| Associative hierarchical crfs for object class image segmentation L Ladicky, C Russell, P Kohli, PHS Torr Computer Vision, 2009 IEEE 12th International Conference on, 739-746, 2009 | 591* | 2009 |
| Graph cut based inference with co-occurrence statistics L Ladicky, C Russell, P Kohli, P Torr Computer Vision–ECCV 2010, 239-253, 2010 | 360 | 2010 |
| What, where and how many? combining object detectors and crfs Ľ Ladický, P Sturgess, K Alahari, C Russell, PHS Torr Computer Vision–ECCV 2010, 424-437, 2010 | 337 | 2010 |
| Joint optimization for object class segmentation and dense stereo reconstruction L Ladický, P Sturgess, C Russell, S Sengupta, Y Bastanlar, W Clocksin, ... International Journal of Computer Vision 100 (2), 122-133, 2012 | 182 | 2012 |
| Looking beyond the image: Unsupervised learning for object saliency and detection P Siva, C Russell, T Xiang, L Agapito Proceedings of the IEEE conference on computer vision and pattern …, 2013 | 132 | 2013 |
| In Defence of Negative Mining for Annotating Weakly Labelled Data P Siva, C Russell, T Xiang ECCV, 2012 | 111 | 2012 |
| Associative hierarchical random fields Ľ Ladický, C Russell, P Kohli, PHS Torr IEEE transactions on pattern analysis and machine intelligence 36 (6), 1056-1077, 2014 | 85 | 2014 |
| Lifting from the deep: Convolutional 3d pose estimation from a single image D Tome, C Russell, L Agapito CVPR 2017 Proceedings, 2500-2509, 2017 | 84 | 2017 |
| Counterfactual fairness MJ Kusner, J Loftus, C Russell, R Silva Advances in Neural Information Processing Systems, 4066-4076, 2017 | 71 | 2017 |
| F-formation detection: Individuating free-standing conversational groups in images F Setti, C Russell, C Bassetti, M Cristani PloS one 10 (5), e0123783, 2015 | 63 | 2015 |
| Inference methods for crfs with co-occurrence statistics Ľ Ladický, C Russell, P Kohli, PHS Torr International journal of computer vision 103 (2), 213-225, 2013 | 63 | 2013 |
| Energy based multiple model fitting for non-rigid structure from motion C Russell, J Fayad, L Agapito Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on …, 2011 | 59 | 2011 |
| Video pop-up: Monocular 3d reconstruction of dynamic scenes C Russell, R Yu, L Agapito European conference on computer vision, 583-598, 2014 | 58 | 2014 |
| Veegan: Reducing mode collapse in gans using implicit variational learning A Srivastava, L Valkov, C Russell, MU Gutmann, C Sutton Advances in Neural Information Processing Systems, 3308-3318, 2017 | 45 | 2017 |
| Automated Articulated Structure and 3D Shape Recovery from Point Correspondences J Fayad, C Russell, L Agapito ICCV, 2011 | 45 | 2011 |
| Direct, dense, and deformable: Template-based non-rigid 3d reconstruction from rgb video R Yu, C Russell, NDF Campbell, L Agapito Proceedings of the IEEE International Conference on Computer Vision, 918-926, 2015 | 36 | 2015 |
| Dense Multibody Motion Estimation and Reconstruction from a Handheld Camera A Roussos, C Russell, R Garg, L Agapito ISMAR, 2012 | 34 | 2012 |
| Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR S Wachter, B Mittelstadt, C Russell Harvard Journal of Law & Technology 31 (2), 2018 | 31 | 2018 |
| Semi-supervised learning using an unsupervised atlas N Pitelis, C Russell, L Agapito Joint European Conference on Machine Learning and Knowledge Discovery in …, 2014 | 29 | 2014 |
| Efficient piecewise learning for conditional random fields K Alahari, C Russell, PHS Torr Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, 895-901, 2010 | 29 | 2010 |
Philip TorrProfessor, University of OxfordVerified email at eng.ox.ac.uk