| Videolstm convolves, attends and flows for action recognition Z Li, K Gavrilyuk, E Gavves, M Jain, CGM Snoek Computer Vision and Image Understanding 166, 41-50, 2018 | 575 | 2018 |
| Better exploiting motion for better action recognition M Jain, H Jégou, P Bouthemy Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on …, 2013 | 520 | 2013 |
| Action localization with tubelets from motion M Jain, J Van Gemert, H Jégou, P Bouthemy, CGM Snoek Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, 740-747, 2014 | 333 | 2014 |
| What do 15,000 object categories tell us about classifying and localizing actions? M Jain, JC Van Gemert, CGM Snoek Proceedings of the IEEE conference on computer vision and pattern …, 2015 | 223 | 2015 |
| Objects2action: Classifying and localizing actions without any video example M Jain, JC Van Gemert, T Mensink, CGM Snoek Proceedings of the IEEE international conference on computer vision, 4588-4596, 2015 | 185 | 2015 |
| APT: Action localization proposals from dense trajectories. JC Van Gemert, M Jain, E Gati, CGM Snoek BMVC 2, 4, 2015 | 180 | 2015 |
| Asymmetric hamming embedding: taking the best of our bits for large scale image search M Jain, H Jégou, P Gros proceedings of the 19th ACM international conference on multimedia, 1441-1444, 2011 | 91 | 2011 |
| Cross-attentional audio-visual fusion for weakly-supervised action localization JT Lee, M Jain, H Park, S Yun International conference on learning representations, 2020 | 64 | 2020 |
| University of amsterdam at thumos challenge 2014 M Jain, J van Gemert, CGM Snoek ECCV THUMOS Challenge 2014, 2014 | 62 | 2014 |
| Actionbytes: Learning from trimmed videos to localize actions M Jain, A Ghodrati, CGM Snoek Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2020 | 59 | 2020 |
| MediaMill at TRECVID 2014: Searching Concepts, Objects, Instances and Events in Video. CGM Snoek, KEA van de Sande, D Fontijne, AH Habibian, M Jain, ... TRECVID 1 (2), 3, 2013 | 45 | 2013 |
| Action localization in sequential data with attention proposals from a recurrent network J Mihir, LI Zhenyang, E Gavves, CGM Snoek US Patent App. 15/250,755, 2017 | 41 | 2017 |
| Hamming embedding similarity-based image classification M Jain, R Benmokhtar, H Jégou, P Gros Proceedings of the 2nd ACM International Conference on Multimedia Retrieval, 1-8, 2012 | 35 | 2012 |
| Guess where? actor-supervision for spatiotemporal action localization V Escorcia, CD Dao, M Jain, B Ghanem, C Snoek Computer Vision and Image Understanding 192, 102886, 2020 | 32 | 2020 |
| Efficient action recognition via dynamic knowledge propagation H Kim, M Jain, JT Lee, S Yun, F Porikli Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 25 | 2021 |
| Recurrent networks with motion-based attention for video understanding LI Zhenyang, E Gavves, J Mihir, CGM Snoek US Patent 10,049,279, 2018 | 23 | 2018 |
| Tubelets: Unsupervised action proposals from spatiotemporal super-voxels M Jain, J Van Gemert, H Jégou, P Bouthemy, CGM Snoek International Journal of Computer Vision 124, 287-311, 2017 | 22 | 2017 |
| Motion-augmented self-training for video recognition at smaller scale K Gavrilyuk, M Jain, I Karmanov, CGM Snoek Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 18 | 2021 |
| Timegate: Conditional gating of segments in long-range activities N Hussein, M Jain, BE Bejnordi arXiv preprint arXiv:2004.01808, 2020 | 16 | 2020 |
| Video analysis with convolutional attention recurrent neural networks LI Zhenyang, E Gavves, J Mihir, CGM Snoek US Patent 9,830,709, 2017 | 15 | 2017 |
Cees G. M. SnoekProfessor of Computer Science, University of AmsterdamVerified email at uva.nl
