SalzmannM

Mathieu Salzmann

Researcher
Canberra Research Laboratory

Office location: Office L1-23, 7 London Circuit, Canberra ACT 2600
Postal address: Locked Bag 8001, Canberra ACT 2601, Australia
Tel: +61 2 6267 6282
Fax: +61 2 6267 6210
Email: mathieu { DOT } salzmann { AT } nicta { DOT } com { DOT } au

Research interests

Computer Vision: 3D reconstruction, Riemannian geometry, optimization methods.
Machine Learning: Discriminative prediction, dimensionality reduction, sparse coding.
Computer Graphics: 3D modeling and animation.

Some project webpages

Monocular 3D reconstruction of deformable surfaces (code + dataset)
MCMC methods on constrained spaces (code)
Combining text and images for image retrieval (dataset)
Object recognition from unseen modalities (code + dataset)

Publications

Conference Papers

M. Baktashmotlagh, M. Harandi, A. Bigdeli, B. Lovell, and M. Salzmann
Non-Linear Stationary Subspace Analysis with Application to Video Classification
International Conference on Machine Learning (ICML), Atlanta, GA, June 2013.
Supplementary material

M. Salzmann
Continuous Inference in Graphical Models with Polynomial Energies
Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 2013.
Code

S. Jayasumana, R. Hartley, M. Salzmann, H. Li and M. Harandi
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices (oral)
Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 2013.

M. Liu, R. Hartley and M. Salzmann
Mirror Surface Reconstruction from a Single Image
Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 2013.

J. M. Alvarez, M. Salzmann and N. Barnes
Learning Appearance Models for Road Detection
Intelligent Vehicles Symposium (IV), Brisbane, Australia, June 2013.

M. Salzmann and R. Urtasun
Beyond Feature Points: Structured Prediction for Monocular Non-rigid 3D Reconstruction
European Conference on Computer Vision (ECCV), Firenze, Italy, October 2012.

A. Varol, M. Salzmann, P. Fua and R. Urtasun
A Constrained Latent Variable Model
Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June 2012.
Proofs

M. Brubaker, M. Salzmann and R. Urtasun
A Family of MCMC Methods on Implicitly Defined Manifolds
International Conference on Artificial Intelligence and Statistics (AISTATS), La Palma, Canary Islands, April 2012.
Code

M. Salzmann and R. Urtasun
Physically-based Motion Models for 3D Tracking: A Convex Formulation
International Conference on Computer Vision (ICCV), Barcelona, November 2011.

Y. Jia, M. Salzmann and T. Darrell
Learning Cross-modality Similarity for Multinomial Data
International Conference on Computer Vision (ICCV), Barcelona, November 2011.
Dataset

M. Salzmann and R. Urtasun
Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation
Neural Information Processing Systems Conference (NIPS), Vancouver, Canada, December 2010.

Y. Jia, M. Salzmann and T. Darrell
Factorized Latent Spaces with Structured Sparsity
Neural Information Processing Systems Conference (NIPS), Vancouver, Canada, December 2010.

C. M. Christoudias, R. Urtasun, M. Salzmann and T. Darrell
Learning to Recognize Objects from Unseen Modalities
European Conference on Computer Vision (ECCV), Heraklion, Crete, September 2010.
Code + dataset

M. Salzmann and R. Urtasun
Combining Discriminative and Generative Methods for 3D Deformable Surface and Articulated Pose Reconstruction (oral)
Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010.

M. Salzmann, C. H. Ek, R. Urtasun and T. Darrell
Factorized Orthogonal Latent Spaces
International Conference on Artificial Intelligence and Statistics (AISTATS), Sardinia, Italy, May 2010.

A. Varol, M. Salzmann, E. Tola and P. Fua
Template-Free Monocular Reconstruction of Deformable Surfaces
International Conference on Computer Vision (ICCV), Kyoto, Japan, October 2009.

M. Salzmann and P. Fua
Reconstructing Sharply Folding Surfaces: A Convex Formulation (oral)
Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, June 2009.
Code

F. Moreno-Noguer, M. Salzmann, V. Lepetit and P. Fua
Capturing 3D Stretchable Surfaces from Single Images in Closed Form
Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, June 2009.

A. Fossati, M. Salzmann and P. Fua
Observable Subspaces for 3D Human Motion Recovery
Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, June 2009.

M. Salzmann, F. Moreno-Noguer, V. Lepetit and P. Fua
Closed-Form Solution to Non-Rigid 3D Surface Registration
European Conference on Computer Vision (ECCV), Marseille, France, October 2008.

M. Salzmann, R. Urtasun and P. Fua
Local Deformation Models for Monocular 3D Shape Recovery (oral)
Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, June 2008.

P. Lagger, M. Salzmann, V. Lepetit and P. Fua
3D Pose Refinement from Reflections (oral)
Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, June 2008.

M. Salzmann, R. Hartley and P. Fua
Convex Optimization for Deformable Surface 3-D Tracking (oral)
IEEE International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, October 2007.

M. Salzmann, V. Lepetit and P. Fua
Deformable Surface Tracking Ambiguities
Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MI, June 2007.

M. Salzmann, S. Ilic and P. Fua
Physically Valid Shape Parameterization for Monocular 3-D Deformable Surface Tracking
British Machine Vision Conference (BMVC), Oxford Brookes, September 2005.

S. Ilic, M. Salzmann and P. Fua
Implicit Surfaces Make for Better Silhouettes
Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, June 2005.

Journal Papers:

A. Varol, A. Shaji, M. Salzmann and P. Fua
Monocular 3D Reconstruction of Locally Textured Surfaces
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, Nr. 6, pp. 1118-1130, June 2012.

M. Salzmann and P. Fua
Linear Local Models for Monocular Reconstruction of Deformable Surfaces
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, Nr. 5, pp. 931-944, May 2011.

M. Salzmann and P. Fua
Deformable Surface 3D Reconstruction from Monocular Images
Morgan & Claypool, Synthesis Lectures on Computer Vision, December 2010.

M. Salzmann, J.Pilet, S.Ilic and P.Fua
Surface Deformation Models for Non-Rigid 3-D Shape Recovery
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, Nr. 8, pp. 1481 - 1487, August 2007.

S. Ilic, M. Salzmann and P. Fua
Implicit Meshes for Effective Silhouette Handling
International Journal of Computer Vision, Vol. 72, Nr. 2, pp. 159 - 178, 2007.

Workshops:

A. Varol, M. Salzmann, P. Fua and R. Urtasun
Constrained Regression for 3D Pose Estimation
Learning Workshop (Snowbird), April 2011.

M. Salzmann, C. H. Ek, R. Urtasun and T. Darrell
FOLS: Factorized Orthogonal Latent Spaces (oral)
Learning Workshop (Snowbird), April 2010.

M. Salzmann and R. Urtasun
A Constrained Combination of Discriminative and Generative Methods
Learning Workshop (Snowbird), April 2010.

Technical Reports:

M. Salzmann, J.Pilet, S.Ilic, P.Fua
Parameterizing Deformable Surfaces for Monocular 3-D Tracking
EPFL Technical Report IC/2005/020, 2005.

R. Urtasun, M. Salzmann, P. Fua
3D Morphing without User Interaction
Technical Report, 2004.

Ph.D Thesis:

M. Salzmann
Learning and Recovering 3D Surface Deformations
EPFL Thesis N° 4270, January 2009.