Picture for Philip H. S. Torr

Philip H. S. Torr

University of Oxford

Learning to Compare: Relation Network for Few-Shot Learning

Add code
Mar 27, 2018
Figure 1 for Learning to Compare: Relation Network for Few-Shot Learning
Figure 2 for Learning to Compare: Relation Network for Few-Shot Learning
Figure 3 for Learning to Compare: Relation Network for Few-Shot Learning
Figure 4 for Learning to Compare: Relation Network for Few-Shot Learning
Viaarxiv icon

Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction

Add code
Mar 27, 2018
Figure 1 for Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction
Figure 2 for Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction
Figure 3 for Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction
Figure 4 for Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction
Viaarxiv icon

WebSeg: Learning Semantic Segmentation from Web Searches

Add code
Mar 27, 2018
Figure 1 for WebSeg: Learning Semantic Segmentation from Web Searches
Figure 2 for WebSeg: Learning Semantic Segmentation from Web Searches
Figure 3 for WebSeg: Learning Semantic Segmentation from Web Searches
Figure 4 for WebSeg: Learning Semantic Segmentation from Web Searches
Viaarxiv icon

Devon: Deformable Volume Network for Learning Optical Flow

Add code
Feb 20, 2018
Figure 1 for Devon: Deformable Volume Network for Learning Optical Flow
Figure 2 for Devon: Deformable Volume Network for Learning Optical Flow
Figure 3 for Devon: Deformable Volume Network for Learning Optical Flow
Viaarxiv icon

Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices

Add code
Feb 20, 2018
Figure 1 for Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices
Figure 2 for Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices
Figure 3 for Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices
Figure 4 for Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices
Viaarxiv icon

Learning Disentangled Representations with Semi-Supervised Deep Generative Models

Add code
Nov 13, 2017
Figure 1 for Learning Disentangled Representations with Semi-Supervised Deep Generative Models
Figure 2 for Learning Disentangled Representations with Semi-Supervised Deep Generative Models
Figure 3 for Learning Disentangled Representations with Semi-Supervised Deep Generative Models
Figure 4 for Learning Disentangled Representations with Semi-Supervised Deep Generative Models
Viaarxiv icon

Holistic, Instance-Level Human Parsing

Add code
Sep 11, 2017
Figure 1 for Holistic, Instance-Level Human Parsing
Figure 2 for Holistic, Instance-Level Human Parsing
Figure 3 for Holistic, Instance-Level Human Parsing
Figure 4 for Holistic, Instance-Level Human Parsing
Viaarxiv icon

Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos

Add code
Aug 06, 2017
Figure 1 for Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
Figure 2 for Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
Figure 3 for Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
Figure 4 for Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
Viaarxiv icon

Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation

Add code
Jul 18, 2017
Figure 1 for Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
Figure 2 for Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
Figure 3 for Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
Figure 4 for Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
Viaarxiv icon

Random Forests versus Neural Networks - What's Best for Camera Localization?

Add code
Jul 13, 2017
Figure 1 for Random Forests versus Neural Networks - What's Best for Camera Localization?
Figure 2 for Random Forests versus Neural Networks - What's Best for Camera Localization?
Figure 3 for Random Forests versus Neural Networks - What's Best for Camera Localization?
Figure 4 for Random Forests versus Neural Networks - What's Best for Camera Localization?
Viaarxiv icon