IEEE Signal Processing Magazine - January 2018 - 51

Universidad de Murcia, Spain, in 2009 and his M.Sc. degree
in computational statistics and machine learning from
University College London in 2010. He received his Ph.D. degree from University College London in 2014, supervised by
Prof. Massimiliano Pontil and Prof. Nadia Berthouze. He was a
postdoctoral research fellow in the Torr Vision Group at the
University of Oxford, United Kingdom, from 2014 to 2016.
He has published in top-tier machine-learning conferences
such as Advances in Neural Information Processing
Systems, the International Conference on Machine Learning,
and the International Conference on Computer Vision. His research focuses on multitask and transfer learning methods applied to computer vision tasks. He is a research scientist at
Google DeepMind.
Måns Larsson (mans.larsson@chalmers.se) received his
B.Sc. degree in engineering physics and his M.Sc. degree in
complex adaptive systems from Chalmers University of
Technology, Sweden, in 2012 and 2015, respectively, where he
is currently a Ph.D. student under the supervision of Prof.
Fredrik Kahl. His research interests include deep learning, probabilistic graphical models, and semantic segmentation tasks in
both medical image analysis and computer vision.
Alexander Kirillov (alexander.kirillov@iwr.uni-heidelberg.de)
received his specialist degree in applied mathematics and computer science from Lomonosov Moscow State University, Russia,
in 2013. He is a Ph.D. student at the Universität Heidelberg,
Germany, jointly supervised by Prof. Carsten Rother and Prof.
Dmitry Vetrov. He has published in top computer vision and
machine-learning venues such as the Conference on Computer
Vision and Pattern Recognition, the International Conference on
Computer Vision, and Advances in Neural Information
Processing Systems. His main research interests are deep-learning models for structured output and energy minimization problems for computer vision applications.
Bogdan Savchynskyy (bogdan.savchynskyy@tu-dresden
.de) received his bachelor's and master's degrees in applied
mathematics from the National Technical University of Ukraine
"Kyiv Polytechnic Institute" in 2000 and 2002, respectively. He
received his Ph.D. degree in computer science (systems and tools
of artificial intelligence) in 2007 from the National Academy of
Sciences of Ukraine. Currently, he is a senior researcher at the
Universität Heidelberg, Germany. He was awarded the 2003
President of Ukraine Scholarship for Young Scientists and the
2014 Best Student Paper Award from the Conference on
Computer Vision and Pattern Recognition. He received funding
on the project Exact Relaxation-Based Inference in Graphical
Models from the German Research Foundation. His research
interests include mathematical optimization problems in machine
learning and computer vision.
Carsten Rother (carsten.rother@iwr.uni-heidelberg.de)
received the diploma degree with distinction in 1999 from the
University of Karlsruhe, Germany, and the Ph.D. degree in 2003
from the Royal Institute of Technology Stockholm, Sweden,
both in computer science. He is a full professor at the Universität
Heidelberg, Germany. His research interests are the field of computer vision and machine learning, such as segmentation, match-

ing, object recognition, and pose estimation, with applications to
natural science, in particular biology and medicine. He won the
Best Paper (honorable mention) Award at the International
Conference on Computer Vision and Pattern Recognition 2005,
the Asian Conference on Computer Vision, and the Association
for Computing Machinery Conference on Human Factors in
Computing Systems 2007. He was awarded the DAGM
Olympus Prize in 2009.
Fredrik Kahl (fredrik.kahl@chalmers.se) received his
M.Sc. degree in computer science and technology in 1995 and
his Ph.D. degree in mathematics in 2001, both from Lund
University, Sweden. His thesis was awarded the Best Nordic
Thesis Award in pattern recognition and image analysis
2001-2002 at the Scandinavian Conference on Image
Analysis 2003. He received the Marr Prize at the 2005 IEEE
International Conference on Computer Vision. In 2007, he was
awarded an ERC starting grant from the European Research
Council, which supported his team during 2008-2013. He is currently a joint professor at Chalmers University of Technology
and Lund University, both in Sweden.
Philip H.S. Torr (philip.torr@eng.ox.ac.uk) completed his
undergraduate degree in pure mathematics from the University
of Southampton, United Kingdom, in 1990. He received his
Ph.D. degree in computer vision in 1995 from Oxford University,
United Kingdom. He remained at Oxford for three years as a
research fellow before becoming a research scientist at Microsoft
Research for six years, first in Redmond, Washington, then in
Cambridge, United Kingdom, founding the vision side of the
Machine Learning and Perception Group. He has won awards
from several top vision conferences, including the International
Conference on Computer Vision, the Conference on Computer
Vision and Pattern Recognition, the European Conference on
Computer Vision, Advances in Neural Information Processing
Systems, and the British Machine Vision Conference. He is currently a professor at Oxford University.

References

[1] M. Minsky and S. Papert, Perceptrons: An Introduction to Computational
Geometry. Cambridge, MA: MIT Press, 1969.
[2] A. Blake, P. Kohli, and C. Rother, Markov Random Fields for Vision and Image
Processing. Cambridge, MA: MIT Press, 2011.
[3] J. Shotton, J. Winn, C. Rother, and A. Criminisi, "Textonboost for image understanding: Multiclass object recognition and segmentation by jointly modeling texture,
layout, and context," Int. J. Comput. Vision, vol. 81, no. 1, pp. 2-23, 2009.
[4] P. Krähenbühl and V. Koltun, "Efficient inference in fully connected CRFs with
gaussian edge potentials," in Proc. Neural Information Processing Systems Conf.,
2011, pp. 109-117.
[5] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, "Semantic
image segmentation with deep convolutional nets and fully connected CRFs," in Proc.
Int. Conf. Learning Representations, 2015.
[6] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic
segmentation," in Proc. IEEE Conf. Computer Vision Pattern Recognition, 2015, pp.
3431-3440.
[7] S. Zheng, S. Jayasumana, B. Romera-Paredes, V. Vineet, Z. Su, D. Du, C. Huang,
and P. Torr, "Conditional random fields as recurrent neural networks," in Proc. IEEE
Int. Conf. Computer Vision, 2015, pp. 1529-1537.
[8] S. Chandra and I. Kokkinos, "Fast, exact and multi-scale inference for semantic
image segmentation with deep Gaussian CRFs," in Proc. IEEE European Conf.
Computer Vision, 2016, pp. 402-418.
[9] L. Ladicky, C. Russell, P. Kohli, and P. H. Torr, "Associative hierarchical CRFs for
object class image segmentation," in Proc. IEEE Int. Conf. Computer Vision, 2009,
pp. 739-746.

IEEE SIGNAL PROCESSING MAGAZINE

January 2018

Table of Contents for the Digital Edition of IEEE Signal Processing Magazine - January 2018