Prof. Dr. Cristian Sminchisescu

Address:	Institut für Numerische Simulation Wegelerstr. 4 (Flachbau) 53115 Bonn Germany
Office:	We4 0.022
Phone:	+49 228 733522
E-Mail:	cristian.sminchisescuins.uni-bonn.de

Cristian Sminchisescu is a faculty member at the University of Bonn where he leads the Computer Vision and Machine Learning Group at the INS. He has obtained a doctorate in Computer Science and Applied Mathematics with an emphasis on imagining, vision and robotics at INRIA, France, under an Eiffel excellence doctoral fellowship, and has done postdoctoral research in the Artificial intelligence Laboratory at the University of Toronto, where he now holds an Adjunct Professor appointment. Prior to Bonn, he has been a faculty member at the Toyota Technological Institute at Chicago. Cristian Sminchisescu is a member in the program committees of the main conferences in computer vision and machine learning (CVPR, ICCV, ECCV, NIPS, AISTATS) and a member of the Editorial Board (Associate Editor) of IEEE Transactions for Pattern Analysis and Machine Intelligence (PAMI). He has given more than 50 invited talks and presentations and has oferred tutorials on 3d tracking, recognition and optimization at ICCV and CVPR, the Chicago Machine Learning Summer School, and the AEFRAI Vision School in Barcelona. Over time, his work has been funded by TTI-C, NSF and the European Commission under a Marie Curie Excellence Grant. Cristian Sminchisescu’s research goal is to train computers to `see’ and interact with the world seamlessly, as humans do. His research interests are in the area of computer vision (articulated objects, 3d reconstruction, segmentation, and object and action recognition) and machine learning (optimization and sampling algorithms, structured prediction, sparse approximations and kernel methods). Recent work in the group has produced state-of-the art results in the monocular 3d human pose estimation benchmark (HumanEva) and ranked first in the PASCAL VOC object segmentation and labeling challenge, in 2009.

Teaching

WS 2007/2008:
Lecture Bayesian Models for Visual Perception
SS 2007:
Lecture Machine Learning for Computer Vision

Publications

[1]	F. Li and C. Sminchisescu. The Feature Selection Path in Kernel Methods. In Artificial Intelligence and Statistics, May 2010. [ bib ]
[2]	J. Carreira and C. Sminchisescu. Constrained Parametric Min-Cuts for Automatic Object Segmentation. In IEEE International Conference on Computer Vision and Pattern Recognition, June 2010. description of our PASCAL VOC 2009 segmentation entry. [ bib ]
[3]	F. Li, J. Carreira, and C. Sminchisescu. Object Recognition as Ranking Holistic Figure-Ground Hypotheses. In IEEE International Conference on Computer Vision and Pattern Recognition, June 2010. description of our PASCAL VOC 2009 recognition entry (first two authors contributed equally). [ bib ]
[4]	J. Carreira, F. Li, and C. Sminchisescu. Object Recognition by Ranking Figure-Ground Hypotheses. Snowbird Learning, April 2010. [ bib \| .pdf 1 ]
[5]	F. Li and C. Sminchisescu. Convex Multiple-Instance Learning. Snowbird Learning, April 2010. [ bib \| .pdf 1 ]
[6]	C. Sminchisescu and M. Welling. Generalized Darting Monte-Carlo. Pattern Recognition, 2010. [ bib \| .pdf 1 ]
[7]	D. Han, L. Bo, and C. Sminchisescu. Selection and Context for Action Recognition. In IEEE International Conference on Computer Vision, September 2009. [ bib \| .pdf 1 ]
[8]	C. Ionescu, L. Bo, and C. Sminchisescu. Structural SVM for Visual Localization and Continuous State Estimation. In IEEE International Conference on Computer Vision, September 2009. [ bib \| .pdf 1 ]
[9]	A. Levinshtein, S. Dickinson, and C. Sminchisescu. Multiscale Symmetric Part Detection and Grouping. In IEEE International Conference on Computer Vision, September 2009. [ bib \| .pdf 1 ]
[10]	L. Bo and C. Sminchisescu. Efficient Match Kernel between Sets of Features for Visual Recognition. In Advances in Neural Information Processing Systems, December 2009. [ bib \| .pdf 1 ]
[11]	L. Bo and C. Sminchisescu. Supervised Spectral Latent Variable Models. In Artificial Intelligence and Statistics, April 2009. [ bib \| .pdf 1 ]
[12]	C. Ionescu and C. Sminchisescu. Hierarchical Latent Variable Models for Human Pose Inference. Snowbird Learning, April 2009. [ bib \| .pdf 1 ]
[13]	F. Li, Y. Fu, Y. Hong-Dai, C. Sminchisescu, and J. Wang. Kernel Learning by Unconstrained Optimization. In Artificial Intelligence and Statistics, April 2009. [ bib \| .pdf 1 ]
[14]	L. Bo and C. Sminchisescu. Structured Output-Associative Regression. In IEEE International Conference on Computer Vision and Pattern Recognition, 2009. [ bib \| .pdf 1 ]
[15]	L. Bo and C. Sminchisescu. Twin Gaussian Processes for Structured Prediction. International Journal of Computer Vision, 2009. [ bib \| .pdf 1 ]
[16]	L. Bo, C. Sminchisescu, A. Kanaujia, and D. Metaxas. Fast Algorithms for Large Scale Conditional 3D Prediction. In IEEE International Conference on Computer Vision and Pattern Recognition, June 2008. [ bib \| .pdf 1 ]
[17]	L. Bo and C. Sminchisescu. Greedy Block Coordinate Descent for Large Scale Gaussian Process Regression. In Uncertainty in Artificial Intelligence, July 2008. [ bib \| .pdf 1 ]
[18]	L. Bo and C. Sminchisescu. Twin Gaussian Processes for Structured Prediction. Snowbird Learning, April 2008. [ bib \| .pdf 1 ]
[19]	A. Levinshtein, C. Sminchisescu, and S. Dickinson. Qualitative 3D Surface Reconstruction from Images. Snowbird Learning, April 2008. [ bib \| .pdf 1 ]
[20]	C. Sminchisescu and C. Ionescu. Hierarchical Spectral Latent Variable Models. Snowbird Learning, April 2008. [ bib \| .pdf 1 ]
[21]	A. Kanaujia, C. Sminchisescu, and D. Metaxas. Spectral Latent Variable Models for Perceptual Inference. In IEEE International Conference on Computer Vision, October 2007. [ bib \| .pdf 1 ]
[22]	A. Kumar and C. Sminchisescu. Support kernel machines for object recognition. In IEEE International Conference on Computer Vision, October 2007. [ bib \| .pdf 1 ]
[23]	A. Kanaujia, C. Sminchisescu, and D. Metaxas. Semi-Supervised Hierarchical Models for 3D Human Pose Reconstruction. In IEEE International Conference on Computer Vision and Pattern Recognition, June 2007. [ bib \| .pdf 1 ]
[24]	A. Kanaujia, C. Sminchisescu, and D. Metaxas. Sparse Spectral Latent Variable Models for Perceptual Inference. Technical Report DCS-TR-610, Rutgers University, February 2007. [ bib ]
[25]	Z. Lu, M. C. Perpinan, and C. Sminchisescu. People Tracking with the Laplacian Eigenmaps Latent Variable Model. In Advances in Neural Information Processing Systems, December 2007. [ bib \| .pdf 1 ]
[26]	A. Kanujia, C. Sminchisescu, and D. Metaxas. Hierarchical Models for 3D Visual Inference. Snowbird Learning, April 2007. [ bib \| .pdf 1 ]
[27]	C. Sminchisescu. Learning and Inference Algorithms for Monocular Perception. Applications to Visual Object Detection, Localization and Time Series Models for 3D Human Motion Understanding, 2007. University of Bonn, Faculty of Mathematics and Natural Sciences. Habilitation Thesis. [ bib \| .pdf 1 ]
[28]	C. Sminchisescu, A. Kanaujia, and D. Metaxas. BM³E: Discriminative Density Propagation for Visual Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007. [ bib \| .pdf 1 ]
[29]	C. Sminchisescu and M. Welling. Generalized Darting Monte-Carlo. In Artificial Intelligence and Statistics, volume 1, 2007. [ bib \| .pdf 1 ]
[30]	C. Sminchisescu and M. Welling. Generalized darting Monte Carlo. Technical Report CSRG-543, University of Toronto, October 2006. [ bib \| .pdf 1 ]
[31]	C. Sminchisescu, A. Kanaujia, and D. Metaxas. Bidirectional Model Learning for Visual Inference. Snowbird Learning, April 2006. [ bib \| .pdf 1 ]
[32]	M. van Eede, D. Macrini, A. Telea, C. Sminchisescu, and S. J. Dickinson. Canonical skeletons for shape matching. In IEEE International Conference on Pattern Recognition, pages 64-69, 2006. [ bib \| .pdf 1 ]
[33]	D. Ramanan and C. Sminchisescu. Training Deformable Models for Localization. In IEEE International Conference on Computer Vision and Pattern Recognition, 2006. [ bib \| .pdf 1 ]
[34]	C. Sminchisescu, A. Kanaujia, and D. Metaxas. Conditional models for contextual human motion recognition. In Computer Vision and Image Understanding, 2006. [ bib \| .pdf 1 ]
[35]	C. Sminchisescu, A. Kanaujia, and D. Metaxas. Learning Joint Top-down and Bottom-up Processes for 3D Visual Inference. In IEEE International Conference on Computer Vision and Pattern Recognition, 2006. [ bib \| .pdf 1 ]
[36]	C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas. Conditional models for human motion recognition. Technical Report CSRG-517, University of Toronto, March 2005. [ bib ]
[37]	A. Levinshtein, C. Sminchisescu, and S. J. Dickinson. Learning hierarchical shape models from examples. In Energy Minimization Methods in Computer Vision and Pattern Recognition, St. Augustine, FL, USA, November 9-11, 2005, Proceedings, pages 251-267, 2005. [ bib \| .pdf 1 ]
[38]	C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas. Discriminative Density Propagation for 3D Human Motion Estimation. In IEEE International Conference on Computer Vision and Pattern Recognition, volume 1, pages 390-397, 2005. [ bib \| .pdf 1 ]
[39]	C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas. Conditional models for contextual human motion recognition. In IEEE International Conference on Computer Vision, volume 2, pages 1808-1815, 2005. [ bib \| .pdf 1 ]
[40]	C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas. Conditional Visual Tracking in Kernel Space. In Advances in Neural Information Processing Systems, 2005. [ bib \| .pdf 1 ]
[41]	C. Sminchisescu, D. Metaxas, and S. Dickinson. Incremental Model-Based Estimation using Geometric Consistency Constraints. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005. [ bib \| .pdf 1 ]
[42]	C. Sminchisescu and B. Triggs. Building Roadmaps of Minima and Transitions in Visual Models. International Journal of Computer Vision, 61(1), 2005. [ bib \| .pdf 1 ]
[43]	C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas. Learning to reconstruct 3D human motion from Bayesian mixtures of experts. A probabilistic discriminative approach. Technical Report CSRG-502, University of Toronto, October 2004. [ bib \| .pdf 1 ]
[44]	C. Sminchisescu and A. Jepson. Variational Mixture Smoothing for Non-Linear Dynamical Systems. In IEEE International Conference on Computer Vision and Pattern Recognition, volume 2, pages 608-615, Washington D.C., 2004. [ bib \| .pdf 1 ]
[45]	C. Sminchisescu and A. Jepson. Generative Modeling for Continuous Non-Linearly Embedded Visual Inference. In International Conference on Machine Learning, pages 759-766, Banff, 2004. [ bib \| .pdf 1 ]
[46]	C. Sminchisescu and B. Triggs. Fast Mixing Hyperdynamic Sampling. Journal of Image and Vision Computing, 2004. Special Issue on Selected Papers from the European Conference on Computer Vision (2002). [ bib \| .pdf 1 ]
[47]	A. Telea, C. Sminchisescu, and S. Dickinson. Optimal Inference for Hierarchical Skeleton Abstraction. In IEEE International Conference on Pattern Recognition, 2004. [ bib \| .pdf 1 ]
[48]	C. Sminchisescu and A. Jepson. Non-linearly Embedded Visual Tracking. Technical Report CSRG-477, University of Toronto, September 2003. [ bib ]
[49]	C. Sminchisescu, M. Welling, and G. Hinton. A Mode-Hopping MCMC Sampler. Technical Report CSRG-478, University of Toronto, September 2003. [ bib \| .pdf 1 ]
[50]	C. Sminchisescu and B. Triggs. Kinematic Jump Processes for Monocular 3D Human Tracking. In IEEE International Conference on Computer Vision and Pattern Recognition, volume 1, pages 69-76, Madison, 2003. [ bib \| .pdf 1 ]
[51]	C. Sminchisescu and B. Triggs. Estimating Articulated Human Motion with Covariance Scaled Sampling. International Journal of Robotics Research, 22(6):371-393, 2003. [ bib \| .pdf 1 ]
[52]	C. Sminchisescu. Estimation Algorithms for Ambiguous Visual Models-Three-Dimensional Human Modeling and Motion Reconstruction in Monocular Video Sequences. PhD thesis, Institute National Politechnique de Grenoble (INRIA), July 2002. [ bib ]
[53]	C. Sminchisescu. Consistency and Coupling in Human Model Likelihoods. In IEEE International Conference on Automatic Face and Gesture Recognition, pages 27-32, Washington D.C., 2002. [ bib \| .pdf 1 ]
[54]	C. Sminchisescu and A. Telea. Human Pose Estimation from Silhouettes. A Consistent Approach Using Distance Level Sets. In WSCG International Conference for Computer Graphics, Visualization and Computer Vision, Czech Republic, 2002. [ bib \| .pdf 1 ]
[55]	C. Sminchisescu and B. Triggs. Building Roadmaps of Local Minima of Visual Models. In European Conference on Computer Vision, volume 1, pages 566-582, Copenhagen, 2002. [ bib \| .pdf 1 ]
[56]	C. Sminchisescu and B. Triggs. Hyperdynamics Importance Sampling. In European Conference on Computer Vision, volume 1, pages 769-783, Copenhagen, 2002. [ bib \| .pdf 1 ]
[57]	C. Sminchisescu, D. Metaxas, and S. Dickinson. Incremental Model-Based Estimation Using Geometric Consistency Constraints. Technical Report 4209, INRIA, June 2001. [ bib \| .ps.gz 1 ]
[58]	C. Sminchisescu, D. Metaxas, and S. Dickinson. Improving the Scope of Deformable Model Shape and Motion Estimation. In IEEE International Conference on Computer Vision and Pattern Recognition, volume 1, pages 485-492, Hawaii, 2001. [ bib \| .pdf 1 ]
[59]	C. Sminchisescu and A. Telea. A Framework for Generic State Estimation in Computer Vision Applications. In S. Verlag, editor, International Conference for Computer Vision, ICVS International Conference on Computer Vision Systems, pages 21-34, Vancouver, 2001. [ bib \| .ps.gz 1 ]
[60]	C. Sminchisescu and B. Triggs. A Robust Multiple Hypothesis Approach to Monocular Human Motion Tracking. Technical Report RR-4208, INRIA, 2001. [ bib \| .ps.gz 1 ]
[61]	C. Sminchisescu and B. Triggs. Covariance-Scaled Sampling for Monocular 3D Body Tracking. In IEEE International Conference on Computer Vision and Pattern Recognition, volume 1, pages 447-454, Hawaii, 2001. [ bib \| .pdf 1 ]
[62]	C. Sminchisescu and A. Telea. An Object-Oriented Approach to C++ Compiler Technology. In European Conference on Object Oriented Programming, PHOOS Workshop, Lisabon, 1999. [ bib \| .ps.gz 1 ]
[63]	A. Telea and C. Sminchisescu. A Component-Based DataFlow Framework for Simulation and Visualization. In European Conference on Object Oriented Programming, PHOOS Workshop, Lisabon, 1999. [ bib \| .ps.gz 1 ]