| Learning disentangled representations with semi-supervised deep generative models N Siddharth, B Paige, JW Van de Meent, A Desmaison, N Goodman, ... | 320* | 2018 |
| Recognize human activities from partially observed videos Y Cao, D Barrett, A Barbu, N Siddharth, H Yu, A Michaux, Y Lin, ... Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2013 | 211 | 2013 |
| Video In Sentences Out A Barbu, A Bridge, Z Burchill, D Coroian, S Dickinson, S Fidler, A Michaux, ... UAI, 102-112, 2012 | 174 | 2012 |
| Disentangling Disentanglement in Variational Autoencoders E Mathieu, T Rainforth, N Siddharth, YW Teh International Conference on Machine Learning, 4402-4412, 2019 | 172 | 2019 |
| Structured disentangled representations B Esmaeili, H Wu, S Jain, A Bozkurt, N Siddharth, B Paige, DH Brooks, ... Proceedings of the 22nd International Conference on Artificial Intelligence …, 2018 | 138* | 2018 |
| Variational mixture-of-experts autoencoders for multi-modal deep generative models Y Shi, N Siddharth, B Paige, PHS Torr Advances in Neural Information Processing Systems, 2019 | 108 | 2019 |
| Playing doom with slam-augmented deep reinforcement learning S Bhatti, A Desmaison, O Miksik, N Nardelli, N Siddharth, PHS Torr arXiv preprint arXiv:1612.00380, 2016 | 77 | 2016 |
| Seeing What You’re Told: Sentence-Guided Activity Recognition in Video N Siddharth, A Barbu, JM Siskind Proceedings of the 27th IEEE Conference on Computer Vision and Pattern …, 2014 | 48* | 2014 |
| Revisiting reweighted wake-sleep for models with stochastic control flow TA Le, AR Kosiorek, N Siddharth, YW Teh, F Wood Uncertainty in Artificial Intelligence, 1039-1049, 2020 | 45* | 2020 |
| Gradient matching for domain generalization Y Shi, J Seely, PHS Torr, N Siddharth, A Hannun, N Usunier, G Synnaeve arXiv preprint arXiv:2104.09937, 2021 | 43 | 2021 |
| A compositional framework for grounding language inference, generation, and acquisition in video H Yu, N Siddharth, A Barbu, JM Siskind Journal of Artificial Intelligence Research 52, 601-713, 2015 | 42 | 2015 |
| Seeing is worse than believing: Reading people’s minds better than computer-vision methods recognize actions A Barbu, DP Barrett, W Chen, N Siddharth, C Xiong, JJ Corso, ... European Conference on Computer Vision, 612-627, 2014 | 40 | 2014 |
| FlipDial: A generative model for two-way visual dialogue D Massiceti, N Siddharth, PK Dokania, PHS Torr Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018 | 34 | 2018 |
| Faithful inversion of generative models for effective amortized inference S Webb, A Golinski, R Zinkov, N Siddharth, T Rainforth, YW Teh, F Wood Advances in Neural Information Processing Systems, 3074-3084, 2018 | 32 | 2018 |
| Correlating videos and sentences JM Siskind, A Barbu, N Siddharth, H Yu US Patent 9,183,466, 2015 | 30 | 2015 |
| Learning physically-instantiated game play through visual observation A Barbu, N Siddharth, JM Siskind Robotics and Automation (ICRA), 2010 IEEE International Conference on, 1879-1886, 2010 | 28 | 2010 |
| Simultaneous Object Detection, Tracking, and Event Recognition A Barbu, N Siddharth, A Michaux, JM Siskind Advances in Cognitive Systems 2, 203-220, 2012 | 27 | 2012 |
| Visual dialogue without vision or dialogue D Massiceti, PK Dokania, N Siddharth, PHS Torr arXiv preprint arXiv:1812.06417, 2018 | 23 | 2018 |
| Capturing label characteristics in VAEs T Joy, SM Schmon, PHS Torr, N Siddharth, T Rainforth International Conference On Learning Representations, 2021 | 18* | 2021 |
| Saying what you're looking for: Linguistics meets video search DP Barrett, A Barbu, N Siddharth, JM Siskind IEEE transactions on pattern analysis and machine intelligence 38 (10), 2069 …, 2015 | 17 | 2015 |
Philip TorrProfessor, University of OxfordVerified email at eng.ox.ac.uk
