# Philip H. S. Torr
Philip H. S. Torr (also cited as Philip Torr) is a British computer vision researcher who holds the Five AI/Royal Academy of Engineering Research Chair in Computer Vision and Machine Learning at the [University of Oxford](https://www.edgepedia.org/university-of-oxford)'s Department of Engineering Science and is a fellow of St Catherine's College.[1](https://eng.ox.ac.uk/people/philip-torr) The Royal Society records his research as pioneering work in object recognition, segmentation, 3D reconstruction, tracking, and scene understanding.[2](https://royalsociety.org/people/philip-torr-35001/) His Royal Society citation identifies two strands: robust statistics in visual geometry, especially computing camera motion from video, and Markov Random Field approaches to segmentation and recognition.[3](https://eng.ox.ac.uk/news/professor-philip-torr-elected-fellow-of-the-royal-society)
| Fact | Detail |
|---|---|
| Position | Five AI/RAEng Research Chair in Computer Vision and Machine Learning, Department of Engineering Science, University of Oxford; fellow of St Catherine's College[1](https://eng.ox.ac.uk/people/philip-torr) |
| Field | Computer vision: object recognition, segmentation, 3D reconstruction, tracking, scene understanding[2](https://royalsociety.org/people/philip-torr-35001/) |
| Training | Pure Mathematics at Southampton University; DPhil, University of Oxford, 1995, advisor David William Murray[4](https://www.stcatz.ox.ac.uk/person/torr/) • [5](https://mathgenealogy.org/id.php?id=177085) |
| Signature work | Res2Net multi-scale backbone architecture, IEEE TPAMI (preprint 2019)[6](https://arxiv.org/pdf/1904.01169) |
| Group | Torr Vision Group, formed 2005, at Oxford since 2013, 25–30 people, part of the Oxford Robotics Institute[7](https://torrvision.com/index.html) • [8](https://imcc.site.ox.ac.uk/people/dr-philip-torr) |
| Honors | Marr prize 1998; RAEng Fellowship 2019; Royal Society Fellowship 2021; Turing AI World-Leading Researcher Fellowship 2021[2](https://royalsociety.org/people/philip-torr-35001/) • [9](https://www.stcatz.ox.ac.uk/news-2021-july-philip-torr-wins-3m-ukri-research-fellowship/) |
| Industry | Founder or advisor of FiveAI, Onfido, Oxsight, AIstetic, Eigent, DreamTech, Visionary Machines, CamelAI[10](https://aigi.ox.ac.uk/people/philip-torr/) |
## Career
Torr studied Pure Mathematics at Southampton University before coming to Oxford for a DPhil in the Department of Engineering Science on automated understanding of images.[4](https://www.stcatz.ox.ac.uk/person/torr/) The Mathematics Genealogy Project records the degree as awarded in 1995 with the dissertation *Outlier Detection and Motion Segmentation*, advised by David William Murray; the ProQuest dissertation record prints the title as *Motion segmentation and outlier detection*.[5](https://mathgenealogy.org/id.php?id=177085) • [11](https://www.proquest.com/docview/304266501) He then left Oxford to work for six years as a research scientist for [Microsoft Research](https://www.edgepedia.org/microsoft-research), first in Redmond in the Vision Technology Group, then in Cambridge, where he founded the vision side of the Machine Learning and Perception Group.[1](https://eng.ox.ac.uk/people/philip-torr) He became a Professor in Computer Vision and Machine Learning at [Oxford Brookes University](https://www.edgepedia.org/oxford-brookes-university), and returned to Oxford as a full professor in 2013.[1](https://eng.ox.ac.uk/people/philip-torr)
## Representative work
**Res2Net.** The Res2Net paper, published in [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://www.edgepedia.org/ieee-transactions-on-pattern-analysis-and-machine-intelligence) (TPAMI) with a 2019 arXiv preprint, proposes a building block for convolutional networks that constructs hierarchical residual-like connections within a single residual block, representing multi-scale features at a granular level.[6](https://arxiv.org/pdf/1904.01169) This exposes a new dimension, scale (the number of feature groups in the block), alongside the existing dimensions of depth, width, and cardinality.[6](https://arxiv.org/pdf/1904.01169) The block can be plugged into existing backbones such as ResNet, ResNeXt, and DLA; on ImageNet, Res2Net-50 reduced top-1 error over ResNet-50 by 1.84%, at roughly matched complexity (about 25M parameters and 4.2G FLOPs for 224×224 images in 50-layer networks).[6](https://arxiv.org/pdf/1904.01169) • [12](https://mmcheng.net/mftp/Papers/19pami_res2net.pdf)
**Struck.** Struck (TPAMI 2015, conference version 2011) is a tracking-by-detection framework based on structured output prediction: by letting the output space express the tracker's needs directly, it avoids the intermediate classification step that earlier adaptive tracking-by-detection methods required.[14](https://www.robots.ox.ac.uk/~tvg/publications/2015/struck-author.pdf) The journal version adds a budgeting mechanism that prevents unbounded growth in the number of support vectors, a GPU implementation, and a multi-kernel variant that achieved state-of-the-art results on the Wu benchmark, outperforming KCF.[14](https://www.robots.ox.ac.uk/~tvg/publications/2015/struck-author.pdf) The publisher record places the 2011 conference version at ICCV, pages 263–270; Torr's own publication list prints the venue as the Twelfth European Conference on Computer Vision.[15](https://dl.acm.org/doi/10.1109/TPAMI.2015.2509974) • [16](https://www.robots.ox.ac.uk/~phst/papers.htm)
**Robust higher order potentials.** According to the 2009 *International Journal of Computer Vision* paper (from a CVPR 2008 oral), the potentials are defined on sets of pixels, image segments produced by unsupervised segmentation, that enforce label consistency, generalising pairwise contrast-sensitive smoothness potentials in conditional random fields.[16](https://www.robots.ox.ac.uk/~phst/papers.htm) • [17](https://www.robots.ox.ac.uk/~lubor/cvpr08.pdf) The Robust Pn potentials can be minimized with graph-cut move-making algorithms whose complexity grows linearly with clique size, allowing cliques of thousands of latent variables; on a multi-class segmentation example, adding the potential raised overall pixelwise accuracy from 95.8% to 98.7% with much better object boundaries.[17](https://www.robots.ox.ac.uk/~lubor/cvpr08.pdf) His publication list also records segmentation and geometry work including OBJCUT, on efficient segmentation using top-down and bottom-up cues (TPAMI, 2010), and global [stereo reconstruction](https://www.edgepedia.org/stereo-reconstruction) under second-order smoothness priors (TPAMI, 2009).[16](https://www.robots.ox.ac.uk/~phst/papers.htm)
## Torr Vision Group
The Torr Vision Group, formerly the Brookes Vision Group, was formed in 2005 and moved to the University of Oxford in 2013.[7](https://torrvision.com/index.html) It comprises 25–30 people working on computer vision and machine learning, and Torr became Co-Director of Oxford's International Multimodal Communication Centre.[8](https://imcc.site.ox.ac.uk/people/dr-philip-torr) The group has contributed to technology transfer into real-world applications, from autonomous cars to cybersecurity.[7](https://torrvision.com/index.html)
## Industry roles and companies
Torr was involved in the algorithm design for Boujou, released by 2D3, which won a technical EMMY among other industry awards.[1](https://eng.ox.ac.uk/people/philip-torr) He has been involved in numerous spin-outs as founder or advisor, including FiveAI, Onfido, Oxsight, Eigent, DreamTech, Visionary Machines, and CamelAI; the Royal Society lists him as founder of companies including Oxsight and AIstetic, and his personal page records OxSight as formed in 2016.[1](https://eng.ox.ac.uk/people/philip-torr) • [2](https://royalsociety.org/people/philip-torr-35001/) • [18](https://www.robots.ox.ac.uk/~phst/old.index.html) He has also worked closely with Google, Meta, Apple, Microsoft, and Sony.[10](https://aigi.ox.ac.uk/people/philip-torr/)
## Honors and recognition
Torr won the Marr prize, described on his Oxford and Royal Society pages as the highest honor in computer vision, in 1998.[1](https://eng.ox.ac.uk/people/philip-torr) • [2](https://royalsociety.org/people/philip-torr-35001/) In 2007 he was made a Wolfson Research Merit Award holder, and he received the European Advanced Investigator Award (ERC Advanced Grant) in 2013, providing 2.5 million euros to set up a new research group at Oxford.[4](https://www.stcatz.ox.ac.uk/person/torr/) • [18](https://www.robots.ox.ac.uk/~phst/old.index.html) He was elected a Fellow of the [Royal Academy of Engineering](https://www.edgepedia.org/royal-academy-of-engineering) in 2019, cited for pioneering research in computer vision, especially SLAM, 3D reconstruction, image segmentation, and object motion tracking, with influence on 3D motion capture and augmented reality.[19](https://raeng.org.uk/about-us/fellowship/new-fellows-2019/philip-torr/) He was elected a [Fellow of the Royal Society](https://www.edgepedia.org/fellow-of-the-royal-society) in 2021 and holds the IAPR Fellow award.[2](https://royalsociety.org/people/philip-torr-35001/) • [3](https://eng.ox.ac.uk/news/professor-philip-torr-elected-fellow-of-the-royal-society) Also in 2021, [UK Research and Innovation](https://www.edgepedia.org/uk-research-and-innovation) appointed him one of five Turing AI World-Leading Researcher Fellows, with a five-year, £3 million fellowship; four partner organizations, Facebook (International), Five AI, Horizon Robotics, and Remark Holdings, contributed an additional £1.9 million.[9](https://www.stcatz.ox.ac.uk/news-2021-july-philip-torr-wins-3m-ukri-research-fellowship/)
## Recent work
The group's 2023 publications include work on model reliability: sample-dependent adaptive temperature scaling for improved calibration, and RANCER, a method for non-axis-aligned anisotropic certification with randomized smoothing, both at AAAI 2023.[13](https://www.robots.ox.ac.uk/~tvg/publication/)
## References
1. Philip Torr, Department of Engineering Science, University of Oxford. https://eng.ox.ac.uk/people/philip-torr
2. Professor Philip Torr FREng FRS, Royal Society. https://royalsociety.org/people/philip-torr-35001/
3. Professor Philip Torr Elected Fellow of the Royal Society, University of Oxford. https://eng.ox.ac.uk/news/professor-philip-torr-elected-fellow-of-the-royal-society
4. Philip Torr, St Catherine's College, Oxford. https://www.stcatz.ox.ac.uk/person/torr/
5. Philip Torr, The Mathematics Genealogy Project. https://mathgenealogy.org/id.php?id=177085
6. Res2Net: A New Multi-scale Backbone Architecture (arXiv preprint). https://arxiv.org/pdf/1904.01169
7. TVG, Torr Vision Group, University of Oxford. https://torrvision.com/index.html
8. Professor Philip Torr, International Multimodal Communication Centre. https://imcc.site.ox.ac.uk/people/dr-philip-torr
9. Philip Torr wins £3m UKRI research fellowship, St Catherine's College. https://www.stcatz.ox.ac.uk/news-2021-july-philip-torr-wins-3m-ukri-research-fellowship/
10. Philip Torr, Oxford Martin AIGI. https://aigi.ox.ac.uk/people/philip-torr/
11. Motion segmentation and outlier detection, ProQuest Dissertations & Theses. https://www.proquest.com/docview/304266501
12. Res2Net: A New Multi-scale Backbone Architecture (TPAMI version, hosted PDF). https://mmcheng.net/mftp/Papers/19pami_res2net.pdf
13. Torr Vision Group publications. https://www.robots.ox.ac.uk/~tvg/publication/
14. Struck: Structured Output Tracking with Kernels (author version). https://www.robots.ox.ac.uk/~tvg/publications/2015/struck-author.pdf
15. Struck: Structured Output Tracking with Kernels, ACM Digital Library record. https://dl.acm.org/doi/10.1109/TPAMI.2015.2509974
16. Philip Torr Papers (personal publication list). https://www.robots.ox.ac.uk/~phst/papers.htm
17. Robust Higher Order Potentials for Enforcing Label Consistency (CVPR 2008 version). https://www.robots.ox.ac.uk/~lubor/cvpr08.pdf
18. Dr Philip Torr's Home Page, Oxford Robotics. https://www.robots.ox.ac.uk/~phst/old.index.html
19. Philip Torr, Royal Academy of Engineering, New Fellows 2019. https://raeng.org.uk/about-us/fellowship/new-fellows-2019/philip-torr/
---
*Topic: Encyclopedia › Technology and the built world › Engineers and computer scientists › Computer scientists and AI researchers › Computer vision researchers*
*Initially written Sep 21, 2026 · Reviewed: Sep 25, 2026; Sep 30, 2026 · Edited: Sep 25, 2026; Oct 15, 2026 · Last review: Sep 30, 2026*
*Copyright 2026 EdgeChat AI, a subsidiary of Biostate AI.*
License: Edgepedia Community License 1.0, https://www.edgepedia.org/edgepedia/license