| Going deeper with convolutions C Szegedy, W Liu, Y Jia, P Sermanet, S Reed, D Anguelov, D Erhan, ... Proceedings of the IEEE conference on computer vision and pattern …, 2015 | 17436 | 2015 |
| Batch normalization: Accelerating deep network training by reducing internal covariate shift S Ioffe, C Szegedy arXiv preprint arXiv:1502.03167, 2015 | 14083 | 2015 |
| Ssd: Single shot multibox detector W Liu, D Anguelov, D Erhan, C Szegedy, S Reed, CY Fu, AC Berg European conference on computer vision, 21-37, 2016 | 5961 | 2016 |
| Rethinking the inception architecture for computer vision C Szegedy, V Vanhoucke, S Ioffe, J Shlens, Z Wojna Proceedings of the IEEE conference on computer vision and pattern …, 2016 | 5814 | 2016 |
| Inception-v4, inception-resnet and the impact of residual connections on learning C Szegedy, S Ioffe, V Vanhoucke, AA Alemi Thirty-First AAAI Conference on Artificial Intelligence, 2017 | 3398 | 2017 |
| Intriguing properties of neural networks C Szegedy, W Zaremba, I Sutskever, J Bruna, D Erhan, I Goodfellow, ... arXiv preprint arXiv:1312.6199, 2013 | 3289 | 2013 |
| Explaining and harnessing adversarial examples IJ Goodfellow, J Shlens, C Szegedy arXiv preprint arXiv:1412.6572, 2014 | 3280 | 2014 |
| Deeppose: Human pose estimation via deep neural networks A Toshev, C Szegedy Proceedings of the IEEE conference on computer vision and pattern …, 2014 | 1288 | 2014 |
| Deep neural networks for object detection C Szegedy, A Toshev, D Erhan Advances in neural information processing systems, 2553-2561, 2013 | 852 | 2013 |
| Scalable object detection using deep neural networks D Erhan, C Szegedy, A Toshev, D Anguelov Proceedings of the IEEE conference on computer vision and pattern …, 2014 | 714 | 2014 |
| Scalable, high-quality object detection C Szegedy, S Reed, D Erhan, D Anguelov, S Ioffe arXiv preprint arXiv:1412.1441, 2014 | 279 | 2014 |
| Training deep neural networks on noisy labels with bootstrapping S Reed, H Lee, D Anguelov, C Szegedy, D Erhan, A Rabinovich arXiv preprint arXiv:1412.6596, 2014 | 259 | 2014 |
| DeepMath-deep sequence models for premise selection G Irving, C Szegedy, AA Alemi, N Eén, F Chollet, J Urban Advances in Neural Information Processing Systems, 2235-2243, 2016 | 90 | 2016 |
| Modular code generation from synchronous block diagrams: modularity vs. code size R Lublinerman, C Szegedy, S Tripakis ACM SIGPLAN Notices 44 (1), 78-89, 2009 | 74 | 2009 |
| Deep network guided proof search S Loos, G Irving, C Szegedy, C Kaliszyk arXiv preprint arXiv:1701.06972, 2017 | 67 | 2017 |
| Object detection using deep neural networks C Szegedy, D Erhan, AT Toshev US Patent 9,275,308, 2016 | 47 | 2016 |
| Holstep: A machine learning dataset for higher-order logic theorem proving C Kaliszyk, F Chollet, C Szegedy arXiv preprint arXiv:1703.00426, 2017 | 32 | 2017 |
| Training a neural network to detect objects in images D Erhan, C Szegedy, D Anguelov US Patent 9,373,057, 2016 | 26 | 2016 |
| Timing optimization by restructuring long combinatorial paths J Werber, D Rautenbach, C Szegedy Proceedings of the 2007 IEEE/ACM international conference on Computer-aided …, 2007 | 22 | 2007 |
| Processing images using deep neural networks C Szegedy, VO Vanhoucke US Patent 9,715,642, 2017 | 17 | 2017 |
Dumitru ErhanStaff Research Scientist, Google BrainVerified email at google.com
