| Online real-time multiple spatiotemporal action localisation and prediction G Singh, S Saha, M Sapienza, PHS Torr, F Cuzzolin Proceedings of the IEEE international conference on computer vision, 3637-3646, 2017 | 365 | 2017 |
| Deep learning for detecting multiple space-time action tubes in videos S Saha, G Singh, M Sapienza, PHS Torr, F Cuzzolin arXiv preprint arXiv:1608.01529, 2016 | 260 | 2016 |
| Infinitam v3: A framework for large-scale 3d reconstruction with loop closure VA Prisacariu, O Kähler, S Golodetz, M Sapienza, T Cavallari, PHS Torr, ... arXiv preprint arXiv:1708.00783, 2017 | 134 | 2017 |
| Learning discriminative space–time action parts from weakly labelled videos M Sapienza, F Cuzzolin, PHS Torr International journal of computer vision 110, 30-47, 2014 | 131 | 2014 |
| Metric learning for Parkinsonian identification from IMU gait measurements F Cuzzolin, M Sapienza, P Esser, S Saha, MM Franssen, J Collett, ... Gait & posture 54, 127-132, 2017 | 63 | 2017 |
| Straight to shapes: real-time detection of encoded shapes S Jetley, M Sapienza, S Golodetz, PHS Torr Proceedings of the IEEE conference on Computer Vision and Pattern …, 2017 | 63 | 2017 |
| Semantic mapping for low-power augmented reality using dynamic vision sensor M Sapienza, A Gupta, A Bendale, F Fontanel US Patent 10,812,711, 2020 | 47 | 2020 |
| Incremental tube construction for human action detection HS Behl, M Sapienza, G Singh, S Saha, F Cuzzolin, PHS Torr arXiv preprint arXiv:1704.01358, 2017 | 24 | 2017 |
| Camera pose determination and tracking A Gupta, M Sapienza, F Fontanel, AZ Bendale, P Mistry US Patent 10,839,547, 2020 | 23 | 2020 |
| Fisher tensor decomposition for unconstrained gait recognition W Gong, M Sapienza, F Cuzzolin Training 2 (3), 2013 | 21 | 2013 |
| CMOS-assisted inside-out dynamic vision sensor tracking for low power mobile platforms M Sapienza, A Gupta, A Bendale, F Fontanel US Patent 11,202,006, 2021 | 20 | 2021 |
| Deep fully-connected part-based models for human pose estimation R De Bem, A Arnab, S Golodetz, M Sapienza, P Torr Asian conference on machine learning, 327-342, 2018 | 20 | 2018 |
| Fasthpe: A recipe for quick head pose estimation M Sapienza, K Camilleri Systems and Control Engineering, Department of Systems and Control …, 2011 | 20 | 2011 |
| Semanticpaint: A framework for the interactive segmentation of 3d scenes S Golodetz, M Sapienza, JPC Valentin, V Vineet, MM Cheng, A Arnab, ... arXiv preprint arXiv:1510.03727, 2015 | 19 | 2015 |
| Feature sampling and partitioning for visual vocabulary generation on large action classification datasets M Sapienza, F Cuzzolin, PHS Torr arXiv preprint arXiv:1405.7545, 2014 | 19 | 2014 |
| Camera pose and plane estimation using active markers and a dynamic vision sensor F Fontanel, A Gupta, M Sapienza, AZ Bendale, P Mistry US Patent 10,529,074, 2020 | 17 | 2020 |
| Joint object-material category segmentation from audio-visual cues A Arnab, M Sapienza, S Golodetz, J Valentin, O Miksik, S Izadi, P Torr arXiv preprint arXiv:1601.02220, 2016 | 16 | 2016 |
| Learning pullback HMM distances F Cuzzolin, M Sapienza IEEE transactions on pattern analysis and machine intelligence 36 (7), 1483-1489, 2013 | 16 | 2013 |
| Semanticpaint: interactive segmentation and learning of 3d worlds S Golodetz, M Sapienza, JPC Valentin, V Vineet, MM Cheng, ... ACM SIGGRAPH 2015 Emerging Technologies, 1-1, 2015 | 15 | 2015 |
| Real-time visuomotor update of an active binocular head M Sapienza, M Hansard, R Horaud Autonomous Robots 34, 35-45, 2013 | 12 | 2013 |
Philip TorrProfessor, University of Oxford確認したメール アドレス: eng.ox.ac.uk