French Institute for Research in Computer Science and Automation

About: French Institute for Research in Computer Science and Automation is a government organization based out in Le Chesnay, France. It is known for research contribution in the topics: Context (language use) & Population. The organization has 13012 authors who have published 38653 publications receiving 1318995 citations. The organization is also known as: INRIA & Institute for national research in information science and automatic control.

Learning to Parse Pictures of People

Abstract: Detecting people in images is a key problem for video indexing, browsing and retrieval. The main difficulties are the large appearance variations caused by action, clothing, illumination, viewpoint and scale. Our goal is to find people in static video frames using learned models of both the appearance of body parts (head, limbs, hands), and of the geometry of their assemblies. We build on Forsyth & Fleck's general 'body plan' methodology and Felzenszwalb & Huttenlocher's dynamic programming approach for efficiently assembling candidate parts into 'pictorial structures'. However we replace the rather simple part detectors used in these works with dedicated detectors learned for each body part using SupportVector Machines (SVMs) or RelevanceVector Machines (RVMs). We are not aware of any previous work using SVMs to learn articulated body plans, however they have been used to detect both whole pedestrians and combinations of rigidly positioned subimages (typically, upper body, arms, and legs) in street scenes, under a wide range of illumination, pose and clothing variations. RVMs are SVM-like classifiers that offer a well-founded probabilistic interpretation and improved sparsity for reduced computation. We demonstrate their benefits experimentally in a series of results showing great promise for learning detectors in more general situations.

Exact Support Recovery for Sparse Spikes Deconvolution

Abstract: This paper studies sparse spikes deconvolution over the space of measures We focus on the recovery properties of the support of the measure (ie, the location of the Dirac masses) using total variation of measures (TV) regularization This regularization is the natural extension of the $$\ell ^1$$l1 norm of vectors to the setting of measures We show that support identification is governed by a specific solution of the dual problem (a so-called dual certificate) having minimum $$L^2$$L2 norm Our main result shows that if this certificate is non-degenerate (see the definition below), when the signal-to-noise ratio is large enough TV regularization recovers the exact same number of Diracs We show that both the locations and the amplitudes of these Diracs converge toward those of the input measure when the noise drops to zero Moreover, the non-degeneracy of this certificate can be checked by computing a so-called vanishing derivative pre-certificate This proxy can be computed in closed form by solving a linear system Lastly, we draw connections between the support of the recovered measure on a continuous domain and on a discretized grid We show that when the signal-to-noise level is large enough, and provided the aforementioned dual certificate is non-degenerate, the solution of the discretized problem is supported on pairs of Diracs which are neighbors of the Diracs of the input measure This gives a precise description of the convergence of the solution of the discretized problem toward the solution of the continuous grid-free problem, as the grid size tends to zero

Harmonic decomposition of audio signals with matching pursuit

Abstract: We introduce a dictionary of elementary waveforms, called harmonic atoms, that extends the Gabor dictionary and fits well the natural harmonic structures of audio signals. By modifying the "standard" matching pursuit, we define a new pursuit along with a fast algorithm, namely, the fast harmonic matching pursuit, to approximate N-dimensional audio signals with a linear combination of M harmonic atoms. Our algorithm has a computational complexity of O(MKN), where K is the number of partials in a given harmonic atom. The decomposition method is demonstrated on musical recordings, and we describe a simple note detection algorithm that shows how one could use a harmonic matching pursuit to detect notes even in difficult situations, e.g., very different note durations, lots of reverberation, and overlapping notes.

Unifying discriminative visual codebook generation with classifier training for object category recognition

Abstract: The idea of representing images using a bag of visual words is currently popular in object category recognition. Since this representation is typically constructed using unsupervised clustering, the resulting visual words may not capture the desired information. Recent work has explored the construction of discriminative visual codebooks that explicitly consider object category information. However, since the codebook generation process is still disconnected from that of classifier training, the set of resulting visual words, while individually discriminative, may not be those best suited for the classifier. This paper proposes a novel optimization framework that unifies codebook generation with classifier training. In our approach, each image feature is encoded by a sequence of ldquovisual bitsrdquo optimized for each category. An image, which can contain objects from multiple categories, is represented using aggregates of visual bits for each category. Classifiers associated with different categories determine how well a given image corresponds to each category. Based on the performance of these classifiers on the training data, we augment the visual words by generating additional bits. The classifiers are then updated to incorporate the new representation. These two phases are repeated until the desired performance is achieved. Experiments compare our approach to standard clustering-based methods and with state-of-the-art discriminative visual codebook generation. The significant improvements over previous techniques clearly demonstrate the value of unifying representation and classification into a single optimization framework.

Genetic Network Analyzer: qualitative simulation of genetic regulatory networks.

Abstract: Motivation: The study of genetic regulatory networks has received a major impetus from the recent development of experimental techniques allowing the measurement of patterns of gene expression in a massively parallel way. This experimental progress calls for the development of appropriate computer tools for the modeling and simulation of gene regulation processes. Results: We present Genetic Network Analyzer (GNA), a computer tool for the modeling and simulation of genetic regulatory networks. The tool is based on a qualitative simulation method that employs coarse-grained models of regulatory networks. The use of GNA is illustrated by a case study of the network of genes and interactions regulating the initiation of sporulation in Bacillus subtilis. Availability: GNA and the model of the sporulation network are available at http://www-helix.inrialpes.fr/gna.