H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science H-index 107 Citations 57,909 403 World Ranking 108 National Ranking 4

Research.com Recognitions

Awards & Achievements

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

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Computer vision
  • Machine learning

Philip H. S. Torr focuses on Artificial intelligence, Computer vision, Segmentation, Pattern recognition and Machine learning. His work in Image segmentation, Video tracking, Deep learning, Object detection and Artificial neural network is related to Artificial intelligence. His work deals with themes such as Robustness and Source code, which intersect with Computer vision.

His research on Segmentation also deals with topics like

  • Pixel which connect with Image,
  • Convolutional neural network, which have a strong connection to Enhanced Data Rates for GSM Evolution. His studies deal with areas such as Estimation theory, Statistics, Bayesian probability and Outlier as well as Pattern recognition. His work on MNIST database as part of general Machine learning study is frequently connected to Generalization, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.

His most cited work include:

  • Struck: Structured output tracking with kernels (1626 citations)
  • MLESAC: A New Robust Estimator with Application to Estimating Image Geometry (1613 citations)
  • Fully-Convolutional Siamese Networks for Object Tracking (1512 citations)

What are the main themes of his work throughout his whole career to date?

His primary areas of investigation include Artificial intelligence, Computer vision, Pattern recognition, Segmentation and Machine learning. His Object, Image segmentation, Image, Artificial neural network and Pixel investigations are all subjects of Artificial intelligence research. His Computer vision study frequently draws connections between adjacent fields such as Robustness.

His Pattern recognition research is multidisciplinary, relying on both Cognitive neuroscience of visual object recognition and Feature. His Segmentation study incorporates themes from CRFS, Conditional random field, Pascal and Inference. Philip H. S. Torr has researched Machine learning in several fields, including Structure, Probabilistic logic and Generative grammar.

He most often published in these fields:

  • Artificial intelligence (76.84%)
  • Computer vision (32.54%)
  • Pattern recognition (26.84%)

What were the highlights of his more recent work (between 2018-2021)?

  • Artificial intelligence (76.84%)
  • Machine learning (20.04%)
  • Pattern recognition (26.84%)

In recent papers he was focusing on the following fields of study:

His primary areas of study are Artificial intelligence, Machine learning, Pattern recognition, Artificial neural network and Segmentation. His study connects Computer vision and Artificial intelligence. His Machine learning research incorporates elements of Generative grammar and Training set.

His research integrates issues of Encoder, Pascal, Invariant and Pooling in his study of Pattern recognition. The concepts of his Artificial neural network study are interwoven with issues in Algorithm, Formal verification, Theoretical computer science, Pruning and Initialization. The various areas that Philip H. S. Torr examines in his Segmentation study include Object, Object detection, Minimum bounding box and Pixel.

Between 2018 and 2021, his most popular works were:

  • Fast Online Object Tracking and Segmentation: A Unifying Approach (367 citations)
  • The sixth visual object tracking VOT2018 challenge results (299 citations)
  • Res2Net: A New Multi-Scale Backbone Architecture (265 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Computer vision
  • Machine learning

Philip H. S. Torr mostly deals with Artificial intelligence, Computer vision, Segmentation, Pattern recognition and Artificial neural network. His Artificial intelligence research incorporates themes from Machine learning and Source code. His Computer vision research includes elements of Set and Robustness.

His work in the fields of Segmentation, such as Image segmentation, overlaps with other areas such as Fusion. His Pattern recognition research includes themes of Pascal, Iterative reconstruction and Existential quantification. His research investigates the connection with Artificial neural network and areas like Algorithm which intersect with concerns in Differentiable function.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Top Publications

Struck: Structured Output Tracking with Kernels

Sam Hare;Stuart Golodetz;Amir Saffari;Vibhav Vineet.
IEEE Transactions on Pattern Analysis and Machine Intelligence (2016)

2697 Citations

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

Philip H. S. Torr;Andrew Zisserman.
Computer Vision and Image Understanding (2000)

2163 Citations

Conditional Random Fields as Recurrent Neural Networks

Shuai Zheng;Sadeep Jayasumana;Bernardino Romera-Paredes;Vibhav Vineet.
international conference on computer vision (2015)

2121 Citations

Struck: Structured output tracking with kernels

Sam Hare;Amir Saffari;Philip H. S. Torr.
international conference on computer vision (2011)

1759 Citations

Fully-Convolutional Siamese Networks for Object Tracking

Luca Bertinetto;Jack Valmadre;João F. Henriques;Andrea Vedaldi.
european conference on computer vision (2016)

1462 Citations

The Visual Object Tracking VOT2016 Challenge Results

Matej Kristan;Aleš Leonardis;Jiři Matas;Michael Felsberg.
european conference on computer vision (2016)

1423 Citations

The Visual Object Tracking VOT2017 Challenge Results

Matej Kristan;Ales Leonardis;Jiri Matas;Michael Felsberg.
international conference on computer vision (2017)

1389 Citations

BING: Binarized Normed Gradients for Objectness Estimation at 300fps

Ming-Ming Cheng;Ziming Zhang;Wen-Yan Lin;Philip Torr.
computer vision and pattern recognition (2014)

1132 Citations

Staple: Complementary Learners for Real-Time Tracking

Luca Bertinetto;Jack Valmadre;Stuart Golodetz;Ondrej Miksik.
computer vision and pattern recognition (2016)

1013 Citations

The Development and Comparison of Robust Methodsfor Estimating the Fundamental Matrix

P. H. S. Torr;D. W. Murray.
International Journal of Computer Vision (1997)

994 Citations

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us

Top Scientists Citing Philip H. S. Torr

Marc Pollefeys

Marc Pollefeys

ETH Zurich

Publications: 137

Luc Van Gool

Luc Van Gool

ETH Zurich

Publications: 118

Huchuan Lu

Huchuan Lu

Dalian University of Technology

Publications: 114

Ming-Hsuan Yang

Ming-Hsuan Yang

University of California, Merced

Publications: 111

Andrew Zisserman

Andrew Zisserman

University of Oxford

Publications: 110

Carsten Rother

Carsten Rother

Heidelberg University

Publications: 94

Pushmeet Kohli

Pushmeet Kohli

Google (United States)

Publications: 91

Ling Shao

Ling Shao

Inception Institute of Artificial Intelligence

Publications: 76

Chunhua Shen

Chunhua Shen

University of Adelaide

Publications: 70

Raquel Urtasun

Raquel Urtasun

University of Toronto

Publications: 70

Shuicheng Yan

Shuicheng Yan

National University of Singapore

Publications: 69

Ian Reid

Ian Reid

University of Adelaide

Publications: 68

Ming-Ming Cheng

Ming-Ming Cheng

Nankai University

Publications: 65

Liang Lin

Liang Lin

Sun Yat-sen University

Publications: 64

Roberto Cipolla

Roberto Cipolla

University of Cambridge

Publications: 63

Something went wrong. Please try again later.