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

Add to Chrome

Add to Firefox

Picture for Philip H. S. Torr

Philip H. S. Torr

Efficient Linear Programming for Dense CRFs

Feb 14, 2017
Thalaiyasingam Ajanthan, Alban Desmaison, Rudy Bunel, Mathieu Salzmann, Philip H. S. Torr, M. Pawan Kumar

Figure 1 for Efficient Linear Programming for Dense CRFs

Figure 2 for Efficient Linear Programming for Dense CRFs

Figure 3 for Efficient Linear Programming for Dense CRFs

Figure 4 for Efficient Linear Programming for Dense CRFs

* 24 pages, 10 figures and 4 tables

Access Paper or Ask Questions

Learning to superoptimize programs - Workshop Version

Dec 04, 2016
Rudy Bunel, Alban Desmaison, M. Pawan Kumar, Philip H. S. Torr, Pushmeet Kohli

Figure 1 for Learning to superoptimize programs - Workshop Version

Figure 2 for Learning to superoptimize programs - Workshop Version

Figure 3 for Learning to superoptimize programs - Workshop Version

Figure 4 for Learning to superoptimize programs - Workshop Version

* Workshop version for the NIPS NAMPI Workshop. Extended version at arXiv:1611.01787

Access Paper or Ask Questions

Inducing Interpretable Representations with Variational Autoencoders

Nov 22, 2016
N. Siddharth, Brooks Paige, Alban Desmaison, Jan-Willem Van de Meent, Frank Wood, Noah D. Goodman, Pushmeet Kohli, Philip H. S. Torr

Figure 1 for Inducing Interpretable Representations with Variational Autoencoders

Figure 2 for Inducing Interpretable Representations with Variational Autoencoders

Figure 3 for Inducing Interpretable Representations with Variational Autoencoders

* Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems

Access Paper or Ask Questions

Recurrent Instance Segmentation

Oct 24, 2016
Bernardino Romera-Paredes, Philip H. S. Torr

Figure 1 for Recurrent Instance Segmentation

Figure 2 for Recurrent Instance Segmentation

Figure 3 for Recurrent Instance Segmentation

Figure 4 for Recurrent Instance Segmentation

* ECCV 2016. 14th European Conference on Computer Vision
* 14 pages (main paper). 24 pages including references and appendix

Access Paper or Ask Questions

Fully-Convolutional Siamese Networks for Object Tracking

Sep 14, 2016
Luca Bertinetto, Jack Valmadre, João F. Henriques, Andrea Vedaldi, Philip H. S. Torr

Figure 1 for Fully-Convolutional Siamese Networks for Object Tracking

Figure 2 for Fully-Convolutional Siamese Networks for Object Tracking

Figure 3 for Fully-Convolutional Siamese Networks for Object Tracking

Figure 4 for Fully-Convolutional Siamese Networks for Object Tracking

* The first two authors contributed equally, and are listed in alphabetical order. Code available at http://www.robots.ox.ac.uk/~luca/siamese-fc.html

Access Paper or Ask Questions

Fully-Trainable Deep Matching

Sep 12, 2016
James Thewlis, Shuai Zheng, Philip H. S. Torr, Andrea Vedaldi

Figure 1 for Fully-Trainable Deep Matching

Figure 2 for Fully-Trainable Deep Matching

Figure 3 for Fully-Trainable Deep Matching

Figure 4 for Fully-Trainable Deep Matching

* British Machine Vision Conference (BMVC) 2016

Access Paper or Ask Questions