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

On the Robustness of Quality Measures for GANs

Jan 31, 2022
Motasem Alfarra, Juan C. Pérez, Anna Frühstück, Philip H. S. Torr, Peter Wonka, Bernard Ghanem

Figure 1 for On the Robustness of Quality Measures for GANs

Figure 2 for On the Robustness of Quality Measures for GANs

Figure 3 for On the Robustness of Quality Measures for GANs

Figure 4 for On the Robustness of Quality Measures for GANs

* 20 pages, 16 figures, 5 tables

Access Paper or Ask Questions

LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Dec 04, 2021
Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr

Figure 1 for LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Figure 2 for LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Figure 3 for LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Figure 4 for LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

* 10 pages, 8 figures

Access Paper or Ask Questions

Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

Nov 15, 2021
Jiyang Qi, Yan Gao, Yao Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge Belongie, Alan Yuille, Philip H. S. Torr, Song Bai

Figure 1 for Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

Figure 2 for Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

Figure 3 for Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

Figure 4 for Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

* Accepted by NeurIPS 2021 Datasets and Benchmarks Track. arXiv admin note: text overlap with arXiv:2102.01558

Access Paper or Ask Questions

Detecting and Quantifying Malicious Activity with Simulation-based Inference

Oct 07, 2021
Andrew Gambardella, Bogdan State, Naeemullah Khan, Leo Tsourides, Philip H. S. Torr, Atılım Güneş Baydin

Figure 1 for Detecting and Quantifying Malicious Activity with Simulation-based Inference

Figure 2 for Detecting and Quantifying Malicious Activity with Simulation-based Inference

Figure 3 for Detecting and Quantifying Malicious Activity with Simulation-based Inference

* Short version, appeared at ICML workshop on Socially Responsible Machine Learning 2021

Access Paper or Ask Questions

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

Figure 1 for ANCER: Anisotropic Certification via Sample-wise Volume Maximization

Figure 2 for ANCER: Anisotropic Certification via Sample-wise Volume Maximization

Figure 3 for ANCER: Anisotropic Certification via Sample-wise Volume Maximization

Figure 4 for ANCER: Anisotropic Certification via Sample-wise Volume Maximization

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

Access Paper or Ask Questions