| Face tracking and recognition with visual constraints in real-world videos M Kim, S Kumar, V Pavlovic, H Rowley 2008 IEEE Conference on Computer Vision and Pattern Recognition, 1-8, 2008 | 633 | 2008 |
| Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference SX Hu, D Li, J Stühmer, M Kim, TM Hospedales Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 235 | 2022 |
| Fisher SAM: Information Geometry and Sharpness Aware Minimisation M Kim, D Li, SX Hu, T Hospedales International Conference on Machine Learning, 11148-11161, 2022 | 80 | 2022 |
| Structured output ordinal regression for dynamic facial emotion intensity prediction M Kim, V Pavlovic European conference on computer vision, 649-662, 2010 | 72 | 2010 |
| Gaussian Processes Multiple Instance Learning. M Kim, F De la Torre ICML, 535-542, 2010 | 66 | 2010 |
| Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach M Kim, P Sahu, B Gholami, V Pavlovic IEEE Conference on Computer Vision and Pattern Recognition, 2019 | 54 | 2019 |
| Relevance Factor VAE: Learning and Identifying Disentangled Factors M Kim, Y Wang, P Sahu, V Pavlovic arXiv preprint arXiv:1902.01568, 2019 | 36 | 2019 |
| Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement M Kim, Y Wang, P Sahu, V Pavlovic International Conference on Computer Vision (ICCV), 2979-2987, 2019 | 33 | 2019 |
| Discriminative learning for dynamic state prediction M Kim, V Pavlovic IEEE Transactions on Pattern Analysis and Machine Intelligence 31 (10), 1847 …, 2009 | 30 | 2009 |
| Central subspace dimensionality reduction using covariance operators M Kim, V Pavlovic IEEE transactions on pattern analysis and machine intelligence 33 (4), 657-670, 2011 | 27 | 2011 |
| Dimensionality reduction using covariance operator inverse regression M Kim, V Pavlovic 2008 IEEE Conference on Computer Vision and Pattern Recognition, 1-8, 2008 | 27 | 2008 |
| Semi-supervised learning of hidden conditional random fields for time-series classification M Kim Neurocomputing 119, 339-349, 2013 | 25 | 2013 |
| FedL2P: Federated Learning to Personalize R Lee, M Kim, D Li, X Qiu, T Hospedales, F Huszár, N Lane Advances in Neural Information Processing Systems 36, 2024 | 24 | 2024 |
| Object tracking in video with visual constraints M Kim, S Kumar, HA Rowley US Patent 8,477,998, 2013 | 23 | 2013 |
| Discriminative learning of mixture of bayesian network classifiers for sequence classification M Kim, V Pavlovic 2006 IEEE Computer Society Conference on Computer Vision and Pattern …, 2006 | 23 | 2006 |
| Model-induced term-weighting schemes for text classification HK Kim, M Kim Applied Intelligence 45 (1), 30-43, 2016 | 22 | 2016 |
| Large margin cost-sensitive learning of conditional random fields M Kim Pattern Recognition 43 (10), 3683-3692, 2010 | 22 | 2010 |
| Correlation-based incremental visual tracking M Kim Pattern Recognition 45 (3), 1050-1060, 2012 | 21 | 2012 |
| Mixtures of conditional random fields for improved structured output prediction M Kim IEEE transactions on neural networks and learning systems 28 (5), 1233-1240, 2017 | 20 | 2017 |
| Object tracking in video with visual constraints M Kim, S Kumar, HA Rowley US Patent 8,085,982, 2011 | 20 | 2011 |
Timothy M. HospedalesProfessor, University of Edinburgh; Samsung AI ResearchEmail verificata su ed.ac.uk
