Search

International audience; An analytical approach based on the multivariate analysis of on-line pyrolysis-gas chromatography/mass spectrometry (Py-GC/MS) data is proposed for the identification of traditional East Asian handmade papers from different fiber material origins. This approach utilized several biomarkers detected during Py-GC/MS analysis of the paper samples. At first, the total ion chromatogram (TIC) was taken as the response and then the extracted ion chromatograms (EICs) were considered to improve the discrimination of papers. The influence of different data pretreatment (raw responses vs normalized values) including different weighting of the variables (weighting as 1 vs weight as 1/STD, where STD stands for standard deviation) for principal component analysis was also investigated. The results showed that compared to the commonly used microscopy techniques, the Py-GC/MS technique proved to be able to discriminate against handmade paper materials that have similar microscopic morphologies such as Morus species vs. Broussonetia species. The data pretreatment influenced the PCA modeling: the analysis based on normalized values showed more interpretable PCA group features for Moraceae species. PCA without weighting resulted unsurprisingly in discrimination through the presence of high intensity response biomarkers, while when applying weight as 1/STD, PCA loading plot was shown to provide a group of compounds, most of them being present at low levels, to be discriminating. Additionally, the characteristic EICs can provide data matrix for statistical analysis avoiding the interference from co-eluting compound and background compared to the data matrix obtained from the TIC. As a result, a quick Py-GC/MS based handmade paper identification procedure using PCA modeling of characteristic EICs was for the first time proposed in the identification of traditional East Asian handmade papers. This procedure could be very beneficial in cultural heritage applications.

International audience; This paper investigates the classification of photographic paper tex-tures using visual descriptors. Such classification is called fine grain due to the very low inter-class variability. We propose a novel image representation for photographic paper texture categorization, relying on the incorporation of a powerful local descriptor into an efficient higher-order model deviation where texture is represented by com-puting statistics on the occurrences of specific local visual patterns. We perform an evaluation on two different challenging datasets of photographic paper textures and show such advanced methods in-deed outperforms existing descriptors.

International audience; In this note, we point out two major errors in the paper "Minimizing total tardiness on parallel machines with preemptions" by Kravchenko and Werner (2012). More precisely, they claimed to have proved that both problems P|pmtn|∑T j and P|r j ,p j =p,pmtn|∑T j are NP -Hard. We give a counter-example to their proofs, letting the complexity of these two problems open.

We deal with the 3D reconstruction of deformed paperlike surfaces given a template and a single perspective image, for which the internal camera parameters are known. The general problem is ill-posed. We show that when the surface rulings are parallel the problem is well-posed. Given a procedure to recover the rulings direction, this particular problem is equivalent to the reconstruction of a 2D curve seen from a set of ID camera pairs given a ID template. Paper can be physically modeled by exploiting local properties. This allows us to formulate the reconstruction problem by non linear variational optimization. We provide experimental results which validate our approach on simulated and real data.

We deliver a short overview of di erent centrality measures and influence concepts in social networks, and present the relation-algebraic approach to the concepts of power and influence. First, we briefly discuss four kinds of measures of centrality: the ones based on degree, closeness, betweenness, and the eigenvector-related measures. We consider centrality of a node and of a network. Moreover, we give a classi cation of the centrality measures based on a topology of network flows. Furthermore, we present a certain model of influence in a social network and discuss some applications of relation algebra and RelView to this model.

Smoothly bent paper-like surfaces are developable. They are however difficult to minimally parameterize since the number of meaningful parameters is intrinsically dependent on the actual deformation. Previous generative models are either incomplete, i.e. limited to subsets of developable surfaces, or depend on huge parameter sets. We propose a generative model governed by a quasi-minimal set of intuitive parameters, namely rules and angles. More precisely, a flat mesh is bent along guiding rules, while a number of extra rules controls the level of smoothness. The generated surface is guaranteed to be developable. A fully automatic multi-camera three dimensional reconstruction algorithm, including model-based bundle-adjustment, demonstrates our model on real images.

Book review ; Da Ruan and Chongfu Huang editors; International audience

International audience; This short paper discusses the contributions made to the featured section on Low Quality Data. We further refine the distinction between the ontic and epistemic views of imprecise data in statistics. We also question the extent to which likelihood functions can be viewed as belief functions. Finally we comment on the data disambiguation effect of learning methods, relating it to data reconciliation problems.

Edited by R. Mesiar and S. Montes; International audience; This position paper discusses the role of the existing body of fuizzy set aggregation operations in various kinds of problems where the process of fusion of items coming from several sources is central. Several kinds of membership functions can be useful according to the nature of the information to be merged: numerical vs. ordinal inputs, preferences vs. uncertain data, observations vs. constraints. In cach case, some aggregation operations look more plausible or feasible than others. The aim of this discussion is to suggest directions for putting at work the results of recent mathernatical investigations in the structure of aggregation operations.

International audience; This paper accounts for the semantics of plurality, in particular, the accessibility relation for plural anaphoras. Two types of dis- course antecedents formations, inherited from the classical treatment [14], namely summation and abstraction, are studied in detail. Solutions for each phenomenon are provided respectively by introducing two new functions Sum and Abs, for obtaining the semantic interpretations. The technical background in this paper is based on a recently proposed dynamic semantic framework [9], which pertains a style of the traditional Montague Grammar and the principle of compositionality, without adding any new concept to classical logic.

Discrimination in selection problems such as hiring or college admission is often explained by implicit bias from the decision maker against disadvantaged demographic groups. In this paper, we consider a model where the decision maker receives a noisy estimate of each candidate's quality, whose variance depends on the candidate's group -- we argue that such differential variance is a key feature of many selection problems. We analyze two notable settings: in the first, the noise variances are unknown to the decision maker who simply picks the candidates with the highest estimated quality independently of their group; in the second, the variances are known and the decision maker picks candidates having the highest expected quality given the noisy estimate. We show that both baseline decision makers yield discrimination, although in opposite directions: the first leads to underrepresentation of the low-variance group while the second leads to underrepresentation of the high-variance group. We study the effect on the selection utility of imposing a fairness mechanism that we term the $\gamma$-rule (it is an extension of the classical four-fifths rule and it also includes demographic parity). In the first setting (with unknown variances), we prove that under mild conditions, imposing the $\gamma$-rule increases the selection utility -- here there is no trade-off between fairness and utility. In the second setting (with known variances), imposing the $\gamma$-rule decreases the utility but we prove a bound on the utility loss due to the fairness mechanism., Comment: Accepted for publication in the Artificial Intelligence Journal. This paper is an extended version of our paper arXiv:2006.13699: we added a Bayesian-optimal baseline (in addition to the group-oblivious baseline) and generalized the model by assuming a group-dependent distribution of quality and an implicit bias; but we removed the part on two-stage selection

This paper addresses the structurally constrained sparse decomposition of multi-dimensional signals onto overcomplete families of vectors, called dictionaries. The contribution of the paper is threefold. Firstly, a generic spatio-temporal regularization term is designed and used together with the standard ź 1 regularization term to enforce a sparse decomposition preserving the spatio-temporal structure of the signal. Secondly, an optimization algorithm based on the split Bregman approach is proposed to handle the associated optimization problem, and its convergence is analyzed. Our well-founded approach yields same accuracy as the other algorithms at the state of the art, with significant gains in terms of convergence speed. Thirdly, the empirical validation of the approach on artificial and real-world problems demonstrates the generality and effectiveness of the method. On artificial problems, the proposed regularization subsumes the Total Variation minimization and recovers the expected decomposition. On the real-world problem of electro-encephalography brainwave decomposition, the approach outperforms similar approaches in terms of P300 evoked potentials detection, using structured spatial priors to guide the decomposition. HighlightsA sparse structured decomposition method is proposed for multi-dimensional signals.Knowledge priors are encoded in a regularization to obtain plausible representations.The proposed split-Bregman based method outperforms counterparts in terms of speed.The approach is applied to EEG denoising for the extraction of P300 potentials.

International audience; This paper aims to propose two main contributions in the field of multivariate data analysis through the possibility theory. The first proposition is the definition of a generalized family of multivariate elliptical possibility distributions. These distributions have been derived from a consistent probability-possibility transformation over the family of so-called elliptical probability distributions. The second contribution proposed by the paper is the definition of two divergence measures between possibilistic distributions. We prove that a symmetric version of the Kullback-Leibler divergence guarantees all divergence properties when related to the space of possibility distributions. We further derive analytical expressions of the latter divergence and of the Hellinger divergence for certain possibility distributions pertaining to the elliptical family proposed, especially the normal multivariate possibility divergence in two dimensions. Finally, this paper provides an illustration of the developed possibilistic tools in an application of bi-band change detection between optical satellite images.

Submission to Reconnaissance de Formes et Intelligence Artificielle (RFIA) 2014, France (2014) - Paper ID 16 / Paper ID114; [Résumé en français] Cet article présente une nouvelle approche appelée bag-of-bags of words (BBoW) pour la recherche d'images par le contenu (CBIR). Il s'agit d'une extension du modèle classique dit sac-de-mots (bag of words - BoW). Dans notre approche, une image est représentée par un graphe placé sur une grille régulière de pixels de l'image. Les poids sur les arêtes dépendent de caractéristiques locales de couleur. Le graphe est découpé en un nombre fixe de régions qui constituent une partition irrégulière de l'image par la méthode Normalized Cuts. Enfin, chaque partition est représentée par sa propre signature suivant le même schéma que le BoW. Une image est donc décrite par un ensemble de signatures qui sont ensuite combinées pour la recherche d'images similaires dans une base de données. Contrairement aux méthodes existantes telle que Spatial Pyramid Matching (SPM), le modèle BBoW proposé ne repose pas sur l'hypothèse que des parties similaires d'une scène apparaissent toujours au même endroit dans des images d'une même catégorie. L'extension de cette méthode à une approche multi-échelle, appelée Irregular Pyramid Matching (IPM), est également décrite. Les résultats démontrent la qualité de notre approche lorsque les partitions obtenues sont stables au sein d'une même catégorie d'images. Une analyse statistique est menée pour définir concrètement la notion de partition stable. Mots Clef : Recherche d'images par le contenu, coupe de graphes, Normalized Cuts, Sac de mots. [Abstract in English] This paper presents a novel approach, named bag-of-bags of words (BBoW), to address the problem of Content-Based Image Retrieval (CBIR) from image databases. The proposed bag-of-bags of words model extends the classical bag-of-words (BoW) model. An image is represented as a connected full graph of local features on a regular grid. Then irregular partitions (subgraphs) of images are further built via Normalized Cuts. Each subgraph in the partition is then represented by its own signature. Compared to existing methods for image retrieval, such as Spatial Pyramid Matching (SPM), the BBoW model does not assume that similar parts of a scene always appear at the same location in images of the same category. The extension of the proposed model to pyramid gives rise to a method we name irregular pyramid matching (IPM). The experiments demonstrate the strength of our method for image retrieval when the partitions are stable across an image category. The statistical analysis of subgraphs is discussed in the paper. Keywords : Content-based image retrieval, graph partitioning, Normalized Cuts, Bag of words.

This paper treats the estimation of a flat fading Rayleigh channel with Jakes' Doppler spectrum model and slow fading variations. A common method is to use a Kalman filter (KF) based on an auto-regressive model of order p (AR(p)). The parameters of the AR model can be simply tuned by using the correlation matching (CM) criterion. However, the major drawback of this method is that high orders are required to approach the Bayesian Cramer–Rao lower bound. The choice of p together with the tuning of the model parameters is thus critical, and a tradeoff must be found between the numerical complexity and the performance. The reasonable tradeoff arising from setting p = 2 has received much attention in the literature. However, the methods proposed for tuning the model parameters are either based on an extensive grid-search analysis or experimental results, which limits their applicability. A general solution for any scenario is simply missing for p = 2 and this paper aims at filling this gap. We propose using a Minimization of Asymptotic Variance (MAV) criterion, for which a general closed-form formula has been derived for the optimal tuning of the model and the mean square error. This provides deeper insight into the behavior of the KF with respect to the channel state (Doppler frequency and signal to noise ratio). Moreover, the paper interprets the proposed solution, especially the dependence of the shape of the optimal AR(2) spectrum on the channel state. Analytic and numerical comparisons with first- and second-order algorithms in the literature are also performed. Simulation results show that the proposed AR(2)-MAV model performs better than the literature and similarly to AR(p)-CM models with p ≥ 15 .

6 pages; International audience; It has been know for at least one decade [1] that functional MRI time series display long-memory properties, such as power-law scaling in the frequency spectrum. Concomitantly, multivariate modelfree analysis of spatial patterns , such as spatial Independent Component Analysis (sICA) [2], has been successfully used to segment from spontaneous activity Resting-State Networks (RSN) that correspond to known brain function. As recent neuroscientific studies suggest a link between spectral properties of brain activity and cognitive processes [3], a burning question emerges: can temporal scaling properties offer new markers of brain states encoded in these large scale networks? In this paper, we combine two recent methodologies: group-level canonical ICA for multi-subject segmentation of brain network, and wavelet leader-based multifractal formalism for the analysis of RSN scaling properties. We identify the brain networks that elicit self-similarity or multifractality and explore which spectral properties correspond specifically to known functionallyrelevant processes in spontaneous activity.

This paper proposes an analysis of and a reflection on interval arithmetic (IA) and its extension to gradual interval arithmetic (GIA). Through this reflection, an overview of a part of IA that is directly related to fuzzy interval arithmetic (FIA) is analyzed, compared, and categorized according to two main families of IA: standard interval arithmetic (SIA) and instantiated interval arithmetic (IIA). Furthermore, SIA and IIA visions represent two viewpoints of computation that are different and they will cause modifications in interval interpretation and manipulation. This vision is essential in understanding the philosophy of IA and GIA computational mechanisms. The contribution of this paper is twofold. First, according to SIA and IIA visions, an analysis and a classification of a part of IAs are given. Equivalences and links between these IAs are analyzed and established. Second, an extension of IA to the gradual context is proposed. The GIA extension provides a new interpretation of FIA according to the gradual representation.

Best paper award in "Real world applications"; International audience; Local image features can provide the basis for robust and invariant recognition of objects and scenes. Therefore, compact and distinctive representations of local shape and appearance has become invaluable in modern computer vision. In this work,we study a local descriptor based on the Hölder exponent, a measure of signal regularity. The proposal is to find an optimal number of dimensions for the descriptor using a genetic algorithm (GA). To guide the GA search, fitness is computed based on the performance of the descriptor when applied to standard region matching problems. This criterion is quantified using the F-Measure, derived from recall and precision analysis. Results show that it is possible to reduce the size of the canonical Hölder descriptor without degrading the quality of its performance. In fact, the best descriptor found through the GA search is nearly 70% smaller and achieves similar performance on standard tests.

International audience; Analogy making is widely recognized as a powerful kind of common-sense reasoning. This paper primarily addresses the relevance of analogical reasoning for recommender systems, which aim at providing suggestions of interest for end-users. A well-known form of analogy is that of analogical proportions, which are statements of the form “a is to b as c is to d“. Encouraged by good results obtained in classification by analogical proportion-based techniques, we study the potential use of analogy as the main underlying principle for implementing rating prediction algorithms. We investigate two ways of using analogical proportions for that purpose. First, we exploit proportions between four users, each described by their respective ratings on items that they have commonly rated. The second prediction method only relies on pairs of users and pairs of items, and leads to better performances. Finally, in order to know to what extent it may be meaningful to apply analogical methods in data analysis, we address the problem of mining analogical proportions between users (or items) in ratings datasets. Altogether, this paper initiates a general investigation of the potential use of analogical proportions for recommendation purposes.

A very large amount of work in Natural Language Processing (NLP) use tree structure as the first class citizen mathematical structures to represent linguistic structures, such as parsed sentences or feature structures. However, some linguistic phenomena do not cope properly with trees; for instance, in the sentence ‘Max decides to leave,’ ‘Max’ is the subject of the both predicates ‘to_decide’ and ‘to_leave’. Tree-based linguistic formalisms generally use some encoding to manage sentences like the previous example. In former papers (Bonfante et al. 2011; Guillaume and Perrier 2012), we discussed the interest to use graphs rather than trees to deal with linguistic structures, and we have shown how Graph Rewriting could be used for their processing, for instance in the transformation of the sentence syntax into its semantics. Our experiments have shown that Graph Rewriting applications to NLP do not require the full computational power of the general Graph Rewriting setting. The most important observation is that all graph vertices in the final structures are in some sense ‘predictable’ from the input data, and so we can consider the framework of Non-size increasing Graph Rewriting. In our previous papers, we have formally described the Graph Rewriting calculus we used and our purpose here is to study the theoretical aspect of termination with respect to this calculus. Given that termination is undecidable in general, we define termination criterions based on weight, we prove the termination of weighted rewriting systems, and we give complexity bounds on derivation lengths for these rewriting systems.

[EN] This work investigates the characterization of bright lesions in retinal fundus images using texture analysis techniques. Exudates and drusen are evidences of retinal damage in diabetic retinopathy (DR) and age-related macular degeneration (AMD) respectively. An automatic detection of pathological tissues could make possible an early detection of these diseases. In this work, fractal analysis is explored in order to discriminate between pathological and healthy retinal texture. After a deep preprocessing step, in which spatial and colour normalization are performed, the fractal dimension is extracted locally by computing the Hurst exponent (H) along different directions. The greyscale image is described by the increments of the fractional Brownian motion model and the H parameter is computed by linear regression in the frequency domain. The ability of fractal dimension to detect pathological tissues is demonstrated using a home-made system, based on fractal analysis and Support Vector Machine, able to achieve around a 70% and 83% of accuracy in E-OPHTHA and DIARETDB1 public databases respectively. In a second experiment, the fractal descriptor is combined with texture information, extracted by the Local Binary Patterns, improving the bright lesion detection. Accuracy, sensitivity and specificity values higher than 89%, 80% and 90% respectively suggest that the method presented in this paper is a robust algorithm for describing retina texture and can be useful in the automatic detection of DR and AMD., This paper was supported by the European Union's Horizon 2020 research and innovation programme under the Project GALAHAD [H2020-ICT-2016-2017, 732613]. In addition, this work was partially funded by the Ministerio de Economia y Competitividad of Spain, Project SICAP [DPI2016-77869-C2-1-R]. The work of Adrian Colomer has been supported by the Spanish Government under a FPI Grant [BES-2014-067889]. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.

The paper deals with regression problems, in which the nonsmooth target is assumed to switch between different operating modes. Specifically, piecewise smooth (PWS) regression considers target functions switching deterministically via a partition of the input space, while switching regression considers arbitrary switching laws. The paper derives generalization error bounds in these two settings by following the approach based on Rademacher complexities. For PWS regression, our derivation involves a chaining argument and a decomposition of the covering numbers of PWS classes in terms of the ones of their component functions and the capacity of the classifier partitioning the input space. This yields error bounds with a radical dependency on the number of modes. For switching regression, the decomposition can be performed directly at the level of the Rademacher complexities, which yields bounds with a linear dependency on the number of modes. By using once more chaining and a decomposition at the level of covering numbers, we show how to recover a radical dependency. Examples of applications are given in particular for PWS and swichting regression with linear and kernel-based component functions., This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice,after which this version may no longer be accessible

In this paper, we address the problem of robustly recovering several instances of a curve model from a single noisy data set with outliers. Using M-estimators revisited in a Lagrangian formalism, we derive an algorithm that we call Simultaneous Multiple Robust Fitting (SMRF), which extends the classical Iterative Reweighted Least Squares algorithm (IRLS). Compared to the IRLS, it features an extra probability ratio, which is classical in clustering algorithms, in the expression of the weights. Potential numerical issues are tackled by banning zero probabilities in the computation of the weights and by introducing a Gaussian prior on curves coefficients. Applications to camera calibration and lane-markings tracking show the effectiveness of the SMRF algorithm, which outperforms classical Gaussian mixture model algorithms in the presence of outliers.

International audience; In this paper, we propose a new approach for symbol recognition using structural signatures and a Galois Lattice as classifier. The structural signatures are based on topological graphs computed from segments which are extracted from the symbol images by using an adapted Hough transform. These structural signatures, which can be seen as dynamic paths which carry high level information, are robust towards various transformations. They are classified by using a Galois Lattice as a classifier. The performances of the proposed approach are evaluated on the GREC03 symbol database and the experimental results we obtain are encouraging.

International audience; This paper describes a new approach to analyze hand gestures, based on an experimental approximation of the shape and kinematics of compressed arm trajectories. The motivation of such a model is on the one hand the reduction of the gesture data, and on the other hand the possibility to segment gestures into meaningful units, yielding to an analysis tool for gesture coding and synthesis. We show that the measures of the inverse of the distance between adaptive samples and velocity estimated at these points are respectively correlated to the instantaneous curvature and tangential velocity directly computed on motion capture data. Based on these correlation results, we propose a new way to automatically segment hand gestures. We show also that this approach can be applied to a global analysis / synthesis framework, useful for automatic animation of virtual characters performing sign langue gestures.

International audience; The present paper deals with gas concentration monitoring based on an electronic nose. The proposed approach investigates two regression methods for gas concentration estimation: the first is the most used in gas quantification with electronic nose and known as the partial least squares (PLS) and the second, known as the support vector machine (SVM) regression, is recently used by the electronic nose community. Data used in this work are collected using an E-nose device developed in our laboratory and responding to various concentrations of pine essential oil vapours. The comparison between the two regression methods studied in this paper is related to the accuracy, the universality as well as the number of samples needed for learning. The results are analyzed in order to select the more suitable prediction model for gas concentration estimation.

International audience; By bridging uncompressed-domain saliency detection and MPEG-4 AVC compression principles, the present paper advances a methodological framework for extracting the saliency maps directly from the stream syntax elements. In this respect, inside each GOP, the intensity, color, orientation and motion elementary saliency maps are related to the energy of the luma coefficients, to the energy of chroma coefficients, to the gradient of the prediction modes and to the amplitude of the motion vectors, respectively. The three spatial saliency maps are pooled according to an average formula, while the static-temporal fusion is achieved by six different formulas. The experiments consider both ground-truth and applicative evaluations. The ground-truth benchmarking investigates the relation between the predicted MPEG-4 AVC saliency map and the actual human saliency, captured by eye-tracking devices. It is based on two corpora (representing density fixation maps and saccade locations), two objective criteria (related to the closeness between the predicted and the real saliency maps and to the difference between the behavior of the predicted saliency map in fixation and random locations), two objective measures (KLD – the Kullback Leibler Divergence and AUC – the Area Under the ROC Curve) and 5 state-of-the-art saliency models (3 acting in spatial domain and 2 acting in compressed domain). The applicative validation is carried out by integrating the MPEG-4 AVC saliency map into a robust watermarking application. As an overall conclusion, the paper demonstrates that although the MPEG-4 AVC standard does not explicitly relies on any visual saliency principle, its stream syntax elements preserve this property. Four main benefits for the MPEG-4 AVC based saliency extraction are thus brought to light: (1) it outperforms (or, at least, is as good as) state-of-the-art uncompressed domain methods, (2) it allows significant gains to be obtained in watermarking transparency (for prescribed data payload and robustness), (3) it is less sensitive to the randomness in the processed visual content, and (4) it has a linear computational complexity. For instance, the ground truth results exhibit absolute relative gains between 60% and 164% in KLD, between 17% and 21% in AUC, and relative gains in KLD sensitivity between 1.18 and 6.12 and in AUC sensitivity between 1.06 and 33.7; the applicative validation brings to light transparency gains up to 10 dB in PSNR.

Sparse versions of principal component analysis (PCA) have imposed themselves as simple, yet powerful ways of selecting relevant features of high-dimensional data in an unsupervised manner. However, when several sparse principal components are computed, the interpretation of the selected variables is difficult since each axis has its own sparsity pattern and has to be interpreted separately. To overcome this drawback, we propose a Bayesian procedure called globally sparse probabilistic PCA (GSPPCA) that allows to obtain several sparse components with the same sparsity pattern. This allows the practitioner to identify the original variables which are relevant to describe the data. To this end, using Roweis' probabilistic interpretation of PCA and a Gaussian prior on the loading matrix, we provide the first exact computation of the marginal likelihood of a Bayesian PCA model. To avoid the drawbacks of discrete model selection, a simple relaxation of this framework is presented. It allows to find a path of models using a variational expectation-maximization algorithm. The exact marginal likelihood is then maximized over this path. This approach is illustrated on real and synthetic data sets. In particular, using unlabeled microarray data, GSPPCA infers much more relevant gene subsets than traditional sparse PCA algorithms., Comment: An earlier version of this paper appeared in the Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016)

A fast nonparametric procedure for classifying functional data is introduced. It consists of a two-step transformation of the original data plus a classifier operating on a low-dimensional space. The functional data are first mapped into a finite-dimensional location-slope space and then transformed by a multivariate depth function into the DD-plot, which is a subset of the unit square. This transformation yields a new notion of depth for functional data. Three alternative depth functions are employed for this, as well as two rules for the final classification in $$[0,1]^2$$ . The resulting classifier has to be cross-validated over a small range of parameters only, which is restricted by a Vapnik–Chervonenkis bound. The entire methodology does not involve smoothing techniques, is completely nonparametric and allows to achieve Bayes optimality under standard distributional settings. It is robust, efficiently computable, and has been implemented in an R environment. Applicability of the new approach is demonstrated by simulations as well as by a benchmark study.

International audience; This paper addresses the problem of under-determined audio source separation in multichannel reverberant mixtures. We target a semi- blind scenario assuming that the mixing filters are known. Source separation is performed from the time-domain mixture signals in order to accurately model the convolutive mixing process. The source signals are however modeled as latent variables in a time-frequency domain. In a previous paper we proposed to use the modified discrete cosine transform. The present paper generalizes the method to the use of the odd-frequency short-time Fourier transform. In this domain, the source coefficients are modeled as centered complex Gaussian random variables whose variances are structured by means of a non-negative matrix factorization model. The inference procedure relies on a variational expectation-maximization algorithm. In the experiments we discuss the choice of the source representation and we show that the proposed approach outperforms two methods from the literature.

International audience; In this paper, we propose a complete scheme to control a mirror, using a visual servoing scheme, using lines as a set of visual features. Considering the equations of the projection of the reflection of a lines on a mirror, this paper introduces the theoretical background that allows to control the mirror using visual information. Experiments using a mirror mounted on the end-effector of a 6 d.o.f robot validate the proposed approach.

International audience; Regularized Tyler Estimator's (RTE) have raised attention over the past years due to their attractive performance over a wide range of noise distributions and their natural robustness to outliers. Developing adaptive methods for the selection of the regularisation parameter α is currently an active topic of research. Indeed, the bias-performance compromise of RTEs highly depends on the considered application. Thus, finding a generic rule that is optimal for every criterion and/or data configurations is not straightforward. This issue is addressed in this paper for undersampled configurations (number of samples lower than the dimension of the data). The paper proposes a new regularisation parameter selection based on a subspace reduction approach. The performance of this method is investigated in terms of estimation accuracy and for adaptive detection purposes, both on simulation and real data.

International audience; In this paper, we aim to blindly calibrate the responses of a sensor network whose outputs are possibly corrupted by outliers. In particular, we extend some well-known nullspace-based blind calibration approaches, proposed for fixed sensors with affine responses—i.e., with unknown gain and offset for each sensor—to that difficult case. These state-of-the-art approaches assume that the true data lie in a known lower dimensional subspace, so that in practice sensors can be calibrated by projection of the uncalibrated observations to this subspace. A robust extension was recently proposed in order to provide less sensitivity to noise. In this paper, we show that such methods (including the robust extensions) are very sensitive to outliers and we propose new extensions able to deal with such issues. For that purpose, we assume the outliers to be rare events, which can be modeled as a sparse contribution to the low-rank observed data. Using such an assumption, we separate sparse outliers from the low-rank data, so that we can perform calibration. We show that the proposed approach is able to handle up to 10% of outliers in the data without major impact on the calibration accuracy while state-of-the-art methods are already sensitive to the presence of one unique outlier.

Best Paper Award; International audience; This paper proposes a novel audiovisual tracking approach that exploits constructively audio and visual modalities in order to estimate trajectories of multiple people in a joint state space. The tracking problem is modeled using a sequential Bayesian filtering framework. Within this framework, we propose to represent the posterior density with a Gaussian Mixture Model (GMM). To ensure that a GMM representation can be retained sequentially over time, the predictive density is approximated by a GMM using the Unscented Transform. While a density interpolation technique is introduced to obtain a continuous representation of the observation likelihood, which is also a GMM. Furthermore, to prevent the number of mixtures from growing exponentially over time, a density approximation based on the Expectation Maximization (EM) algorithm is applied, resulting in a compact GMM representation of the posterior density. Recordings using a camcorder and microphone array are used to evaluate the proposed approach, demonstrating significant improvements in tracking performance of the proposed audiovisual approach compared to two benchmark visual trackers.

The paper introduces a new method for Blind Source Separation (BSS) in noisy instantaneous mixtures of both independent or dependent source component signals. This approach is based on the minimization of a regularized criterion. Precisely, it consists in combining the total variation method for denoising with the Kullback-Leibler divergence between copula densities. The latter takes advantage of the copula to model the structure of the dependence between signal components. The obtained algorithm achieves separation in a noisy context where standard BSS methods fail. The efficiency and robustness of the proposed approach are illustrated by numerical simulations. HighlightsThe paper provides a new Blind source separation for noisy mixtures of independent/dependent sources.The proposed approach combine TV-regularization for denoising and separation by minimizing TV-regularized Kullback-Leibler divergence between copulas.The efficiency and robustness properties of the proposed approach have been illustrated by simulations.

Possibilistic networks offer a qualitative approach for modeling epistemic uncertainty. Their practical implementation requires the specification of conditional possibility tables, as in the case of Bayesian networks for probabilities. The elicitation of probability tables by experts is made much easier by means of noisy logical gates that enable multidimensional tables to be constructed from the knowledge of a few parameters. This paper presents the possibilistic counterparts of usual noisy connectives (and, or, max, min, ). Their interest and limitations are illustrated on an example taken from a human geography modeling problem. The difference of behavior between probabilistic and possibilistic connectives is discussed in detail. Results in this paper may be useful to bring possibilistic networks closer to applications. A definition of uncertain logical gates in possibilistic networks and their detailed expressions including the leaky cases.A comparison with noisy gates in probabilistic networks.An illustrative example of using such gates on an application to human geography.

International audience; In this paper we investigate the problem of optimal games played over networks and focus our attention on the importance of the topology of communication between the agents. We consider a set of agents which are connected via a directed communication graph: each agent in the network has to optimize a local cost function which depends on the agent's decision and on the decision taken by the set of its neighbors, giving rise to a Network Game. We show that, by condensing the strongly connected components of the control graph into super-nodes, it is possible to give a hierarchical interpretation to the Network Game. Then we apply the proposed architecture to the case of a large scale network which takes inspiration by traffic networks application.

International audience; In this paper, the problem of convolutive source separation via multimodal soft Nonnegative Matrix Co-Factorization (NMCF) is addressed. Different aspects of a phenomenon may be recorded by sensors of different types (e.g., audio and video of human speech), and each of these recorded signals is called a modality. Since the underlying phenomenon of the modalities is the same, they have some similarities. Especially, they usually have similar time changes. It means that changes in one of them usually correspond to changes in the other one. So their active or inactive periods are usually similar. Assuming this similarity, it is expected that the activation coefficient matrices of their Nonnegative Matrix Factorization (NMF) have a similar form. In this paper, the similarity of the activation coefficient matrices between the modalities is considered for co-factorization. This similarity is used for separation procedure in a soft manner by using penalty terms. This results in more flexibility in the separation procedure. Simulation results and comparison with state-of-the-art algorithms show the effectiveness of the proposed algorithm.

International audience; The notion of tangential cover, based on maximal segments, is a well-known tool to study the geometrical characteristics of a discrete curve. However, it is not robust to noise, while extracted contours from digital images typically contain noise and this makes the geometric analysis tasks on such contours difficult. To tackle this issue, we investigate in this paper a discrete structure, named Adaptive Tangential Cover (ATC), which is based on the notion of tangential cover and on a local noise estimator. More specifically, the ATC is composed of maximal segments with different widths deduced from the local noise values estimated at each point of the contour. Furthermore, a parameter-free algorithm is also presented to compute ATC. This study leads to the proposal of several applications of ATC on noisy digital contours: dominant point detection, contour length estimator, tangent/normal estimator, detection of convex and concave parts. An extension of ATC to 3D curves is also proposed in this paper. The experimental results demonstrate the efficiency of this new notion.

International audience; This paper proposes incremental preference elicitation methods for multicri-teria decision making with a Choquet integral. The Choquet integral is an evaluation function that performs a weighted aggregation of criterion values using a capacity function assigning a weight to any coalition of criteria, thus enabling positive and/or negative interactions among them and covering an important range of possible decision behaviors. However, the specification of the capacity involves many parameters which raises challenging questions, both in terms of elicitation burden and guarantee on the quality of the final recommendation. In this paper, we investigate the incremental elicitation of the capacity through a sequence of preference queries (questions) selected one-by-one using a minimax regret strategy so as to progressively reduce the set of possible capacities until the regret (the worst-case " loss " due to reasoning with only partially specified capacities) is low enough. We propose a new approach designed to efficiently compute minimax regret for the Choquet model and we show how this approach can be used in different settings: 1) the problem of recommending a single alternative, 2) the problem of ranking alternatives from best to worst, and 3) sorting several alternatives into ordered categories. Numerical experiments are provided to demonstrate the practical efficiency of our approach for each of these situations.

International audience; This paper investigates an extension of lightweight ontologies, encoded here in DL-Lite languages, to the product-based possibility theory framework. We first introduce the language (and its associated semantics) used for representing uncertainty in lightweight ontologies. We show that, contrarily to a min-based possibilistic DL-Lite, query answering in a product-based possibility theory is a hard task. We provide equivalent transformations between the problem of computing an inconsistency degree (the key notion in reasoning from a possibilistic DL-Lite knowledge base) and the weighted maximum 2-Horn SAT problem. The last part of the paper provides an encoding of the problem of computing inconsistency degree in product-based possibility DL-Lite as a weighted set cover problem and the use of a greedy algorithm to compute an approximate value of the inconsistency degree. This encoding allows us to provide an approximate algorithm for answering instance checking queries in product-based possibilistic DL-Lite. Experimental studies show the quality of the approximate algorithms for both inconsistency degree computation and instance checking queries

International audience; This paper deals with the difficult problem of video colorization. Methods in the literature are generally based on spatio-temporal video blocks, or on frame to frame color propagation methods, each technique having its own advantages and drawbacks. In this paper , we present both a novel automatic frame-to-frame propagation approach and an interactive correction method within a variational framework. The proposed method propagates colors from an initial colorized frame to the whole grayscale video sequence. The automatic propagation results may be visually unsuitable in some cases. To overcome this limitation, a spatio-temporal functional with a user-guided correction is introduced. Two primal-dual algorithms are designed to solve the proposed variational models. Numerical results show the efficiency and the potentiality of the proposed approach in comparison with state-of-the-art methods.

In this paper, it is argued that, despite its many strengths and undoubted value in science, mathematics also has some weaknesses as a handmaiden for science. There appears to be potential in developing a new mathematics for science (NMFS) which is designed to overcome those weaknesses and to meet more fully the needs of science. As a background to the proposals: 1) The conclusions of a companion paper are noted - that mathematics is, fundamentally, a set of techniques for the compression of information and the application of those techniques; 2) That the effectiveness of mathematics in science is because it provides a means of achieving the compression of information which lies at the heart of science; 3) Since science and mathematics are products of the human intellect, it should not be surprising to find that the workings of the human mind has an influence on both of them; and 4) The significance of information compression in science and mathematics is in line with an abundance of other evidence for the significance of information compression in human learning, perception, and thinking. Continuing the theme of information compression as a unifying principle, the SP theory of intelligence and its realisation in the SP computer model demonstrate how diverse aspects of intelligence may be modelled via information compression within the powerful framework of multiple alignment. An NMFS is proposed, created as an amalgamation of mathematics as it is today with the SP system as it is today, including developments in both areas that are anticipated now. It is envisaged that, for reasons described in the paper, the proposed NMFS will overcome several of the apparent weaknesses in mathematics. In several sections, there is discussion of some possible implications for science of the proposed NMFS, including: potential for the long-sought-after unification of quantum mechanics and general relativity; expansion of the concept of "object" in physics; ambiguity in human perception as an analogy for the concept of superposition in quantum mechanics; the phenomenon of discontinuous dependencies in natural languages as an analogy for nonlocality and entanglement in quantum mechanics; a "waterspout" interpretation for some of the two-slits experiments; potential advantages of the proposed NMFS in the realm of statistics; and its potential to be a vehicle for the representation of all kinds of scientific knowledge, with consequent benefits in the processing of that knowledge.

The accuracy of a text classification method based on a SVM learner depends on the weighting metric used in order to assign a weight to a term. Weighting metrics can be classified as supervised or unsupervised according to whether they use prior information on the number of documents belonging to each category. A supervised metric should be highly informative about the relation of a document term to a category, and discriminative in separating the positive documents from the negative documents for this category. In this paper, we propose 80 metrics never used for the term-weighting problem and compare them to 16 functions of the literature. A large number of these metrics were initially proposed for other data mining problems: feature selection, classification rules and term collocations. While many previous works have shown the merits of using a particular metric, our experience suggests that the results obtained by such metrics can be highly dependent on the label distribution on the corpus and on the performance measures used (microaveraged or macroaveraged $$F_1$$F1-Score). The solution that we propose consists in combining the metrics in order to improve the classification. More precisely, we show that using a SVM classifier which combines the outputs of SVM classifiers that utilize different metrics performs well in all situations. The second main contribution of this paper is an extended term representation for the vector space model that improves significantly the prediction of the text classifier.

Background modeling constitutes the building block of many computer-vision tasks. Traditional schemes model the background as a low rank matrix with corrupted entries. These schemes operate in batch mode and do not scale well with the data size. Moreover, without enforcing spatiotemporal information in the low-rank component, and because of occlusions by foreground objects and redundancy in video data, the design of a background initialization method robust against outliers is very challenging. To overcome these limitations, this paper presents a spatiotemporal low-rank modeling method on dynamic video clips for estimating the robust background model. The proposed method encodes spatiotemporal constraints by regularizing spectral graphs. Initially, a motion-compensated binary matrix is generated using optical flow information to remove redundant data and to create a set of dynamic frames from the input video sequence. Then two graphs are constructed, one between frames for temporal consistency and the other between features for spatial consistency, to encode the local structure for continuously promoting the intrinsic behavior of the low-rank model against outliers. These two terms are then incorporated in the iterative Matrix Completion framework for improved segmentation of background. Rigorous evaluation on severely occluded and dynamic background sequences demonstrates the superior performance of the proposed method over state-of-the-art approaches. 2016 IEEE. Manuscript received July 21, 2016; revised October 14, 2016; accepted November 20, 2016. Date of publication November 23, 2016; date of current version June 4, 2018. This work was supported by the Ministry of Science, ICT and Future Planning, South Korea, under the Information Technology Research Center under Grant IITP-2016-H8601-16-1002 supervised by the Institute for Information & Communications Technology Promotion. This paper was recommended by Associate Editor J. Yuan. (Corresponding author: Soon Ki Jung.) S. Javed and S. K. Jung are with the Virtual Reality Laboratory, School of Computer Science and Engineering, Kyungpook National University, Daegu 41566, South Korea (e-mail: sajid@vr.knu.ac.kr; skjung@knu.ac.kr). Scopus

International audience; This paper addresses the problem of robust covariance matrix (CM) estimation in the context of a disturbance composed of a low rank (LR) heterogeneous clutter plus an additive white Gaussian noise. The LR clutter is modeled by a spherically invariant random vector with assumed high clutter-to-noise ratio. In such a context, adaptive process should require less training samples than classical methods to reach equivalent performance as in a “full rank” clutter configuration. The main issue is that classical robust estimators of the CM cannot be computed in the undersampled configuration. To overcome this issue, the current approach is based on regularization methods. Nevertheless, most of these solutions are enforcing the estimate to be well conditioned, while in our context, it should be LR structured. This paper, therefore, addresses this issue and derives an algorithm to compute the maximum likelihood estimator of the CM for the considered disturbance model. Several relaxations and robust generalizations of the result are discussed. Performance is finally illustrated on numerical simulations and on a space time adaptive processing for airborne radar application.

International audience; In a classical Group Decision-Making (GDM) analysis, the ratings of potential alternatives and the weights of criteria or Decision Makers (DMs) are known precisely. However, for dealing with uncertain situations, the DMs can de ne their opinions inlinguistic variables based on fuzzy sets in industrial selection problems. In this respect, an Interval-Valued Hesitant Fuzzy Set (IVHFS) is the suitable and capable theory that could help the DMs with assigning some interval-valued membership degrees to a candidate or option under a set. This paper introduces a novel Interval-Valued Hesitant Fuzzy Distance-Based Group Decision (IVHF-DBGD) model by a group of DMs, in which the best potential alternative can be appraised and selected among the con icting criteria. In the proposed IVHF-DBGD model, the weight of each criterion is determined by extended IVHF-entropy method along with the DMs' opinions about the criteria's weights. Also, the weight of each DM is computed by a new IVHF-order preference method with the relative closeness. Moreover, this paper introduces a new IVHF-collective index to discriminate among potential alternatives in the selection process. Finally, the computational results with a robot selection from the literature indicate that the proposed IVHF-DBGD model is the suitable group decision-making tool for the industrial selection problems.

International audience; Graph-Based Representation (GBR) has recently been proposed for rectified multiview dataset. The core idea of G-BR is to use graphs for describing the color and geometry information of a multiview dataset. The color information is represented by the vertices of the graph while the scene geometry is represented by the edges of the graph. In this paper , we generalize the GBR to multi-view images with complex camera configurations. Compared with previous work, the GBR representation introduced in this paper can handle not only horizontal displacements of the cameras but also forward/backward displacements, rotations etc. In order to have a sparse (i.e., easy to code) graph structure, we further propose to use a distortion metric to select the most meaningful connections. For the graph transmission, each selected connection is then replaced by a disparity-based quantity. The experiments show that the proposed GBR achieves high reconstructing quality with less or comparable coding rate compared with traditional depth-based representations, that directly compress the depth signal without considering the rendering task.

This paper aims to propose a new feature and intensity-based image registration method. The proposed approach is based on the block matching algorithm (Ourselin et al., 2000 1): a displacement field is locally computed by matching spatially invariant intensity sub-blocks of the images before performing an optimization algorithm from this vector field to estimate the transformation. Our approach proposes a new way to calculate the displacement field by matching spatially variant sub-blocks of the images, called General Adaptive Neighborhoods (GANs) (Debayle and Pinoli, 2006 2). These neighborhoods are adaptive with respect to both the intensities and the spatial structures of the image. They represent the patterns within the grayscale images. This paper also presents a consistent shape metric used to match the GANs. The performed qualitative and quantitative experiments show that the proposed GAN matching method provides accurate displacement fields enabling us to perform image rigid registration, even for data from different modalities, that outperforms the classical block matching algorithm with respect to robustness and accuracy criteria. HighlightsNovel image rigid registration method based on a block matching strategy.Displacement vectors computed with spatially variant neighborhoods.Consistent shape metric for matching neighborhoods.Qualitative and quantitative evaluation of the proposed method.

One difficulty faced in knowledge engineering for Bayesian Network (BN) is the quantification step where the Conditional Probability Tables (CPTs) are determined. The number of parameters included in CPTs increases exponentially with the number of parent variables. The most common solution is the application of the so-called canonical gates. The Noisy-OR (NOR) gate, which takes advantage of the independence of causal interactions, provides a logarithmic reduction of the number of parameters required to specify a CPT. In this paper, an extension of NOR model based on the theory of belief functions, named Belief Noisy-OR (BNOR), is proposed. BNOR is capable of dealing with both aleatory and epistemic uncertainty of the network. Compared with NOR, more rich information which is of great value for making decisions can be got when the available knowledge is uncertain. Specially, when there is no epistemic uncertainty, BNOR degrades into NOR. Additionally, different structures of BNOR are presented in this paper in order to meet various needs of engineers. The application of BNOR model on the reliability evaluation problem of networked systems demonstrates its effectiveness.