| Conditional Random Fields as Recurrent Neural Networks S Zheng, S Jayasumana, B Romera-Paredes, V Vineet, Z Su, D Du, ... IEEE International Conference on Computer Vision (ICCV), 2015 | 3304 | 2015 |
| Long-Tail Learning via Logit Adjustment AK Menon, S Jayasumana, AS Rawat, H Jain, A Veit, S Kumar ICLR, 2021 | 722 | 2021 |
| Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices S Jayasumana, R Hartley, M Salzmann, H Li, M Harandi Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 73-80, 2013 | 358 | 2013 |
| Higher order conditional random fields in deep neural networks A Arnab, S Jayasumana, S Zheng, PHS Torr Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The …, 2016 | 285 | 2016 |
| Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels S Jayasumana, R Hartley, M Salzmann, H Li, M Harandi IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015 | 281 | 2015 |
| Conditional random fields meet deep neural networks for semantic segmentation: Combining probabilistic graphical models with deep learning for structured prediction A Arnab, S Zheng, S Jayasumana, B Romera-Paredes, M Larsson, ... IEEE Signal Processing Magazine 35 (1), 37-52, 2018 | 171 | 2018 |
| Expanding the family of grassmannian kernels: An embedding perspective MT Harandi, M Salzmann, S Jayasumana, R Hartley, H Li Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland …, 2014 | 114 | 2014 |
| Prototypical Priors: From Improving Classification to Zero-Shot Learning S Jetley, B Romera-Paredes, S Jayasumana, P Torr The British Machine Vision Conference (BMVC), 2015 | 55 | 2015 |
| A framework for shape analysis via hilbert space embedding S Jayasumana, M Salzmann, H Li, M Harandi Proceedings of the IEEE International Conference on Computer Vision, 1249-1256, 2013 | 44 | 2013 |
| Optimizing Over Radial Kernels on Compact Manifolds S Jayasumana, R Hartley, M Salzmann, H Li, M Harandi Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, 2014 | 43 | 2014 |
| Rethinking FID: Towards a Better Evaluation Metric for Image Generation S Jayasumana, S Ramalingam, A Veit, D Glasner, A Chakrabarti, ... IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024 | 36 | 2024 |
| Higher order potentials in end-to-end trainable conditional random fields A Arnab, S Jayasumana, S Zheng, PHS Torr arXiv preprint arXiv:1511.08119 2, 2015 | 33 | 2015 |
| Combining multiple manifold-valued descriptors for improved object recognition S Jayasumana, R Hartley, M Salzmann, H Li, M Harandi 2013 International Conference on Digital Image Computing: Techniques and …, 2013 | 28 | 2013 |
| In defense of dual-encoders for neural ranking A Menon, S Jayasumana, AS Rawat, S Kim, S Reddi, S Kumar International Conference on Machine Learning, 15376-15400, 2022 | 23 | 2022 |
| Disentangling sampling and labeling bias for learning in large-output spaces AS Rawat, AK Menon, W Jitkrittum, S Jayasumana, F Yu, S Reddi, ... International conference on machine learning, 8890-8901, 2021 | 11 | 2021 |
| Bipartite Conditional Random Fields for Panoptic Segmentation S Jayasumana, K Ranasinghe, M Jayawardhana, S Liyanaarachchi, ... British Machine Vision Conference (BMVC), 2020 | 10 | 2020 |
| Kernelized classification in deep networks S Jayasumana, S Ramalingam, S Kumar arXiv preprint arXiv:2012.09607, 2020 | 9 | 2020 |
| Kernels on Riemannian manifolds S Jayasumana, R Hartley, M Salzmann Riemannian computing in computer vision, 45-67, 2016 | 8 | 2016 |
| Embeddistill: A geometric knowledge distillation for information retrieval S Kim, AS Rawat, M Zaheer, S Jayasumana, V Sadhanala, W Jitkrittum, ... arXiv preprint arXiv:2301.12005, 2023 | 5 | 2023 |
| Do we need neural collapse? learning diverse features for fine-grained and long-tail classification J Ma, C You, SJ Reddi, S Jayasumana, H Jain, F Yu, SF Chang, S Kumar | 2 | 2023 |
Sanjiv KumarGoogle Fellow, VP, Google ResearchVerified email at google.com
