Philip Torr

is this you? claim profile

Chief Scientific Advisor at FiveAI since 2016, Director and co-Founder at OxSight since 2016, Professor at University of Oxford since 2013, Professor at Oxford Brookes University from 2004-2013, Researcher at Microsoft 1997-2004.

Learning to Sample the Most Useful Training Patches from Images

Some image restoration tasks like demosaicing require difficult training...
11/24/2020 ∙ by Shuyang Sun, et al. ∙ 0 ∙ share

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

In this paper we present a novel loss function, called class-agnostic se...
10/28/2020 ∙ by Angira Sharma, et al. ∙ 5 ∙ share

read it
Diagnosing and Preventing Instabilities in Recurrent Video Processing

Recurrent models are becoming a popular choice for video enhancement tas...
10/10/2020 ∙ by Thomas Tanay, et al. ∙ 0 ∙ share

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

Multi-Object Tracking (MOT) has been notoriously difficult to evaluate. ...
09/16/2020 ∙ by Jonathon Luiten, et al. ∙ 15 ∙ share

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

Object detection has witnessed significant progress by relying on large,...
08/21/2020 ∙ by Carlo Biffi, et al. ∙ 0 ∙ share

read it
Simulation-Based Inference for Global Health Decisions

The COVID-19 pandemic has highlighted the importance of in-silico epidem...
05/14/2020 ∙ by Christian Schroeder de Witt, et al. ∙ 11 ∙ share

read it
Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control

Deep multi-agent reinforcement learning (MARL) holds the promise of auto...
03/14/2020 ∙ by Christian Schroeder de Witt, et al. ∙ 13 ∙ share

read it
Using Hindsight to Anchor Past Knowledge in Continual Learning

In continual learning, the learner faces a stream of data whose distribu...
02/19/2020 ∙ by Arslan Chaudhry, et al. ∙ 0 ∙ share

read it
Global Texture Enhancement for Fake Face Detection in the Wild

Generative Adversarial Networks (GANs) can generate realistic fake face ...
02/01/2020 ∙ by Zhengzhe Liu, et al. ∙ 24 ∙ share

read it
Domain-invariant Stereo Matching Networks

State-of-the-art stereo matching networks have difficulties in generaliz...
11/29/2019 ∙ by Feihu Zhang, et al. ∙ 4 ∙ share

read it
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale

Probabilistic programming languages (PPLs) are receiving widespread atte...
07/08/2019 ∙ by Atılım Güneş Baydin, et al. ∙ 2 ∙ share

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

Many applications require a camera to be relocalised online, without exp...
06/20/2019 ∙ by Tommaso Cavallari, et al. ∙ 2 ∙ share

read it
Res2Net: A New Multi-scale Backbone Architecture

Representing features at multiple scales is of great importance for nume...
04/02/2019 ∙ by Shang-Hua Gao, et al. ∙ 0 ∙ share

read it
Long-term Tracking in the Wild: A Benchmark

We introduce a new video dataset and benchmark to assess single-object t...
03/26/2018 ∙ by Jack Valmadre, et al. ∙ 0 ∙ share

read it
Learning Arbitrary Pairwise Potentials in CRFs for Semantic Segmentation

Are we using the right potential functions in the Conditional Random Fie...
01/24/2017 ∙ by Måns Larsson, et al. ∙ 0 ∙ share

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

We consider the task of learning a classifier for semantic segmentation ...
12/07/2016 ∙ by Qinbin Hou, et al. ∙ 0 ∙ share

read it
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction

We present a deep-learning framework for real-time multiple spatio-tempo...
11/25/2016 ∙ by Gurkirt Singh, et al. ∙ 0 ∙ share

read it
Deeply supervised salient object detection with short connections

Recent progress on saliency detection is substantial, benefiting mostly ...
11/15/2016 ∙ by Qibin Hou, et al. ∙ 0 ∙ share

read it
Learning to Navigate the Energy Landscape

In this paper, we present a novel and efficient architecture for address...
03/18/2016 ∙ by Julien Valentin, et al. ∙ 0 ∙ share

read it
Joint Object-Material Category Segmentation from Audio-Visual Cues

It is not always possible to recognise objects and infer material proper...
01/10/2016 ∙ by Anurag Arnab, et al. ∙ 0 ∙ share

read it
Staple: Complementary Learners for Real-Time Tracking

Correlation Filter-based trackers have recently achieved excellent perfo...
12/04/2015 ∙ by Luca Bertinetto, et al. ∙ 0 ∙ share

read it
Prototypical Priors: From Improving Classification to Zero-Shot Learning

Recent works on zero-shot learning make use of side information such as ...
12/03/2015 ∙ by Saumya Jetley, et al. ∙ 0 ∙ share

read it
Efficient Semidefinite Branch-and-Cut for MAP-MRF Inference

We propose a Branch-and-Cut (B&C) method for solving general MAP-MRF inf...
04/20/2014 ∙ by Peng Wang, et al. ∙ 0 ∙ share

read it
ImageSpirit: Verbal Guided Image Parsing

Humans describe images in terms of nouns and adjectives while algorithms...
10/16/2013 ∙ by Ming-Ming Cheng, et al. ∙ 0 ∙ share

read it

Philip Torr

Featured Co-authors

Chunhua Shen

Ming-Hsuan Yang

Peng Wang

Anton van den Hengel

Andrea Vedaldi

Pushmeet Kohli

Matthias Nießner

Ming-Ming Cheng

Shimon Whiteson

Frank Wood

Ali Borji

Learning to Sample the Most Useful Training Patches from Images

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

Diagnosing and Preventing Instabilities in Recurrent Video Processing

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

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

Simulation-Based Inference for Global Health Decisions

Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control

Using Hindsight to Anchor Past Knowledge in Continual Learning

Global Texture Enhancement for Fake Face Detection in the Wild

Domain-invariant Stereo Matching Networks

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale

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

Res2Net: A New Multi-scale Backbone Architecture

Long-term Tracking in the Wild: A Benchmark

Learning Arbitrary Pairwise Potentials in CRFs for Semantic Segmentation

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

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction

Deeply supervised salient object detection with short connections

Learning to Navigate the Energy Landscape

Joint Object-Material Category Segmentation from Audio-Visual Cues

Staple: Complementary Learners for Real-Time Tracking

Prototypical Priors: From Improving Classification to Zero-Shot Learning

Efficient Semidefinite Branch-and-Cut for MAP-MRF Inference

ImageSpirit: Verbal Guided Image Parsing