Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Michael Sapienza

Straight to Shapes++: Real-time Instance Segmentation Made More Accurate


May 27, 2019
Laurynas Miksys, Saumya Jetley, Michael Sapienza, Stuart Golodetz, Philip H. S. Torr

* Technical report, 27 pages (12 main, 15 supplementary), 17 figures, 14 tables 

  Access Paper or Ask Questions

Incremental Tube Construction for Human Action Detection


Jul 23, 2018
Harkirat Singh Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip H. S. Torr

* British Machine Vision Conference (BMVC) 2018 

  Access Paper or Ask Questions

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction


Aug 24, 2017
Gurkirt Singh, Suman Saha, Michael Sapienza, Philip Torr, Fabio Cuzzolin

* 10 pages 3 figures, ICCV 2017, Added link to new annotations of ucf101-24 

  Access Paper or Ask Questions

Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos


Aug 06, 2017
Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin

* Typos corrected 

  Access Paper or Ask Questions

InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure


Aug 02, 2017
Victor Adrian Prisacariu, Olaf Kähler, Stuart Golodetz, Michael Sapienza, Tommaso Cavallari, Philip H S Torr, David W Murray

* This article largely supersedes arxiv:1410.0925 (it describes version 3 of the InfiniTAM framework) 

  Access Paper or Ask Questions

Straight to Shapes: Real-time Detection of Encoded Shapes


Jul 05, 2017
Saumya Jetley, Michael Sapienza, Stuart Golodetz, Philip H. S. Torr

* 16 pages including appendix; Published at CVPR 2017 

  Access Paper or Ask Questions

Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos


Aug 04, 2016
Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin

* Accepted by British Machine Vision Conference 2016 

  Access Paper or Ask Questions

Joint Object-Material Category Segmentation from Audio-Visual Cues


Jan 10, 2016
Anurag Arnab, Michael Sapienza, Stuart Golodetz, Julien Valentin, Ondrej Miksik, Shahram Izadi, Philip Torr

* Published in British Machine Vision Conference (BMVC) 2015 

  Access Paper or Ask Questions

SemanticPaint: A Framework for the Interactive Segmentation of 3D Scenes


Oct 13, 2015
Stuart Golodetz, Michael Sapienza, Julien P. C. Valentin, Vibhav Vineet, Ming-Ming Cheng, Anurag Arnab, Victor A. Prisacariu, Olaf Kähler, Carl Yuheng Ren, David W. Murray, Shahram Izadi, Philip H. S. Torr

* 33 pages, Project: http://www.semantic-paint.com, Code: https://github.com/torrvision/spaint 

  Access Paper or Ask Questions

Feature sampling and partitioning for visual vocabulary generation on large action classification datasets


May 29, 2014
Michael Sapienza, Fabio Cuzzolin, Philip H. S. Torr


  Access Paper or Ask Questions