| Context encoders: Feature learning by inpainting D Pathak, P Krahenbuhl, J Donahue, T Darrell, AA Efros Proceedings of the IEEE conference on computer vision and pattern …, 2016 | 6752 | 2016 |
| Objects as points X Zhou, D Wang, P Krähenbühl arXiv preprint arXiv:1904.07850, 2019 | 4477 | 2019 |
| Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials P Krähenbühl, V Koltun NIPS, 2011 | 4154 | 2011 |
| Adversarial feature learning J Donahue, P Krähenbühl, T Darrell arXiv preprint arXiv:1605.09782, 2016 | 2542 | 2016 |
| Saliency filters: Contrast based filtering for salient region detection F Perazzi, P Krähenbühl, Y Pritch, A Hornung 2012 IEEE conference on computer vision and pattern recognition, 733-740, 2012 | 2373 | 2012 |
| Center-based 3d object detection and tracking T Yin, X Zhou, P Krähenbühl CVPR, 2021 | 1780 | 2021 |
| Generative visual manipulation on the natural image manifold JY Zhu, P Krähenbühl, E Shechtman, AA Efros Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The …, 2016 | 1623 | 2016 |
| Tracking Objects as Points X Zhou, V Koltun, P Krähenbühl ECCV, 2020 | 1307 | 2020 |
| Bottom-up object detection by grouping extreme and center points X Zhou, J Zhuo, P Krahenbuhl Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019 | 1179 | 2019 |
| Sampling matters in deep embedding learning CY Wu, R Manmatha, AJ Smola, P Krähenbühl ICCV 2017, 2017 | 1121 | 2017 |
| Constrained convolutional neural networks for weakly supervised segmentation D Pathak, P Krahenbuhl, T Darrell Proceedings of the IEEE international conference on computer vision, 1796-1804, 2015 | 781 | 2015 |
| Long-term feature banks for detailed video understanding CY Wu, C Feichtenhofer, H Fan, K He, P Krahenbuhl, R Girshick Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019 | 590 | 2019 |
| Detecting twenty-thousand classes using image-level supervision X Zhou, R Girdhar, A Joulin, P Krähenbühl, I Misra European Conference on Computer Vision, 350-368, 2022 | 580 | 2022 |
| Learning by cheating D Chen, B Zhou, V Koltun, P Krähenbühl Conference on Robot Learning, 66-75, 2019 | 519 | 2019 |
| Geodesic object proposals P Krähenbühl, V Koltun Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland …, 2014 | 473 | 2014 |
| Learning dense correspondence via 3d-guided cycle consistency T Zhou, P Krahenbuhl, M Aubry, Q Huang, AA Efros Proceedings of the IEEE conference on computer vision and pattern …, 2016 | 440 | 2016 |
| Compressed video action recognition CY Wu, M Zaheer, H Hu, R Manmatha, AJ Smola, P Krähenbühl Proceedings of the IEEE conference on computer vision and pattern …, 2018 | 408 | 2018 |
| Video compression through image interpolation CY Wu, N Singhal, P Krahenbuhl Proceedings of the European conference on computer vision (ECCV), 416-431, 2018 | 388 | 2018 |
| A system for retargeting of streaming video P Krähenbühl, M Lang, A Hornung, M Gross ACM SIGGRAPH Asia 2009 papers, 1-10, 2009 | 309 | 2009 |
| Probabilistic two-stage detection X Zhou, V Koltun, P Krähenbühl arXiv preprint arXiv:2103.07461, 2021 | 302 | 2021 |
Vladlen KoltunDistinguished Scientist, AppleVerified email at apple.com
