Cristian Sminchisescu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Cristian Sminchisescu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Alex Levinshtein
University of Toronto, Toronto, USA
2 shared publications - Sven Dickinson
Department of Computer Science, University of Toronto, Toronto, ON, Canada
2 shared publications - Adrian Ion
Institute for Numerical Simulation, University of Bonn, Germany
1 shared publication - Atul Kanaujia
ObjectVideo
1 shared publication - Catalin Ionescu
Institute of Mathematics of the Romanian Academy
1 shared publication - Eduard Gabriel Băzăvan
Institute of Mathematics
1 shared publication
Latest Publications
- 8 February 2013
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 104 (2) , 117-134
Multiscale Symmetric Part Detection and Grouping
- 8 February 2013
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 104 (2) , 117-134
Multiscale Symmetric Part Detection and Grouping
- 4 May 2012
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 100 (1) , 99-119
Optimal Image and Video Closure by Superpixel Grouping
- 4 May 2012
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 100 (1) , 99-119
Optimal Image and Video Closure by Superpixel Grouping
- Open Access
Learning Random Kernel Approximations for Object Recognition
Approximations based on random Fourier features have recently emerged as an efficient and formally consistent methodology to design large-scale kernel machines. By expressing the kernel as a Fourier expansion, features are generated based on a finite set of random basis projections, sampled from the Fourier transform of the kernel, with inner products that are Monte Carlo approximations of the original kernel. Based on the observation that different kernel-induced Fourier sampling distributions correspond to different kernel parameters, we show that an optimization process in the Fourier domain can be used to identify the different frequency bands that are useful for prediction on training data. Moreover, the application of group Lasso to random feature vectors corresponding to a linear combination of multiple kernels, leads to efficient and scalable reformulations of the standard multiple kernel learning model \cite{Varma09}. In this paper we develop the linear Fourier approximation methodology for both single and multiple gradient-based kernel learning and show that it produces fast and accurate predictors on a complex dataset such as the Visual Object Challenge 2011 (VOC2011).
Open AccessLearning Random Kernel Approximations for Object Recognition
Approximations based on random Fourier features have recently emerged as an efficient and formally consistent methodology to design large-scale kernel machines. By expressing the kernel as a Fourier expansion, features are generated based on a finite set of random basis projections, sampled from the Fourier transform of the kernel, with inner products that are Monte Carlo approximations of the original kernel. Based on the observation that different kernel-induced Fourier sampling distributions correspond to different kernel parameters, we show that an optimization process in the Fourier domain can be used to identify the different frequency bands that are useful for prediction on training data. Moreover, the application of group Lasso to random feature vectors corresponding to a linear combination of multiple kernels, leads to efficient and scalable reformulations of the standard multiple kernel learning model \cite{Varma09}. In this paper we develop the linear Fourier approximation methodology for both single and multiple gradient-based kernel learning and show that it produces fast and accurate predictors on a complex dataset such as the Visual Object Challenge 2011 (VOC2011).
- Open Access
Generalized Boundaries from Multiple Image Interpretations
Boundary detection is essential for a variety of computer vision tasks such as segmentation and recognition. In this paper we propose a unified formulation and a novel algorithm that are applicable to the detection of different types of boundaries, such as intensity edges, occlusion boundaries or object category specific boundaries. Our formulation leads to a simple method with state-of-the-art performance and significantly lower computational cost than existing methods. We evaluate our algorithm on different types of boundaries, from low-level boundaries extracted in natural images, to occlusion boundaries obtained using motion cues and RGB-D cameras, to boundaries from soft-segmentation. We also propose a novel method for figure/ground soft-segmentation that can be used in conjunction with our boundary detection method and improve its accuracy at almost no extra computational cost.
Open AccessGeneralized Boundaries from Multiple Image Interpretations
Boundary detection is essential for a variety of computer vision tasks such as segmentation and recognition. In this paper we propose a unified formulation and a novel algorithm that are applicable to the detection of different types of boundaries, such as intensity edges, occlusion boundaries or object category specific boundaries. Our formulation leads to a simple method with state-of-the-art performance and significantly lower computational cost than existing methods. We evaluate our algorithm on different types of boundaries, from low-level boundaries extracted in natural images, to occlusion boundaries obtained using motion cues and RGB-D cameras, to boundaries from soft-segmentation. We also propose a novel method for figure/ground soft-segmentation that can be used in conjunction with our boundary detection method and improve its accuracy at almost no extra computational cost.
- 19 November 2011
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 98 (3) , 243-262
Object Recognition by Sequential Figure-Ground Ranking
- 19 November 2011
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 98 (3) , 243-262
Object Recognition by Sequential Figure-Ground Ranking
- Open Access
Image Segmentation by Discounted Cumulative Ranking on Maximal Cliques
We propose a mid-level image segmentation framework that combines multiple figure-ground hypothesis (FG) constrained at different locations and scales, into interpretations that tile the entire image. The problem is cast as optimization over sets of maximal cliques sampled from the graph connecting non-overlapping, putative figure-ground segment hypotheses. Potential functions over cliques combine unary Gestalt-based figure quality scores and pairwise compatibilities among spatially neighboring segments, constrained by T-junctions and the boundary interface statistics resulting from projections of real 3d scenes. Learning the model parameters is formulated as rank optimization, alternating between sampling image tilings and optimizing their potential function parameters. State of the art results are reported on both the Berkeley and the VOC2009 segmentation dataset, where a 28% improvement was achieved.
Open AccessImage Segmentation by Discounted Cumulative Ranking on Maximal Cliques
We propose a mid-level image segmentation framework that combines multiple figure-ground hypothesis (FG) constrained at different locations and scales, into interpretations that tile the entire image. The problem is cast as optimization over sets of maximal cliques sampled from the graph connecting non-overlapping, putative figure-ground segment hypotheses. Potential functions over cliques combine unary Gestalt-based figure quality scores and pairwise compatibilities among spatially neighboring segments, constrained by T-junctions and the boundary interface statistics resulting from projections of real 3d scenes. Learning the model parameters is formulated as rank optimization, alternating between sampling image tilings and optimizing their potential function parameters. State of the art results are reported on both the Berkeley and the VOC2009 segmentation dataset, where a 28% improvement was achieved.
- 12 February 2009
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 87 (1-2) , 28-52
Twin Gaussian Processes for Structured Prediction
- 12 February 2009
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 87 (1-2) , 28-52
Twin Gaussian Processes for Structured Prediction