Machine Learning
  • Advanced Image and Video Retrieval Techniques
  • Generative Adversarial Networks and Image Synthesis
  • Machine Learning and Data Classification

Significant recent publications authored or co-authored by Philip H. S. Torr include:

  • "Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?", 2020, arXiv (Cornell University)
  • "FACMAC: Factored Multi-Agent Centralised Policy Gradients", 2020, arXiv (Cornell University)
  • "SiamMask: A Framework for Fast Online Object Tracking and Segmentation.", 2023, PubMed
  • "Solving Inefficiency of Self-supervised Representation Learning", 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • "Open World Entity Segmentation", 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence

Philip H. S. Torr's collaborations are considerable, with frequent coauthors including:

  • Adel Bibi
  • Bernard Ghanem
  • Puneet K. Dokania
  • Motasem Alfarra
  • Pau de Jorge

Their research outputs have been published extensively in various venues, notably:

  • arXiv (Cornell University)
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • PubMed
  • 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence

Philip H. S. Torr has been recognized with several awards, including appointment as a Fellow of the Royal Academy of Engineering (UK) in 2019. Additionally, they were named Fellow of the International Association for Pattern Recognition (IAPR) in 2012 for contributions to robust computer vision.

Best Publications

  • Learning to Compare: Relation Network for Few-Shot Learning

    Flood Sung;Yongxin Yang;Li Zhang;Tao Xiang

  • Fully-Convolutional Siamese Networks for Object Tracking

    Luca Bertinetto;Jack Valmadre;João F. Henriques;Andrea Vedaldi

  • Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

    Sixiao Zheng;Jiachen Lu;Hengshuang Zhao;Xiatian Zhu

  • Struck: Structured Output Tracking with Kernels

    Sam Hare;Stuart Golodetz;Amir Saffari;Vibhav Vineet

  • Res2Net: A New Multi-Scale Backbone Architecture

    Shang-Hua Gao;Ming-Ming Cheng;Kai Zhao;Xin-Yu Zhang

  • MLESAC: A New Robust Estimator with Application to Estimating Image Geometry

    Philip H. S. Torr;Andrew Zisserman

  • Conditional Random Fields as Recurrent Neural Networks

    Shuai Zheng;Sadeep Jayasumana;Bernardino Romera-Paredes;Vibhav Vineet

  • The Visual Object Tracking VOT2016 Challenge Results

    Matej Kristan;Aleš Leonardis;Jiři Matas;Michael Felsberg

  • Staple: Complementary Learners for Real-Time Tracking

    Luca Bertinetto;Jack Valmadre;Stuart Golodetz;Ondrej Miksik

  • The Visual Object Tracking VOT2017 Challenge Results

    Matej Kristan;Ales Leonardis;Jiri Matas;Michael Felsberg

  • The Visual Object Tracking VOT2015 Challenge Results

    Matej Kristan;Jiri Matas;Ale Leonardis;Michael Felsberg

  • Struck: Structured output tracking with kernels

    Sam Hare;Amir Saffari;Philip H. S. Torr

  • HOTA: A Higher Order Metric for Evaluating Multi-object Tracking.

    Jonathon Luiten;Aljosa Osep;Patrick Dendorfer;Philip H. S. Torr

  • End-to-End Representation Learning for Correlation Filter Based Tracking

    Jack Valmadre;Luca Bertinetto;Joao Henriques;Andrea Vedaldi

  • Fast Online Object Tracking and Segmentation: A Unifying Approach

    Qiang Wang;Li Zhang;Luca Bertinetto;Weiming Hu

  • Deeply Supervised Salient Object Detection with Short Connections

    Qibin Hou;Ming-Ming Cheng;Xiaowei Hu;Ali Borji

  • BING: Binarized Normed Gradients for Objectness Estimation at 300fps

    Ming-Ming Cheng;Ziming Zhang;Wen-Yan Lin;Philip Torr

  • Deeply Supervised Salient Object Detection with Short Connections

    Qibin Hou;Ming-Ming Cheng;Xiaowei Hu;Ali Borji

  • An embarrassingly simple approach to zero-shot learning

    Bernardino Romera-Paredes;Philip Torr

  • Global Contrast Based Salient Region Detection

    Unknown

  • The Development and Comparison of Robust Methodsfor Estimating the Fundamental Matrix

    P. H. S. Torr;D. W. Murray

  • SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY

    Namhoon Lee;Thalaiyasingam Ajanthan;Philip H. S. Torr

Frequent Co-Authors

Pushmeet Kohli
Pushmeet Kohli DeepMind (United Kingdom)
Andrew Zisserman
Andrew Zisserman University of Oxford
Ming-Ming Cheng
Ming-Ming Cheng Nankai University
Roberto Cipolla
Roberto Cipolla University of Cambridge
Andrea Vedaldi
Andrea Vedaldi University of Oxford
Carsten Rother
Carsten Rother Heidelberg University
Chris Russell
Chris Russell University of Oxford
Xiaojuan Qi
Xiaojuan Qi University of Hong Kong
Victor Adrian Prisacariu
Victor Adrian Prisacariu University of Oxford
Song Bai
Song Bai ByteDance

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 Computer Science in the USA opens doors to a variety of flexible online degrees and career pathways. Many students start with associate programs, which provide solid foundations for IT and tech roles. For those seeking quick, convenient entry, you might consider the easiest associate degree to get online to build basic technical skills and credentials.

If you're looking to advance your education on a budget, numerous cheap online master's programs are available across the U.S. These programs allow you to specialize in areas like software development, data science, or cybersecurity—often while working full-time.

For those interested in leadership or academia within technology, advanced online options are also accessible. Consider pursuing a phd in leadership and management online, which can prepare you for executive positions or research roles. Similarly, an ed d degree can lead to influential roles in education, policy, or training within the tech industry.

With affordable and flexible online degrees now widely available, students can tailor their learning and career trajectory to fit their individual goals, schedules, and budgets.

Best Scientists Citing Philip H. S. Torr

Trending Scientists

Recently Published Articles