---
title: "Philip H. S. Torr — author profile and papers — Elamur Research"
description: "Philip H. S. Torr, Johns Hopkins University: 3 papers on Elamur Research (2023–2025), h-index 92 — affiliations, topics, co-authors and who…"
canonical: "https://research.elamur.ai/free/en/authors/philip-h-s-torr/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/philip-h-s-torr/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Philip H. S. Torr

# Philip H. S. Torr

Philip H. S. Torr has 3 papers in our library, in 2023–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/), [Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/); often with [Biqing Qi](https://md.research.elamur.ai/free/en/authors/biqing-qi/), [Bowen Zhou](https://md.research.elamur.ai/free/en/authors/bowen-zhou/), [Hui Li](https://md.research.elamur.ai/free/en/authors/hui-li/).

3 papers in our library · 2023–2025

[OpenAlex](https://openalex.org/A5042899882) · [ORCID](https://orcid.org/0009-0006-0259-5732) · [Wikidata](https://www.wikidata.org/wiki/Q131012202) · [**h-index 92**](https://openalex.org/authors/A5042899882) · [476 works](https://openalex.org/works?filter=author.id:A5042899882) · [54,445 citations](https://openalex.org/works?filter=author.id:A5042899882&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/philip-h-s-torr/#papers) · [🔗 Cited 549 times in our library](https://md.research.elamur.ai/free/en/authors/philip-h-s-torr/cited-by/) · [54 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #5247](https://md.research.elamur.ai/free/en/paper-stars/page/53/#star-5247)

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Philip+H.+S.+Torr) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Philip+H.+S.+Torr) · [dblp](https://dblp.org/search?q=Philip+H.+S.+Torr) · [ACL Anthology](https://aclanthology.org/search/?q=Philip+H.+S.+Torr)

## Affiliations

[🎓**University of Oxford** Oxford · United Kingdom 1993–2026 · 327 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) · [🎓**Johns Hopkins University** Baltimore · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/johns-hopkins-university/) · [🎓**Oxford Brookes University** Oxford · United Kingdom 2005–2013 · 21 papers](https://ror.org/04v2twj65) · [🏢**Microsoft** Redmond · United States 1999–2021 · 6 papers](https://md.research.elamur.ai/free/en/companies/microsoft/) · [🏢**Microsoft Research** Cambridge · United Kingdom 2000–2004 · 3 papers](https://md.research.elamur.ai/free/en/companies/microsoft-research-united-kingdom/) · [🎓**Temple University** Philadelphia · United States 2019 · 2 papers](https://md.research.elamur.ai/free/en/universities/temple-university/) · [🎓**University of Reading** Reading · United Kingdom 1992–1998 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-reading/)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

## Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 8 The field of science this work belongs to (OpenAlex fields).[Arts and Humanities · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Safety Research · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Signal Processing · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/)

🧭 Topics 4 Research subjects and languages the work is about.[Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) · [Tokenization & segmentation · 1 work](https://md.research.elamur.ai/free/en/topics/tokenization/) · [Dialogue systems · 1 work](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Speech & spoken language · 1 work](https://md.research.elamur.ai/free/en/topics/speech/)

💡 Concepts 2 Key ideas and methods explained on our concept pages.[Subword tokenization · 1 work](https://md.research.elamur.ai/free/en/concepts/subword-tokenization/) · [Tokenization · 1 work](https://md.research.elamur.ai/free/en/concepts/tokenization/)

## Works by year

### 2020s

[**2025** 2 papers](https://md.research.elamur.ai/free/en/authors/philip-h-s-torr/year/2025/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/philip-h-s-torr/year/2023/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Language Model Tokenizers Introduce Unfairness Between Languages](https://md.research.elamur.ai/free/en/papers/petrov-2023-language-model-tokenizers-introduce-unfairness/)** *(2023 · 206 citations)* The authors examine whether language model tokenizers treat different languages equally. They show that inequality arises even before the model receives the text: already at the stage where the text is split into tokens. To compare languages, they propose the notion of tokenizer parity. The same sentence is taken in…
2. **[Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://md.research.elamur.ai/free/en/papers/su-2025-many-heads-are-better-than/)** *(2025 · 40 citations)* Most LLM tools for automated research ideation use a single agent or rely on artificial collaboration setups, such as invented researcher profiles or synthetic co-author networks.
3. **[Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models](https://md.research.elamur.ai/free/en/papers/gao-2025-benchmarking-open-ended-audio-dialogue/)** *(2025 · 12 citations)* Large Audio-Language Models (LALMs) such as GPT-4o can now hold spoken conversations directly with users. Until this work, however, no benchmark tested how well they understand open-ended audio dialogue. Earlier evaluations covered basic audio tasks, audio QA driven by text instructions, or general-purpose chat only.

## All works

57 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. **[Point Transformer ↗](https://doi.org/10.1109/iccv48922.2021.01595) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Hengshuang Zhao et al.*2021 · 2,532 citations*
2. **[MLESAC: A New Robust Estimator with Application to Estimating Image Geometry ↗](https://doi.org/10.1006/cviu.1999.0832) Computer Vision and Image Understanding · no summary yet**Philip H. S. Torr, Andrew Zisserman*1999 · 2,400 citations*
3. **[Staple: Complementary Learners for Real-Time Tracking ↗](https://doi.org/10.1109/cvpr.2016.156) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Luca Bertinetto et al.*2016 · 1,791 citations*
4. **[Fast Online Object Tracking and Segmentation: A Unifying Approach ↗](https://doi.org/10.1109/cvpr.2019.00142) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Qiang Wang et al.*2019 · 1,513 citations*
5. **[Deeply Supervised Salient Object Detection with Short Connections ↗](https://doi.org/10.1109/cvpr.2017.563) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Qibin Hou et al.*2017 · 1,175 citations*
6. **[DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents ↗](https://doi.org/10.1109/cvpr.2017.233) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Namhoon Lee et al.*2017 · 1,085 citations*
7. **[Struck: Structured Output Tracking with Kernels ↗](https://doi.org/10.1109/tpami.2015.2509974) IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yet**Sam Hare et al.*2015 · 998 citations*
8. **[GA-Net: Guided Aggregation Net for End-To-End Stereo Matching ↗](https://doi.org/10.1109/cvpr.2019.00027) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Feihu Zhang et al.*2019 · 835 citations*
9. **[3D model acquisition from extended image sequences ↗](https://doi.org/10.1007/3-540-61123-1_181) Lecture notes in computer science · no summary yet**Paul A. Beardsley, P. Torr, Andrew Zisserman*1996 · 388 citations*
10. **[Managing extreme AI risks amid rapid progress ↗](https://doi.org/10.1126/science.adn0117) Science · no summary yet**Yoshua Bengio et al.*2024 · 382 citations*
11. **[OBJ CUT ↗](https://doi.org/10.1109/cvpr.2005.249) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Manish Kumar, Philip H. S. Torr, Andrew Zisserman*2005 · 329 citations*
12. **[PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer ↗](https://doi.org/10.1109/cvpr52688.2022.00415) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Zitong Yu et al.*2022 · 301 citations*
13. **[Hand detection using multiple proposals ↗](https://doi.org/10.5244/c.25.75) British Machine Vision Conference (BMVC) · no summary yet**Arpit Mittal, Andrew Zisserman, Philip H. S. Torr*2011 · 269 citations*
14. **[Learning feed-forward one-shot learners ↗](https://openalex.org/W2962810352) neural information processing systems · no summary yet**Luca Bertinetto et al.*2016 · 256 citations*
15. **[Pixelwise Instance Segmentation with a Dynamically Instantiated Network ↗](https://doi.org/10.1109/cvpr.2017.100) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Anurag Arnab, Philip H. S. Torr*2017 · 228 citations*
16. **[Language Model Tokenizers Introduce Unfairness Between Languages](https://md.research.elamur.ai/free/en/papers/petrov-2023-language-model-tokenizers-introduce-unfairness/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Aleksandar Petrov, Emanuele La Malfa, Philip H. S. Torr, et al.*2023 · 206 citations*
17. **[Robust parameterization and computation of the trifocal tensor ↗](https://doi.org/10.1016/s0262-8856(97)00010-3) Image and Vision Computing · no summary yet**Philip H. S. Torr, Andrew Zisserman*1997 · 206 citations*
18. **[Using Hindsight to Anchor Past Knowledge in Continual Learning ↗](https://doi.org/10.1609/aaai.v35i8.16861) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Arslan Chaudhry et al.*2021 · 200 citations*
19. **[End-to-End Representation Learning for Correlation Filter Based Tracking ↗](https://doi.org/10.1109/cvpr.2017.531) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Jack Valmadre et al.*2017 · 198 citations*
20. **[Robust computation and parametrization of multiple view relations ↗](https://doi.org/10.1109/iccv.1998.710798) International Conference on Computer Vision · no summary yet**Philip H. S. Torr, Andrew Zisserman*1998 · 171 citations*
21. **[The Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences ↗](https://doi.org/10.1023/a:1008140928553) International Journal of Computer Vision · no summary yet**Philip H. S. Torr, Andrew W Fitzgibbon, Andrew Zisserman*1999 · 156 citations*
22. **[Exploiting uncertainty in regression forests for accurate camera relocalization ↗](https://doi.org/10.1109/cvpr.2015.7299069) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Julien Valentin et al.*2015 · 154 citations*
23. **[MOSE: A New Dataset for Video Object Segmentation in Complex Scenes ↗](https://doi.org/10.1109/iccv51070.2023.01850) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Henghui Ding et al.*2023 · 148 citations*
24. **[Robust Detection of Degenerate Configurations while Estimating the Fundamental Matrix ↗](https://doi.org/10.1006/cviu.1997.0559) Computer Vision and Image Understanding · no summary yet**Philip H. S. Torr, Andrew Zisserman, Stephen J. Maybank*1997 · 121 citations*
25. **[Deep Deterministic Uncertainty: A New Simple Baseline ↗](https://doi.org/10.1109/cvpr52729.2023.02336) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Jishnu Mukhoti et al.*2023 · 118 citations*

[See all 57 works by Philip H. S. Torr →](https://md.research.elamur.ai/free/en/authors/philip-h-s-torr/works/)

## Co-authors here

10 co-authors with a page, the most papers together first.

- [Biqing Qi](https://md.research.elamur.ai/free/en/authors/biqing-qi/)
- [Bowen Zhou](https://md.research.elamur.ai/free/en/authors/bowen-zhou/)
- [Hui Li](https://md.research.elamur.ai/free/en/authors/hui-li/)
- [Jindong Gu](https://md.research.elamur.ai/free/en/authors/jindong-gu/)
- [Ke Xu](https://md.research.elamur.ai/free/en/authors/ke-xu/)
- [Kuofeng Gao](https://md.research.elamur.ai/free/en/authors/kuofeng-gao/)
- [Qi Wu](https://md.research.elamur.ai/free/en/authors/qi-wu/)
- [Shu-Tao Xia](https://md.research.elamur.ai/free/en/authors/shu-tao-xia/)
- [Wanli Ouyang](https://md.research.elamur.ai/free/en/authors/wanli-ouyang/)
- [Zhenfei Yin](https://md.research.elamur.ai/free/en/authors/zhenfei-yin/)

## Venues

Where their works here were published, the most works first, with the editions of those that have a page.

- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×16
- Lecture notes in computer science ×5
- IEEE/CVF International Conference on Computer Vision (ICCV) ×4
- [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×3: [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) ×2
- British Machine Vision Conference (BMVC) ×3
- IEEE International Conference on Computer Vision (ICCV) ×3
- International Conference on Computer Vision ×3
- Computer Vision and Image Understanding ×2
- IEEE Transactions on Pattern Analysis and Machine Intelligence ×2
- International Journal of Computer Vision ×2
- [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/): [NeurIPS 2023](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2023/)
- Image and Vision Computing

## Cited by

Papers of our library cite their works 549 times (of the 149,439 papers whose bibliographies we read); [74 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/philip-h-s-torr/cited-by/).

Updated 1 November 2026