Publications

2018

Rodrigo de Bem, Anurag Arnab, Stuart Golodetz, Michael Sapienza, Philip H.S. Torr, Deep Fully-Connected Part-Based Models for Human Pose Estimation, Asian Conference on Machine Learning (ACML), 2018. (Best paper runner-up) [pdf - supplementary]

Harkirat S. Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip H. S. Torr, Incremental Tube Construction for Human Action Detection, British Machine Vision Conference, 2018. [pdf - video]

2017

Gurkirt Singh, Suman Saha, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin, Online Real-time Multiple Spatiotemporal Action Localisation and Prediction, International Conference on Computer Vision (ICCV), 2017. [pdf - code - poster - video]

Saumya Jetley*, Michael Sapienza*, Stuart Golodetz and Philip H. S. Torr, Straight to Shapes: Real-time Detection of Encoded Shapes, Computer Vision and Pattern Recognition (CVPR), 2017. [pdf - poster - project page - video - code - updated-results]

Fabio Cuzzolin, Michael Sapienza, Patrick Esser, Suman Saha, Miss Marloes Franssen, Johnny Collett, Helen Dawes, Metric learning for Parkinsonian identification from IMU gait measurements, Gait & Posture, 2017. [pdf]

2016

Cristian Roman, Michael Sapienza, Peter Ball, Shumao Ou, Fabio Cuzzolin, Philip H.S. Torr, Heterogeneous Wireless System Testbed for Remote Image Processing in Automated Vehicles, IEEE/IET Int. Symposium on Communication Systems, Networks and Digital Signal Processing, 2016. (oral) [pdf]

Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H.S. Torr , Fabio Cuzzlion, Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos, British Machine Vision Conference, 2016. [pdf - project page - video - code]

2015

Stuart Golodetz, Michael Sapienza, Julien Valentin, Vibhav Vineet, Ming-Ming Cheng, Victor Adrian Prisacariu, Olaf Kaehler, Carl Yuheng Ren, Anurag Arnab, Stephen Hicks, David W. Murray, Shahram Izadi, Philip H.S. Torr, SemanticPaint: Interactive Segmentation and Learning of 3D Worlds, Proceeding ACM SIGGRAPH 2015 Emerging Technologies, 2015. (live demo) [pdf - project page - code - facebook] (live demo) Media coverage: BBC Click - BBC Click best bits - BBC - BBC Asia - GIzmodo - Engadget

Anurag Arnab, Michael Sapienza, Stuart Golodetz, Julien Valentin, Ondrej Miksik, Shahram Izadi, Philip H.S. Torr, Joint Object-Material Category Segmentation from Audio-Visual Cues, British Machine Vision Conference, 2015. [pdf - project page - dataset]

2014

Michael Sapienza, Fabio Cuzzolin, Philip H.S. Torr, Learning discriminative space-time action parts from weakly labelled videos, International Journal of Computer Vision, 2014. [pdf - project page - video - BibTex]

Fabio Cuzzolin, Michael Sapienza, Learning pullback HMM distances, IEEE Trans Pattern Analysis and Machine Intelligence, 2014. [pdf - supplementary - BibTex]

2013

Wenjuan Gong, Michael Sapienza, Fabio Cuzzolin, Fisher tensor decomposition for unconstrained gait recognition, ECML/PKDD Workshop, 2013. [pdf - BibTex]

Michael Sapienza, Miles Hansard, Radu Horaud, Real-time visuomotor update of an active binocular head, Autonomous Robots, 34(1):35–45, 2013. [pdf - video - BibTex]

2012

Michael Sapienza, Fabio Cuzzolin, Philip H.S. Torr, Learning discriminative space-time actions from weakly labelled videos, British Machine Vision Conference, 2012. (oral) [pdf - project page - slides - poster - talk - video - BibTex]

Michael Sapienza, Kenneth P. Camilleri, A generative traversability model for monocular robot self-guidance, 9th Int. Conf. on Informatics in Control, Automation and Robotics, 2012. (oral) [pdf - code - dataset - slides - video - BibTex]

Talks:

SemanticPaint: A Framework for the Interactive segmentation of 3D Scenes, CVSSP Seminar, University of Surrey, November 2015. [slides]

Reconfigurable bag-of-word models, VGG Reading Group, March 2013. [slides]

Learning discriminative space-time actions from weakly labelled videos, Toshiba Research Europe CVG, February 2013. [slides]

Technical Reports:

Laurynas Miksys, Saumya Jetley, Michael Sapienza, Stuart Golodetz, Philip H.S. Torr, Straight to Shapes++: Real-time Instance Segmentation Made More Accurate, Department of Engineering Science, University of Oxford, 2019. [pdf]

Victor Adrian Prisacariu, Olaf Kähler, Stuart Golodetz, Michael Sapienza, Tommaso Cavallari, Philip H S Torr, David W Murray, InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure, Department of Engineering Science, University of Oxford, 2017. [pdf]

Stuart Golodetz, Michael Sapienza, Julien Valentin, Vibhav Vineet, Ming-Ming Cheng, Victor Adrian Prisacariu, Olaf Kaehler, Carl Yuheng Ren, Anurag Arnab, Stephen Hicks, David W. Murray, Shahram Izadi, Philip H.S. Torr, SemanticPaint: A Framework for the Interactive segmentation of 3D Scenes, Department of Engineering Science, University of Oxford, 2015. [pdf - project page - BibTex]

Michael Sapienza, Fabio Cuzzolin, Philip H.S. Torr, Feature sampling and partitioning for visual vocabulary generation on large action classification datasets, Department of Computing and Communications Technology, Oxford Brookes University, and Department of Engineering Science, Univerisity of Oxford, 2014. [pdf - BibTex]

Michael Sapienza, Kenneth P. Camilleri, Fasthpe: A recipe for quick head pose estimation, Department of Systems & Control, University of Malta, 2011. [pdf - code - video - BibTex]

Posters:

Learning discriminative space-time actions from weakly labelled videos, M. Sapienza, F. Cuzzolin, P. H.S. Torr, VRML 2012 Summer School, Visual Recognition & Machine Learning. (poster prize)

Real-time monocular robot guidance, M. Sapienza, K.P. Camilleri, BMVA 2010 Summer School, Computer Vision.

Theses:

Recognising and localising human actions, M. Sapienza, Ph.D Dissertation, Oxford Brookes University, 2014. [RADAR research archive]

Vision for Autonomous Mobile Robot Guidance, M. Sapienza, M.Sc (by research) Dissertation, University of Malta, 2011.

Real-time head pose estimation in the 6 degrees of freedom, M. Sapienza, B.Eng (HONS) Dissertation, University of Malta, 2009.

In the media:

SemanticPaint Improving Computer Vision, BBC World News, 2015.

Tracking 3D objects in real-time using active stereo vision, Sabine Hauert, RoboHub, 2012.

A robot that guides itself, M. Sapienza, K. P. Camilleri, Times of Malta, 2011.