Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Philip Torr

Philip Torr

Implicit Communication as Minimum Entropy Coupling


Jul 17, 2021
Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl, Luisa Zintgraf, Philip Torr, Shimon Whiteson, Jakob Foerster

Figure 1 for Implicit Communication as Minimum Entropy Coupling
Figure 2 for Implicit Communication as Minimum Entropy Coupling
Figure 3 for Implicit Communication as Minimum Entropy Coupling
Figure 4 for Implicit Communication as Minimum Entropy Coupling

  Access Paper or Ask Questions

Visual Parser: Representing Part-whole Hierarchies with Transformers


Jul 13, 2021
Shuyang Sun*, Xiaoyu Yue*, Song Bai, Philip Torr

Figure 1 for Visual Parser: Representing Part-whole Hierarchies with Transformers
Figure 2 for Visual Parser: Representing Part-whole Hierarchies with Transformers
Figure 3 for Visual Parser: Representing Part-whole Hierarchies with Transformers
Figure 4 for Visual Parser: Representing Part-whole Hierarchies with Transformers

  Access Paper or Ask Questions

Large-scale Unsupervised Semantic Segmentation


Jun 06, 2021
Shang-Hua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, Philip Torr

Figure 1 for Large-scale Unsupervised Semantic Segmentation
Figure 2 for Large-scale Unsupervised Semantic Segmentation
Figure 3 for Large-scale Unsupervised Semantic Segmentation
Figure 4 for Large-scale Unsupervised Semantic Segmentation

  Access Paper or Ask Questions

Point Transformer


Dec 16, 2020
Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun

Figure 1 for Point Transformer
Figure 2 for Point Transformer
Figure 3 for Point Transformer
Figure 4 for Point Transformer

  Access Paper or Ask Questions

Learning to Sample the Most Useful Training Patches from Images


Nov 24, 2020
Shuyang Sun, Liang Chen, Gregory Slabaugh, Philip Torr

Figure 1 for Learning to Sample the Most Useful Training Patches from Images
Figure 2 for Learning to Sample the Most Useful Training Patches from Images
Figure 3 for Learning to Sample the Most Useful Training Patches from Images
Figure 4 for Learning to Sample the Most Useful Training Patches from Images

  Access Paper or Ask Questions

Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation


Oct 28, 2020
Angira Sharma, Naeemullah Khan, Ganesh Sundaramoorthi, Philip Torr

Figure 1 for Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
Figure 2 for Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
Figure 3 for Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
Figure 4 for Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation

  Access Paper or Ask Questions

Diagnosing and Preventing Instabilities in Recurrent Video Processing


Oct 17, 2020
Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip Torr, Ales Leonardis, Gregory Slabaugh

Figure 1 for Diagnosing and Preventing Instabilities in Recurrent Video Processing
Figure 2 for Diagnosing and Preventing Instabilities in Recurrent Video Processing
Figure 3 for Diagnosing and Preventing Instabilities in Recurrent Video Processing
Figure 4 for Diagnosing and Preventing Instabilities in Recurrent Video Processing

  Access Paper or Ask Questions

HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking


Sep 29, 2020
Jonathon Luiten, Aljosa Osep, Patrick Dendorfer, Philip Torr, Andreas Geiger, Laura Leal-Taixe, Bastian Leibe

Figure 1 for HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Figure 2 for HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Figure 3 for HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Figure 4 for HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
* Pre-print. Accepted for Publication in the International Journal of Computer Vision, 19 August 2020. Code is available at https://github.com/JonathonLuiten/HOTA-metrics 
  Access Paper or Ask Questions

Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection


Aug 26, 2020
Carlo Biffi, Steven McDonagh, Philip Torr, Ales Leonardis, Sarah Parisot

Figure 1 for Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
Figure 2 for Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
Figure 3 for Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
Figure 4 for Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
* Accepted at ECCV 2020. Camera-ready version and Appendices 
  Access Paper or Ask Questions

Simulation-Based Inference for Global Health Decisions


May 14, 2020
Christian Schroeder de Witt, Bradley Gram-Hansen, Nantas Nardelli, Andrew Gambardella, Rob Zinkov, Puneet Dokania, N. Siddharth, Ana Belen Espinosa-Gonzalez, Ara Darzi, Philip Torr, Atılım Güneş Baydin

Figure 1 for Simulation-Based Inference for Global Health Decisions

  Access Paper or Ask Questions

Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control


Mar 18, 2020
Christian Schroeder de Witt, Bei Peng, Pierre-Alexandre Kamienny, Philip Torr, Wendelin Böhmer, Shimon Whiteson

Figure 1 for Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control
Figure 2 for Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control
Figure 3 for Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control
Figure 4 for Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control

  Access Paper or Ask Questions

Using Hindsight to Anchor Past Knowledge in Continual Learning


Feb 19, 2020
Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip Torr, David Lopez-Paz

Figure 1 for Using Hindsight to Anchor Past Knowledge in Continual Learning
Figure 2 for Using Hindsight to Anchor Past Knowledge in Continual Learning
Figure 3 for Using Hindsight to Anchor Past Knowledge in Continual Learning
Figure 4 for Using Hindsight to Anchor Past Knowledge in Continual Learning

  Access Paper or Ask Questions

Global Texture Enhancement for Fake Face Detection in the Wild


Feb 01, 2020
Zhengzhe Liu, Xiaojuan Qi, Jiaya Jia, Philip Torr

Figure 1 for Global Texture Enhancement for Fake Face Detection in the Wild
Figure 2 for Global Texture Enhancement for Fake Face Detection in the Wild
Figure 3 for Global Texture Enhancement for Fake Face Detection in the Wild
Figure 4 for Global Texture Enhancement for Fake Face Detection in the Wild

  Access Paper or Ask Questions

Domain-invariant Stereo Matching Networks


Nov 29, 2019
Feihu Zhang, Xiaojuan Qi, Ruigang Yang, Victor Prisacariu, Benjamin Wah, Philip Torr

Figure 1 for Domain-invariant Stereo Matching Networks
Figure 2 for Domain-invariant Stereo Matching Networks
Figure 3 for Domain-invariant Stereo Matching Networks
Figure 4 for Domain-invariant Stereo Matching Networks

  Access Paper or Ask Questions

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale


Jul 08, 2019
Atılım Güneş Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Lawrence Meadows, Jialin Liu, Andreas Munk, Saeid Naderiparizi, Bradley Gram-Hansen, Gilles Louppe, Mingfei Ma, Xiaohui Zhao, Philip Torr, Victor Lee, Kyle Cranmer, Prabhat, Frank Wood

Figure 1 for Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Figure 2 for Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Figure 3 for Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Figure 4 for Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
* 14 pages, 8 figures 
  Access Paper or Ask Questions

Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation


Jun 20, 2019
Tommaso Cavallari, Luca Bertinetto, Jishnu Mukhoti, Philip Torr, Stuart Golodetz

Figure 1 for Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation
Figure 2 for Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation
Figure 3 for Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation
Figure 4 for Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation
* Tommaso Cavallari and Stuart Golodetz contributed equally to this paper 
  Access Paper or Ask Questions

Res2Net: A New Multi-scale Backbone Architecture


Apr 02, 2019
Shang-Hua Gao, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, Philip Torr

Figure 1 for Res2Net: A New Multi-scale Backbone Architecture
Figure 2 for Res2Net: A New Multi-scale Backbone Architecture
Figure 3 for Res2Net: A New Multi-scale Backbone Architecture
Figure 4 for Res2Net: A New Multi-scale Backbone Architecture

  Access Paper or Ask Questions

Long-term Tracking in the Wild: A Benchmark


Aug 10, 2018
Jack Valmadre, Luca Bertinetto, João F. Henriques, Ran Tao, Andrea Vedaldi, Arnold Smeulders, Philip Torr, Efstratios Gavves

Figure 1 for Long-term Tracking in the Wild: A Benchmark
Figure 2 for Long-term Tracking in the Wild: A Benchmark
Figure 3 for Long-term Tracking in the Wild: A Benchmark
Figure 4 for Long-term Tracking in the Wild: A Benchmark
* To appear at ECCV 2018 
  Access Paper or Ask Questions

Prototypical Priors: From Improving Classification to Zero-Shot Learning


Apr 25, 2018
Saumya Jetley, Bernardino Romera-Paredes, Sadeep Jayasumana, Philip Torr

Figure 1 for Prototypical Priors: From Improving Classification to Zero-Shot Learning
Figure 2 for Prototypical Priors: From Improving Classification to Zero-Shot Learning
Figure 3 for Prototypical Priors: From Improving Classification to Zero-Shot Learning
Figure 4 for Prototypical Priors: From Improving Classification to Zero-Shot Learning
* 12 Pages, 6 Figures, 2 Tables, in British Machine Vision Conference (BMVC), 2015 
  Access Paper or Ask Questions

Deeply supervised salient object detection with short connections


Mar 16, 2018
Qibin Hou, Ming-Ming Cheng, Xiao-Wei Hu, Ali Borji, Zhuowen Tu, Philip Torr

Figure 1 for Deeply supervised salient object detection with short connections
Figure 2 for Deeply supervised salient object detection with short connections
Figure 3 for Deeply supervised salient object detection with short connections
Figure 4 for Deeply supervised salient object detection with short connections
* Q. Hou, M. M. Cheng, X. Hu, A. Borji, Z. Tu and P. H. S. Torr, "Deeply Supervised Salient Object Detection with Short Connections," IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018 
 * IEEE TPAMI 2018 (IEEE CVPR 2017) 
  Access Paper or Ask Questions

A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials


Jan 02, 2018
MÃ¥ns Larsson, Anurag Arnab, Fredrik Kahl, Shuai Zheng, Philip Torr

Figure 1 for A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
Figure 2 for A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
Figure 3 for A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
Figure 4 for A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
* Presented at EMMCVPR 2017 conference 
  Access Paper or Ask Questions

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction


Aug 24, 2017
Gurkirt Singh, Suman Saha, Michael Sapienza, Philip Torr, Fabio Cuzzolin

Figure 1 for Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
Figure 2 for Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
Figure 3 for Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
Figure 4 for Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
* 10 pages 3 figures, ICCV 2017, Added link to new annotations of ucf101-24 
  Access Paper or Ask Questions

Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation


Apr 09, 2017
Qinbin Hou, Puneet Kumar Dokania, Daniela Massiceti, Yunchao Wei, Ming-Ming Cheng, Philip Torr

Figure 1 for Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
Figure 2 for Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
Figure 3 for Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
Figure 4 for Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation

  Access Paper or Ask Questions

Higher Order Conditional Random Fields in Deep Neural Networks


Jul 29, 2016
Anurag Arnab, Sadeep Jayasumana, Shuai Zheng, Philip Torr

Figure 1 for Higher Order Conditional Random Fields in Deep Neural Networks
Figure 2 for Higher Order Conditional Random Fields in Deep Neural Networks
Figure 3 for Higher Order Conditional Random Fields in Deep Neural Networks
Figure 4 for Higher Order Conditional Random Fields in Deep Neural Networks
* ECCV 2016 
  Access Paper or Ask Questions

Staple: Complementary Learners for Real-Time Tracking


Apr 13, 2016
Luca Bertinetto, Jack Valmadre, Stuart Golodetz, Ondrej Miksik, Philip Torr

Figure 1 for Staple: Complementary Learners for Real-Time Tracking
Figure 2 for Staple: Complementary Learners for Real-Time Tracking
Figure 3 for Staple: Complementary Learners for Real-Time Tracking
Figure 4 for Staple: Complementary Learners for Real-Time Tracking
* To appear in CVPR 2016 
  Access Paper or Ask Questions

Learning to Navigate the Energy Landscape


Mar 18, 2016
Julien Valentin, Angela Dai, Matthias Nießner, Pushmeet Kohli, Philip Torr, Shahram Izadi, Cem Keskin

Figure 1 for Learning to Navigate the Energy Landscape
Figure 2 for Learning to Navigate the Energy Landscape
Figure 3 for Learning to Navigate the Energy Landscape
Figure 4 for Learning to Navigate the Energy Landscape

  Access Paper or Ask Questions

Joint Object-Material Category Segmentation from Audio-Visual Cues


Jan 10, 2016
Anurag Arnab, Michael Sapienza, Stuart Golodetz, Julien Valentin, Ondrej Miksik, Shahram Izadi, Philip Torr

Figure 1 for Joint Object-Material Category Segmentation from Audio-Visual Cues
Figure 2 for Joint Object-Material Category Segmentation from Audio-Visual Cues
Figure 3 for Joint Object-Material Category Segmentation from Audio-Visual Cues
Figure 4 for Joint Object-Material Category Segmentation from Audio-Visual Cues
* Published in British Machine Vision Conference (BMVC) 2015 
  Access Paper or Ask Questions