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 H. S. Torr

Philip H. S. Torr

University of Oxford

ANCER: Anisotropic Certification via Sample-wise Volume Maximization


Jul 20, 2021
Francisco Eiras, Motasem Alfarra, M. Pawan Kumar, Philip H. S. Torr, Puneet K. Dokania, Bernard Ghanem, Adel Bibi

* First two authors and the last one contributed equally to this work 

  Access Paper or Ask Questions

Do Different Tracking Tasks Require Different Appearance Models?


Jul 05, 2021
Zhongdao Wang, Hengshuang Zhao, Ya-Li Li, Shengjin Wang, Philip H. S. Torr, Luca Bertinetto


  Access Paper or Ask Questions

DeformRS: Certifying Input Deformations with Randomized Smoothing


Jul 02, 2021
Motasem Alfarra, Adel Bibi, Naeemullah Khan, Philip H. S. Torr, Bernard Ghanem

* First two authors contributed equally to this work 

  Access Paper or Ask Questions

Learning Multimodal VAEs through Mutual Supervision


Jul 01, 2021
Tom Joy, Yuge Shi, Philip H. S. Torr, Tom Rainforth, Sebastian M. Schmon, N. Siddharth


  Access Paper or Ask Questions

KL Guided Domain Adaptation


Jun 14, 2021
A. Tuan Nguyen, Toan Tran, Yarin Gal, Philip H. S. Torr, Atılım Güneş Baydin


  Access Paper or Ask Questions

You Never Cluster Alone


Jun 03, 2021
Yuming Shen, Ziyi Shen, Menghan Wang, Jie Qin, Philip H. S. Torr, Ling Shao

* Preprint 

  Access Paper or Ask Questions

Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning


May 12, 2021
Yansong Tang, Zhenyu Jiang, Zhenda Xie, Yue Cao, Zheng Zhang, Philip H. S. Torr, Han Hu

* Technical report 

  Access Paper or Ask Questions

Gradient Matching for Domain Generalization


Apr 20, 2021
Yuge Shi, Jeffrey Seely, Philip H. S. Torr, N. Siddharth, Awni Hannun, Nicolas Usunier, Gabriel Synnaeve


  Access Paper or Ask Questions

Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition


Apr 14, 2021
Alessandro De Palma, Rudy Bunel, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar

* Submitted for review to JMLR. This is an extended version of our paper in the UAI-20 conference (arXiv:2002.10410) 

  Access Paper or Ask Questions

Cloth Interactive Transformer for Virtual Try-On


Apr 12, 2021
Bin Ren, Hao Tang, Fanyang Meng, Runwei Ding, Ling Shao, Philip H. S. Torr, Nicu Sebe

* 11 pages, 6 figures, 

  Access Paper or Ask Questions

Combating Adversaries with Anti-Adversaries


Mar 26, 2021
Motasem Alfarra, Juan C. Pérez, Ali Thabet, Adel Bibi, Philip H. S. Torr, Bernard Ghanem

* 15 pages, 5 figures, 7 tables 

  Access Paper or Ask Questions

Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty


Feb 23, 2021
Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal


  Access Paper or Ask Questions

Shape-Tailored Deep Neural Networks


Feb 16, 2021
Naeemullah Khan, Angira Sharma, Ganesh Sundaramoorthi, Philip H. S. Torr


  Access Paper or Ask Questions

Occluded Video Instance Segmentation


Feb 08, 2021
Jiyang Qi, Yan Gao, Yao Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge Belongie, Alan Yuille, Philip H. S. Torr, Song Bai

* 10 pages, 11 figures 

  Access Paper or Ask Questions

Scaling the Convex Barrier with Sparse Dual Algorithms


Jan 26, 2021
Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H. S. Torr, M. Pawan Kumar

* Previous version: published at ICLR 2021. This extended version: submitted to JMLR 

  Access Paper or Ask Questions

Scaling the Convex Barrier with Active Sets


Jan 14, 2021
Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H. S. Torr, M. Pawan Kumar

* Published at ICLR 2021 

  Access Paper or Ask Questions

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers


Dec 31, 2020
Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip H. S. Torr, Li Zhang

* project page at https://fudan-zvg.github.io/SETR/ 

  Access Paper or Ask Questions

On Batch Normalisation for Approximate Bayesian Inference


Dec 24, 2020
Jishnu Mukhoti, Puneet K. Dokania, Philip H. S. Torr, Yarin Gal


  Access Paper or Ask Questions

Multi-shot Temporal Event Localization: a Benchmark


Dec 17, 2020
Xiaolong Liu, Yao Hu, Song Bai, Fei Ding, Xiang Bai, Philip H. S. Torr

* Project page at https://songbai.site/muses 

  Access Paper or Ask Questions

GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation


Dec 13, 2020
Xiaojuan Qi, Zhengzhe Liu, Renjie Liao, Philip H. S. Torr, Raquel Urtasun, Jiaya Jia

* TPAMI 2020. Code available: https://github.com/xjqi/GeoNet 

  Access Paper or Ask Questions

Data Dependent Randomized Smoothing


Dec 08, 2020
Motasem Alfarra, Adel Bibi, Philip H. S. Torr, Bernard Ghanem

* First two authors contributed equally to this work 

  Access Paper or Ask Questions

Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?


Nov 18, 2020
Christian Schroeder de Witt, Tarun Gupta, Denys Makoviichuk, Viktor Makoviychuk, Philip H. S. Torr, Mingfei Sun, Shimon Whiteson


  Access Paper or Ask Questions

Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation


Oct 23, 2020
Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz

* NeurIPS 2020 

  Access Paper or Ask Questions

Continual Learning in Low-rank Orthogonal Subspaces


Oct 22, 2020
Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr

* NeurIPS, 2020 
* The paper is accepted at NeurIPS'20 

  Access Paper or Ask Questions

Bipartite Graph Reasoning GANs for Person Image Generation


Aug 20, 2020
Hao Tang, Song Bai, Philip H. S. Torr, Nicu Sebe

* 13 pages, 6 figures, accepted to BMVC 2020 as an oral paper, fix typos 

  Access Paper or Ask Questions

AutoSimulate: (Quickly) Learning Synthetic Data Generation


Aug 16, 2020
Harkirat Singh Behl, Atılım Güneş Baydin, Ran Gal, Philip H. S. Torr, Vibhav Vineet

* European Conference on Computer Vision (ECCV) 2020 
* ECCV 2020 

  Access Paper or Ask Questions