| Photo-realistic single image super-resolution using a generative adversarial network C Ledig, L Theis, F Huszár, J Caballero, A Cunningham, A Acosta, ... Proceedings of the IEEE conference on computer vision and pattern …, 2017 | 11629 | 2017 |
| Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network W Shi, J Caballero, F Huszár, J Totz, AP Aitken, R Bishop, D Rueckert, ... Proceedings of the IEEE conference on computer vision and pattern …, 2016 | 6047 | 2016 |
| Lossy image compression with compressive autoencoders L Theis, W Shi, A Cunningham, F Huszár arXiv preprint arXiv:1703.00395, 2017 | 1087 | 2017 |
| Bayesian active learning for classification and preference learning N Houlsby, F Huszár, Z Ghahramani, M Lengyel arXiv preprint arXiv:1112.5745, 2011 | 699 | 2011 |
| Amortised MAP Inference for Image Super-resolution C Kaae Sřnderby, J Caballero, L Theis, W Shi, F Huszár ArXiv e-prints, arXiv: 1610.04490, 2016 | 489* | 2016 |
| How (not) to train your generative model: Scheduled sampling, likelihood, adversary? F Huszár arXiv preprint arXiv:1511.05101, 2015 | 308 | 2015 |
| Faster gaze prediction with dense networks and fisher pruning L Theis, I Korshunova, A Tejani, F Huszár arXiv preprint arXiv:1801.05787, 2018 | 199 | 2018 |
| Algorithmic amplification of politics on Twitter F Huszár, SI Ktena, C O’Brien, L Belli, A Schlaikjer, M Hardt Proceedings of the National Academy of Sciences 119 (1), e2025334119, 2022 | 189 | 2022 |
| Adaptive Bayesian quantum tomography F Huszár, NMT Houlsby Physical Review A 85 (5), 052120, 2012 | 182 | 2012 |
| Is the deconvolution layer the same as a convolutional layer? W Shi, J Caballero, L Theis, F Huszar, A Aitken, C Ledig, Z Wang arXiv preprint arXiv:1609.07009, 2016 | 171 | 2016 |
| Collaborative Gaussian processes for preference learning N Houlsby, F Huszar, Z Ghahramani, JM Hernández-lobato Advances in Neural Information Processing Systems, 2096-2104, 2012 | 146 | 2012 |
| Variational inference using implicit distributions F Huszár arXiv preprint arXiv:1702.08235, 2017 | 145 | 2017 |
| Note on the quadratic penalties in elastic weight consolidation F Huszár Proceedings of the National Academy of Sciences 115 (11), E2496-E2497, 2018 | 130 | 2018 |
| Optimally-weighted herding is Bayesian quadrature F Huszár, D Duvenaud arXiv preprint arXiv:1204.1664, 2012 | 107 | 2012 |
| Experimental adaptive Bayesian tomography KS Kravtsov, SS Straupe, R I. V., NMT Houlsby, H Ferenc, SP Kulik Physical Review A 87 (6), 062122, 2013 | 99 | 2013 |
| Training end-to-end video processes Z Wang, RD Bishop, F Huszar, L Theis US Patent 10,666,962, 2020 | 93 | 2020 |
| Approximate inference for the loss-calibrated Bayesian S Lacoste–Julien, F Huszár, Z Ghahramani Proceedings of the Fourteenth International Conference on Artificial …, 2011 | 81 | 2011 |
| Photo-realistic single image super-resolution using a generative adversarial network. arXiv 2016 C Ledig, L Theis, F Huszar, J Caballero, A Cunningham, A Acosta, ... arXiv preprint arXiv:1609.04802, 2016 | 70 | 2016 |
| Cognitive tomography reveals complex, task-independent mental representations NMT Houlsby, F Huszár, MM Ghassemi, G Orbán, DM Wolpert, M Lengyel Current Biology 23 (21), 2169-2175, 2013 | 62 | 2013 |
| Addressing delayed feedback for continuous training with neural networks in CTR prediction SI Ktena, A Tejani, L Theis, PK Myana, D Dilipkumar, F Huszár, S Yoo, ... Proceedings of the 13th ACM conference on recommender systems, 187-195, 2019 | 55 | 2019 |
Wenzhe Shi（施闻哲）ML@SharechatEmail verificata su sharechat.co
