**Matthew B. Blaschko**

Chargé de Recherche (Inria) and Associate Professor

Center for Visual Computing

École Centrale Paris

Grande Voie des Vignes

92295 Châtenay-Malabry

France

Visitor
Directions

Voice: +33 141131098

Fax: +33 141131006

Email:

[news] [students]
[publications]
[teaching]
[seminars]

_________________________________________________________________________

**Research Highlights:**

I am interested in the interface between machine learning and computer vision. Areas I have worked on include structured output prediction, object detection and localization, clustering, taxonomic prediction, fMRI analysis, and medical image analysis.

**Education:
(Mathematics Genealogy)**

Habilitation (HDR) | École Normale Supérieure de Cachan | 2014 |

Research Fellow | University of Oxford | 2009-2011 |

Dr. rer. nat. | Technische Universität Berlin | 2009 |

M.S. | University of Massachusetts Amherst | 2005 |

B.S. | Columbia University | 2001 |

I would like to thank the following funding sources for supporting my
research:

- I taught at the Third School on Machine Learning and Knowledge Discovery in Databases in São Carlos, Brazil.
- Predicting cross-task behavioral variables from fMRI data using the k-support norm won Best Paper at the Sparsity Techniques in Medical Imaging workshop at MICCAI 2014.
- I was an area chair for NIPS 2014, BMVC 2014, and ICVGIP 2014.
- Katerina Gkirtzou successfully defended her PhD thesis, December 2013.
- I am a permanent research scientist in the Inria Saclay research center, October 2013.
- Our aircraft dataset is included in the fine-grained classification challenge, 2013.
- I taught at the Biomedical Image Analysis Summer School, July 2013.
- I gave a tutorial on Visual Learning with Weak Supervision at CVPR 2013.
- I was an area chair for BMVC 2013.
- I was on the senior program committee for AISTATS 2012.
- I was an area chair for BMVC 2012.
- I joined École Centrale Paris as a faculty member in October, 2011.
- I gave a tutorial on
*Structured Prediction and Inference in Computer Vision*at BMVC 2011 in Dundee, Scotland. - I gave a tutorial at the Twentieth Annual Computational Neuroscience Meeting CNS*2011 in Stockholm, Sweden.
- I received a best reviewer award for CVPR 2011.
- Some additional information is available from my old homepages at the University of Oxford and the Max Planck Institute for Biological Cybernetics.

- Amal Rannen, Yonsei University, Ph.D. student (co-advised with Yoon Mo Jung).
- Maxim Berman, École Centrale Paris, Ph.D. student (co-advised with Nikos Paragios).
- Eugene Belilovsky, École Centrale Paris, Ph.D. student.
- Jiaqian Yu, École Centrale Paris, Ph.D. student.
- Wacha Bounliphone, Supélec, Ph.D. student (co-advised
with Arthur
Tenenhaus).

- Katerina
Gkirtzou, École Centrale Paris, Ph.D. 2013.

Thesis: Sparsity regularization and graph-based representation in medical imaging - Wojciech Zaremba, École Polytechnique, M.Sc. 2012.

Thesis: Modeling the variability of EEG/MEG data through statistical machine learning - Ben Mather, University of Oxford, MEng 2011.
- Shah Ruhul Amin, University of Oxford, MEng 2010.
- Jacquelyn A. Shelton, Universität Tübingen, M.Sc. 2010.

Thesis: Semi-supervised Subspace Learning and Application to Human Functional Magnetic Brain Resonance Imaging Data

**Intern:**

- José Ignacio Orlando, Inria Saclay - Île-de-France, 2013.

**Publications:
(Google
Scholar Profile)**

- Blaschko, M. B. and J. Yu: Hardness Results for Structured
Learning and Inference with Multiple Correct Outputs. Constructive
Machine Learning Workshop at ICML, 2015.
**[bibtex]**

- Belilovsky, E., A. Argyriou, G. Varoquaux, and M. B. Blaschko:
Convex Relaxations of Penalties for Sparse Correlated
Variables With Bounded Total Variation. Machine Learning, 100(2-3):533-553,
2015.
**[bibtex; doi]**

- Yu, J. and M. B. Blaschko: Learning Submodular Losses with the
Lovász Hinge. International Conference on Machine Learning (ICML),
2015.
**[bibtex; code]**

- Bounliphone, W., A. Gretton, A. Tenenhaus, and M. B. Blaschko: A
low variance consistent test of relative dependency. International
Conference on Machine Learning (ICML),
2015.
**[bibtex; code]**

- Sidahmed, H., E. Prokofyeva, and M. B. Blaschko:
Discovering Predictors of Mental Health Service Utilization with
k-support
Regularized Logistic Regression. Information Sciences,
2015.
**[bibtex; code; doi]**

- Belilovsky, E., K. Gkirtzou, M. Misyrlis, A. B.
Konova, J. Honorio, N. Alia-Klein, R. Z. Goldstein, D. Samaras,
and M. B. Blaschko: Predictive sparse modeling of fMRI data for improved
classication, regression, and visualization using the
k-support norm. Computerized Medical Imaging and
Graphics, 2015.
**[bibtex; code; doi]**

- Belilovsky, E., A. Argyriou, and M. B. Blaschko: Approximating
Combined Discrete Total Variation and Correlated Sparsity With
Convex Relaxations. NIPS Workshop on Discrete and Combinatorial
Problems in Machine Learning, 2014.
**[bibtex]**

- Bounliphone, W., A. Gretton, and M. B. Blaschko: Kernel
non-parametric tests of relative dependency. NIPS Workshop on Modern
Nonparametrics 3: Automating the Learning Pipeline, 2014.
**[bibtex]**

- Yu, J. and M. B. Blaschko: Lovasz Hinge for Learning Submodular
Losses. NIPS Workshop on Representation and Learning Methods for
Complex Outputs, 2014.
**[bibtex]**

- Blaschko, M. B.: Advances in Empirical Risk Minimization for Image
Analysis and Pattern Recognition. Mémoire d'habilitation
à diriger des recherches, École Normale
Supérieure de Cachan, 2014.
**[bibtex]**

- Orlando, J. I. and M. B. Blaschko: Learning fully-connected CRFs
for blood vessel segmentation in
retinal images. Medical Image Computing and Computer Assisted
Intervention (MICCAI),
2014.
**[bibtex; data; doi]**

- Ghafarianzadeh, M., M. B. Blaschko, and G. Sibley: Unsupervised
Spatio-Temporal Segmentation with
Sparse Spectral-Clustering. British Machine Vision Conference (BMVC),
2014.
**[bibtex]**

- Blaschko, M. B., A. Mittal, and E. Rahtu: An O(n log n) Cutting
Plane Algorithm for Structured
Output Ranking. 36th German Conference on Pattern Recognition (GCPR),
2014.
**[bibtex; doi]**

- Misyrlis, M., A. B. Konova, M. B. Blaschko, J.
Honorio, N. Alia-Klein, R. Z. Goldstein, D. Samaras: Predicting
cross-task behavioral variables from fMRI data using the k-support
norm. Sparsity Techniques in Medical Imaging,
2014.
**[Note: Best paper award; bibtex]**

- Vedaldi, A., S. Mahendran, S. Tsogkas, S. Maji, R. Girshick,
J. Kannala, E. Rahtu, I. Kokkinos, M. B. Blaschko, D. Weiss,
B. Taskar, K. Simonyan, N. Saphra, and S. Mohamed:
Understanding Objects in Detail with Fine-grained Attributes.
Proceedings of
the IEEE Conference on Computer Vision and Pattern Recognition
(CVPR),
2014.
**[bibtex; code; data; doi]**

- Blaschko,
M. B.: Machine Learning
for Neurological Disorders. Centraliens, 632 (2014)
40-42.
**[bibtex]**

- Zaremba, W., A. Gretton, and
M. Blaschko: B-tests: Low
Variance Kernel Two-Sample Tests. Neural
Information Processing Systems (NIPS),
2013.
**[bibtex; code]**

- Gkirtzou, K., J. Honorio, D. Samaras, R. Goldstein, and
M. Blaschko: fMRI Analysis with Sparse Weisfeiler-Lehman Graph
Statistics. International Workshop on Machine Learning in Medical
Imaging (MLMI),
2013.
**[bibtex; code; doi]**

- Gkirtzou, K., J.-F. Deux, G. Bassez, A. Sotiras, A. Rahmouni,
T. Varacca, N. Paragios, and
M. B. Blaschko: Sparse
classification with MRI based markers for neuromuscular disease categorization. International Workshop on
Machine Learning in Medical Imaging (MLMI),
2013.
**[bibtex; code; doi]**

- Maji, S., E. Rahtu, J. Kannala, M. Blaschko, and
A. Vedaldi: Fine-Grained
Visual Classification of Aircraft. arXiv:1306.5151,
2013.
**[bibtex; code and data]**

- Blaschko, M. B., W. Zaremba, and
A. Gretton: Taxonomic
Prediction with Tree-Structured Covariances. European
Conference on Machine Learning and Principles and Practice of
Knowledge Discovery in Databases (ECML/PKDD),
2013.
**[bibtex; code and data; doi]**

- Blaschko, M. B., J. Kannala, and
E. Rahtu: Non
Maximal Suppression in Cascaded Ranking Models. Scandinavian
Conference on Image Analysis (SCIA),
2013.
**[bibtex; code and data; doi]**

- Blaschko,
M. B.: A
Note on k-support Norm Regularized Risk
Minimization. arXiv:1303.6390, 2013.
**[bibtex; code]**

- Zaremba, W., M. P. Kumar, A. Gramfort, and
M. B. Blaschko: Learning
from M/EEG data with variable brain activation
delays. International Conference on Information Processing in
Medical Imaging (IPMI),
2013.
**[bibtex; code and data; doi]**

- Gkirtzou, K., J. Honorio, D. Samaras, R. Goldstein, and
M. B. Blaschko: fMRI
Analysis of Cocaine Addiction Using k-support
Sparsity. International Symposium on Biomedical Imaging
(ISBI),
2013.
**[bibtex; code; doi]**

- Flint, A. and
M. B. Blaschko: Perceptron
Learning of SAT. Neural Information Processing Systems (NIPS),
2012.
**[bibtex]**

- Mittal, A., M. B. Blaschko, A. Zisserman,
P. H. S. Torr: Taxonomic
Multi-class Prediction and Person Layout using Efficient
Structured Ranking. European Conference on Computer Vision
(ECCV), 2012.
**[bibtex; code; doi]**

- Blaschko, M. B. and
C. H. Lampert: Guest
Editorial: Special Issue on Structured Prediction and
Inference. International Journal of Computer Vision (IJCV),
99(3):257-258, 2012.
**[bibtex; doi]**

- Rahtu, E., J. Kannala, and M. B. Blaschko: Learning
a Category
Independent Object Detection Cascade.
International Conference on Computer
Vision (ICCV), 2011.
**[bibtex; code and data; doi]**

- Vedaldi, A., M. B. Blaschko, and A. Zisserman: Learning
Equivariant Structured Output SVM Regressors.
International Conference on Computer
Vision (ICCV), 2011.
**[bibtex; doi]**

- Blaschko, M. B.: Branch
and Bound Strategies for Non-maximal
Suppression in Object Detection. International Conference on Energy
Minimization Methods in Computer
Vision and Pattern Recognition (EMMCVPR), 2011.
**[bibtex; doi]**

- Blaschko, M. B., J. A. Shelton, A. Bartels, C. H. Lampert
and A. Gretton:
Semi-supervised
Kernel Canonical Correlation Analysis with Application
to Human fMRI. Pattern Recognition Letters, 32(11):1572-1583,
2011.
**[bibtex; doi]**

- Blaschko, M. B., A. Vedaldi and A. Zisserman:
Simultaneous
Object Detection and Ranking with Weak Supervision.
Proceedings of the Twenty-Fourth Annual Conference on
Neural Information Processing Systems (NIPS 2010)
**[bibtex]**

- Shelton, J. A., M. B. Blaschko, A. Gretton, J. Müller, E. Fischer
and A. Bartels, Similarities in Resting State and Feature-driven Activity:
Non-parametric Evaluation of Human fMRI. NIPS'10 Workshop on Learning and
Planning from Batch Time Series Data, 2010.
**[bibtex]**

- Shelton, J. A., M. B. Blaschko, and A. Bartels: Augmentation of fMRI
Data Analysis using Resting State Activity and Semi-supervised Canonical
Correlation Analysis. Women in Machine Learning Workshop (WiML 2010),
Vancouver, BC, Canada 2010.
**[bibtex]**

- Tuytelaars, T., C. H. Lampert, M. B. Blaschko
and W. Buntine:
Unsupervised Object
Discovery: A
Comparison. International Journal of Computer Vision (IJCV),
88(2):284-302,
2010.
**[bibtex; code; doi]**

- Blaschko, M. B., J. A. Shelton and A. Bartels:
Augmenting
Feature-driven fMRI Analyses: Semi-supervised Learning and
Resting State Activity.
Proceedings of the Twenty-Third Annual Conference on
Neural Information Processing Systems (NIPS 2009)
**[bibtex]**

- Blaschko, M. B. and C. H. Lampert: Object
Localization with Global
and Local Context Kernels. British Machine Vision Conference (BMVC),
2009.
**[bibtex; video; doi]**

- Lampert, C. H., M. B. Blaschko and T. Hofmann: Efficient
Subwindow
Search: A Branch and Bound Framework for Object Localization.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
31(12):2129-2142,
2009.
**[bibtex; code; doi]**

- Shelton, J. A., M. B. Blaschko, C. H. Lampert and A. Bartels:
Semi-supervised
Analysis of Human fMRI. Berlin Brain-Computer Interface
Workshop (BBCI), 2009.
**[bibtex]**

- Shelton, J., M. B. Blaschko and A. Bartels: Semi-supervised
Subspace
Analysis of Human Functional Magnetic Resonance Imaging Data. Max
Planck
Institute for Biological Cybernetics Tech Report (185) (05
2009)
**[bibtex]**

- Lampert, C. H. and M. B.
Blaschko: Structured Prediction
by Joint Kernel Support Estimation. Machine Learning, 77(2-3):249-269,
2009.
**[bibtex; doi]**

- Blaschko, M. B.: Kernel
Methods in Computer Vision: Object
Localization, Clustering, and Taxonomy Discovery. Doctoral Thesis, Max
Planck Institute for Biological Cybernetics, Awarded by the Technische
Universität Berlin, 2009.
**[bibtex]**

- Blaschko, M. B. and A. Gretton: Learning
Taxonomies by Dependence
Maximization. Proceedings of the Twenty-Second Annual Conference on
Neural Information Processing Systems (NIPS 2008), 1-8. (Eds.)
Koller, D., D. Schuurmans, Y. Bengio, L. Bottou (01 2009)
**[bibtex]**

- Lampert, C. H. and M. Blaschko: Joint Kernel
Support Estimation
for Structured Prediction. NIPS 2008 Workshop on "Structured Input -
Structured Output" 2008, 76 (12 2008)
**[bibtex]**

- Blaschko, M. B. and A. Gretton: Taxonomy Inference
Using Kernel
Dependence Measures. Max Planck Institute for Biological Cybernetics
Tech Report (181) (11 2008)
**[bibtex]**

- Blaschko, M. B. and C. H. Lampert: Learning to
Localize Objects
with Structured Output Regression. Computer Vision: ECCV 2008, 2-15.
(Eds.) Forsyth, D. A., P. H.S. Torr, A. Zisserman, Springer, Berlin,
Germany (10 2008)
**[Note: Best Student Paper Award; bibtex; code; doi]**

- Blaschko, M. B., C. H. Lampert and A. Gretton: Semi-Supervised
Laplacian Regularization of Kernel Canonical Correlation Analysis.
Machine Learning and Knowledge Discovery in Databases: European
Conference, ECML PKDD 2008, 133-145. (Eds.) Daelemans, W., B.
Goethals, K. Morik, Springer, Berlin, Germany (08
2008)
**[bibtex; doi]**

- Blaschko, M. B. and A. Gretton: A Hilbert-Schmidt
Dependence
Maximization Approach to Unsupervised Structure Discovery.
Proceedings of the 6th International Workshop on Mining and Learning
with Graphs (MLG 2008), 1-3 (07 2008)
**[bibtex]**

- Blaschko, M. B. and C. H. Lampert: Correlational
Spectral
Clustering. Proceedings of the IEEE Computer Society Conference on
Computer Vision and Pattern Recognition (CVPR 2008), 1-8, IEEE
Computer Society, Los Alamitos, CA, USA (06 2008)
**[bibtex; code; doi]**

- Lampert, C. H., M. B. Blaschko and T. Hofmann: Beyond
Sliding
Windows: Object Localization by Efficient Subwindow Search.
Proceedings of the IEEE Computer Society Conference on Computer
Vision and Pattern Recognition (CVPR 2008), 1-8, IEEE Computer
Society, Los Alamitos, CA, USA (06 2008)
**[Note: Best paper award; bibtex; code; doi]**

- Lampert, C. and M. B. Blaschko: A Multiple Kernel
Learning
Approach to Joint Multi-Class Object Detection. Pattern Recognition:
Proceedings of the 30th DAGM Symposium, 31-40. (Eds.) Rigoll, G.
Springer, Berlin, Germany (06 2008)
**[Note: Main Award DAGM 2008; bibtex; doi]**

- Blaschko, M. B., T. Hofmann and C. H. Lampert: Efficient
Subwindow Search for Object Localization. Max Planck Institute for
Biological Cybernetics Tech Report (164) (08 2007)
**[bibtex]**

- Blaschko, M. B. and T. Hofmann: Conformal
Multi-Instance Kernels.
NIPS 2006 Workshop on Learning to Compare Examples, 1-6 (12
2006)
**[bibtex]**

- Lisin, D. A., M. A. Mattar, M. B. Blaschko, M. C. Benfield and E.
G. Learned-Miller: Combining
Local and Global Image Features for
Object Class Recognition. Proceedings of IEEE Workshop on Learning in
Computer Vision and Pattern Recognition (in conjunction with CVPR),
47 (06 2005)
**[bibtex; doi]**

- Blaschko, M. B.: Support
Vector Classification of Images with Local
Features. M.S. Thesis, University of Massachusetts Amherst, Dept. of
Computer Science (05 2005)
**[bibtex]**

- Blaschko, M. B., G. Holness, M. A. Mattar, D. Lisin, P.
E. Utgoff, A. R. Hanson, H. Schultz, E. M. Riseman, M. E. Sieracki, W.
M. Balch and B. Tupper: Automatic
In Situ Identification of Plankton.
Proceedings of the Seventh IEEE Workshops on Application of Computer
Vision (WACV/MOTION'05), 79 - 86 (01
2005)
**[bibtex; doi]**

- Shapiro, M. D. and M. B. Blaschko: Stability
of Hausdorff-based
Distance Measures. Visualization, Imaging, and Image Processing, 1-6
(09
2004)
**[bibtex]**

- Shapiro, M. D. and M. B. Blaschko: On
Hausdorff Distance
Measures. University of Massachusetts Amherst, Computer Science
Dept. Technical report (08 2004)
**[bibtex]**