Laboratoire d'Informatique en Images et Systèmes d'Information

Local binary pattern (LBP) is a nonparametric descriptor, which efficiently summarizes the local structures of images. In recent years, it has aroused increasing interest in many areas of image processing and computer vision and has shown its effectiveness in a number of applications, in particular for facial image analysis, including tasks as diverse as face detection, face recognition, facial expression analysis, and demographic classification. This paper presents a comprehensive survey of LBP methodology, including several more recent variations. As a typical application of the LBP approach, LBP-based facial image analysis is extensively reviewed, while its successful extensions, which deal with various tasks of facial image analysis, are also highlighted.

Several research studies have shown that complex networks modeling real-world phenomena are characterized by striking properties: (i) they are organized according to community structure, and (ii) their structure evolves with time. Many researchers have worked on methods that can efficiently unveil substructures in complex networks, giving birth to the field of community discovery. A novel and fascinating problem started capturing researcher interest recently: the identification of evolving communities. Dynamic networks can be used to model the evolution of a system: nodes and edges are mutable, and their presence, or absence, deeply impacts the community structure that composes them. This survey aims to present the distinctive features and challenges of dynamic community discovery and propose a classification of published approaches. As a “user manual,” this work organizes state-of-the-art methodologies into a taxonomy, based on their rationale, and their specific instantiation. Given a definition of network dynamics, desired community characteristics, and analytical needs, this survey will support researchers to identify the set of approaches that best fit their needs. The proposed classification could also help researchers choose in which direction to orient their future research.

Amyotrophic lateral sclerosis (ALS) is a devastating condition with an estimated mortality of 30,000 patients a year worldwide. The median reported survival time since onset ranges from 24 to 48 months. Riluzole is the only currently approved mildly efficacious treatment. Riluzole received marketing authorization in 1995 in the USA and in 1996 in Europe. In the years that followed, over 60 molecules have been investigated as a possible treatment for ALS. Despite significant research efforts, the overwhelming majority of human clinical trials (CTs) have failed to demonstrate clinical efficacy. In the past year, oral masitinib and intravenous edaravone have emerged as promising new therapeutics with claimed efficacy in CTs in ALS patients. Given their advanced phase of clinical development one may consider these drugs as the most likely near-term additions to the therapeutic arsenal available for patients with ALS. In terms of patient inclusion, CT with masitinib recruited a wider, more representative, less restrictive patient population in comparison to the only successful edaravone CT (edaravone eligibility criteria represents only 18% of masitinib study patients). The present manuscript reviews >50 CTs conducted in the last 20 years since riluzole was first approved. A special emphasis is put on the analysis of existing evidence in support of the clinical efficacy of edaravone and masitinib and the possible implications of an eventual marketing authorisation in the treatment of ALS.

The Internet of Medical Things (IoMT) designates the interconnection of communication-enabled medical-grade devices and their integration to wider-scale health networks in order to improve patients' health. However, because of the critical nature of health-related systems, the IoMT still faces numerous challenges, more particularly in terms of reliability, safety, and security. In this paper, we present a comprehensive literature review of recent contributions focused on improving the IoMT through the use of formal methodologies provided by the cyber-physical systems community. We describe the practical application of the democratization of medical devices for both patients and health-care providers. We also identify unexplored research directions and potential trends to solve uncharted research problems.

Which topics spark the most heated debates on social media? Identifying those topics is not only interesting from a societal point of view but also allows the filtering and aggregation of social media content for disseminating news stories. In this article, we perform a systematic methodological study of controversy detection by using the content and the network structure of social media. Unlike previous work, rather than studying controversy in a single hand-picked topic and using domain-specific knowledge, we take a general approach to study topics in any domain . Our approach to quantifying controversy is based on a graph-based three-stage pipeline, which involves (i) building a conversation graph about a topic, (ii) partitioning the conversation graph to identify potential sides of the controversy, and (iii) measuring the amount of controversy from characteristics of the graph. We perform an extensive comparison of controversy measures, different graph-building approaches, and data sources. We use both controversial and non-controversial topics on Twitter, as well as other external datasets. We find that our new random-walk-based measure outperforms existing ones in capturing the intuitive notion of controversy and show that content features are vastly less helpful in this task.

Credit card fraud is a criminal offense. It causes severe damage to financial institutions and individuals. Therefore, the detection and prevention of fraudulent activities are critically important to financial institutions. Fraud detection and prevention are costly, time-consuming, and labor-intensive tasks. A number of significant research works have been dedicated to developing innovative solutions to detect different types of fraud. However, these solutions have been proved ineffective. According to Cifa, 33 305 cases of credit card identity fraud were reported between January and June in 2018. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> Various weaknesses of existing solutions have been reported in the literature. Among them all, the imbalance classification is the most critical and well-known problem. Imbalance classification consists of having a small number of observations of the minority class compared with the majority in the data set. In this problem, the ratio fraud: legitimate is very small, which makes it extremely difficult for the classification algorithm to detect fraud cases. In this paper, we will conduct a rigorous experimental study with the solutions that tackle the imbalance classification problem. We explored these solutions along with the machine learning algorithms used for fraud detection. We identified their weaknesses and summarized the results that we obtained using a credit card fraud labeled dataset. According to this paper, imbalanced classification approaches are ineffective, especially when the data are highly imbalanced. This paper reveals that the existing approaches result in a large number of false alarms, which are costly to financial institutions. This may lead to inaccurate detection as well as increasing the occurrence of fraud cases.

Byzantine Fault Tolerant state machine replication (BFT) protocols are replication protocols that tolerate arbitrary faults of a fraction of the replicas. Although significant efforts have been recently made, existing BFT protocols do not provide acceptable performance when faults occur. As we show in this paper, this comes from the fact that all existing BFT protocols targeting high throughput use a special replica, called the primary, which indicates to other replicas the order in which requests should be processed. This primary can be smartly malicious and degrade the performance of the system without being detected by correct replicas. In this paper, we propose a new approach, called RBFT for Redundant-BFT: we execute multiple instances of the same BFT protocol, each with a primary replica executing on a different machine. All the instances order the requests, but only the requests ordered by one of the instances, called the master instance, are actually executed. The performance of the different instances is closely monitored, in order to check that the master instance provides adequate performance. If that is not the case, the primary replica of the master instance is considered malicious and replaced. We implemented RBFT and compared its performance to that of other existing robust protocols. Our evaluation shows that RBFT achieves similar performance as the most robust protocols when there is no failure and that, under faults, its maximum performance degradation is about 3%, whereas it is at least equal to 78% for existing protocols.

Community shared bicycle systems, such as the Vélo'v program launched in Lyon in May 2005, are public transportation programs that can be studied as a complex system composed of interconnected stations that exchange bicycles. They generate digital footprints that reveal the activity in the city over time and space, making possible a quantitative analysis of movements using bicycles in the city. A careful study relying on nonstationary statistical modeling and data mining allows us to first model the time evolution of the dynamics of movements with Vélo'v, that is mostly cyclostationary over the week with nonstationary evolutions over larger time-scales, and second to disentangle the spatial patterns to understand and visualize the flows of Vélo'v bicycles in the city. This study gives insights on the social behaviors of the users of this intermodal transportation system, the objective being to help in designing and planning policy in urban transportation.

3D point clouds constitute an emerging multimedia content, now used in a wide range of applications. The main drawback of this representation is the size of the data since typical point clouds may contain millions of points, usually associated with both geometry and color information. Consequently, a significant amount of work has been devoted to the efficient compression of this representation. Lossy compression leads to a degradation of the data and thus impacts the visual quality of the displayed content. In that context, predicting perceived visual quality computationally is essential for the optimization and evaluation of compression algorithms. In this paper, we introduce PCQM, a full-reference objective metric for visual quality assessment of 3D point clouds. The metric is an optimally-weighted linear combination of geometry-based and color-based features. We evaluate its performance on an open subjective dataset of colored point clouds compressed by several algorithms; the proposed quality assessment approach outperforms all previous metrics in terms of correlation with mean opinion scores.

This paper presents GridNet, a new Convolutional Neural Network (CNN)\narchitecture for semantic image segmentation (full scene labelling). Classical\nneural networks are implemented as one stream from the input to the output with\nsubsampling operators applied in the stream in order to reduce the feature maps\nsize and to increase the receptive field for the final prediction. However, for\nsemantic image segmentation, where the task consists in providing a semantic\nclass to each pixel of an image, feature maps reduction is harmful because it\nleads to a resolution loss in the output prediction. To tackle this problem,\nour GridNet follows a grid pattern allowing multiple interconnected streams to\nwork at different resolutions. We show that our network generalizes many well\nknown networks such as conv-deconv, residual or U-Net networks. GridNet is\ntrained from scratch and achieves competitive results on the Cityscapes\ndataset.\n

This brief addresses the problem of the optimal control and scheduling of networked control systems over limited bandwidth deterministic networks. Multivariable linear systems subject to communication constraints are modeled in the mixed logical dynamical (MLD) framework. The translation of the MLD model into the mixed integer quadratic programming (MIQP) formulation is described. This formulation allows the solving of the optimal control and scheduling problem using efficient branch and bound algorithms. Advantages and drawbacks of online and offline scheduling algorithms are discussed. Based on this discussion, a computationally efficient online scheduling algorithm, which can be seen as a compromise, is presented and its performance is evaluated. Finally, this algorithm, called optimal pointer placement (OPP) scheduling algorithm, is applied to the control and scheduling of a car suspension system.

We propose in this paper a generic algorithm based on ant colony optimization to solve multi-objective optimization problems. The proposed algorithm is parameterized by the number of ant colonies and the number of pheromone trails. We compare different variants of this algorithm on the multi-objective knapsack problem. We compare also the obtained results with other evolutionary algorithms from the literature.

This paper presents a novel and efficient deep fusion convolutional neural network (DF-CNN) for multimodal 2D+3D facial expression recognition (FER). DF-CNN comprises a feature extraction subnet, a feature fusion subnet, and a softmax layer. In particular, each textured three-dimensional (3D) face scan is represented as six types of 2D facial attribute maps (i.e., geometry map, three normal maps, curvature map, and texture map), all of which are jointly fed into DF-CNN for feature learning and fusion learning, resulting in a highly concentrated facial representation (32-dimensional). Expression prediction is performed by two ways: 1) learning linear support vector machine classifiers using the 32-dimensional fused deep features, or 2) directly performing softmax prediction using the six-dimensional expression probability vectors. Different from existing 3D FER methods, DF-CNN combines feature learning and fusion learning into a single end-to-end training framework. To demonstrate the effectiveness of DF-CNN, we conducted comprehensive experiments to compare the performance of DFCNN with handcrafted features, pre-trained deep features, finetuned deep features, and state-of-the-art methods on three 3D face datasets (i.e., BU-3DFE Subset I, BU-3DFE Subset II, and Bosphorus Subset). In all cases, DF-CNN consistently achieved the best results. To the best of our knowledge, this is the first work of introducing deep CNN to 3D FER and deep learning-based featurelevel fusion for multimodal 2D+3D FER.

3D meshes are commonly used to represent virtual surface and volumes. However, their raw data representations take a large amount of space. Hence, 3D mesh compression has been an active research topic since the mid 1990s. In 2005, two very good review articles describing the pioneering works were published. Yet, new technologies have emerged since then. In this article, we summarize the early works and put the focus on these novel approaches. We classify and describe the algorithms, evaluate their performance, and provide synthetic comparisons. We also outline the emerging trends for future research.

Extending image processing techniques to videos is a non-trivial task; applying processing independently to each video frame often leads to temporal inconsistencies, and explicitly encoding temporal consistency requires algorithmic changes. We describe a more general approach to temporal consistency. We propose a gradient-domain technique that is blind to the particular image processing algorithm. Our technique takes a series of processed frames that suffers from flickering and generates a temporally-consistent video sequence. The core of our solution is to infer the temporal regularity from the original unprocessed video, and use it as a temporal consistency guide to stabilize the processed sequence. We formally characterize the frequency properties of our technique, and demonstrate, in practice, its ability to stabilize a wide range of popular image processing techniques including enhancement and stylization of color and tone, intrinsic images, and depth estimation.

The widespread adoption of continuously connected smartphones and tablets developed the usage of mobile applications, among which many use location to provide geolocated services. These services provide new prospects for users: getting directions to work in the morning, leaving a check-in at a restaurant at noon and checking next day's weather in the evening are possible right from any mobile device embedding a GPS chip. In these location-based applications, the user's location is sent to a server, which uses them to provide contextual and personalized answers. However, nothing prevents the latter from gathering, analyzing and possibly sharing the collected information, which opens the door to many privacy threats. Indeed, mobility data can reveal sensitive information about users, among which one's home, work place or even religious and political preferences. For this reason, many privacy-preserving mechanisms have been proposed these last years to enhance location privacy while using geolocated services. This paper surveys and organizes contributions in this area from classical building blocks to the most recent developments of privacy threats and location privacy-preserving mechanisms. We divide the protection mechanisms between online and offline use cases, and organize them into six categories depending on the nature of their algorithm. Moreover, this paper surveys the evaluation metrics used to assess protection mechanisms in terms of privacy, utility and performance. Finally, open challenges and new directions to address the problem of computational location privacy are pointed out and discussed.

Summary form only given. Constructing fast, accurate classifiers for large data sets is an important task in data mining and knowledge discovery. In this research paper, a new classification method called multi-class classification based on association rules (MCAR) is presented. MCAR uses an efficient technique for discovering frequent items and employs a rule ranking method which ensures detailed rules with high confidence are part of the classifier. After experimentation with fifteen different data sets, the results indicated that the proposed method is an accurate and efficient classification technique. Furthermore, the classifiers produced are highly competitive with regards to error rate and efficiency, if compared with those generated by popular methods like decision trees, RIPPER and CBA.

The Internet of Things aims at connecting everything, ranging from individuals, organizations, and companies to things in the physical and virtual world. The digital identity has always been considered as the keystone for all online services and the foundation for building security mechanisms such as authentication and authorization. However, the current literature still lacks a comprehensive study on the digital identity management for the Internet of Things (IoT). In this paper, we firstly identify the requirements of building identity management systems for IoT, which comprises scalability, interoperability, mobility, security and privacy. Then, we trace the identity problem back to the origin in philosophy, analyze the Internet digital identity management solutions in the context of IoT and investigate recent surging blockchain sovereign identity solutions. Finally, we point out the promising future research trends in building IoT identity management systems and elaborate challenges of building a complete identity management system for the IoT, including access control, privacy preserving, trust and performance respectively.

Three-dimensional (3-D) meshes have been used more and more in industrial, medical and entertainment applications during the last decade. Many researchers, from both the academic and the industrial sectors, have become aware of their intellectual property protection and authentication problems arising with their increasing use. This paper gives a comprehensive survey on 3-D mesh watermarking, which is considered an effective solution to the above two emerging problems. Our survey covers an introduction to the relevant state of the art, an attack-centric investigation, and a list of existing problems and potential solutions. First, the particular difficulties encountered while applying watermarking on 3-D meshes are discussed. Then we give a presentation and an analysis of the existing algorithms by distinguishing them between fragile techniques and robust techniques. Since attacks play an important role in the design of 3-D mesh watermarking algorithms, we also provide an attack-centric viewpoint of this state of the art. Finally, some future working directions are pointed out especially on the ways of devising robust and blind algorithms and on some new probably promising watermarking feature spaces.

Abstract Many processing operations are nowadays applied on 3D meshes like compression, watermarking, remeshing and so forth; these processes are mostly driven and/or evaluated using simple distortion measures like the Hausdorff distance and the root mean square error, however these measures do not correlate with the human visual perception while the visual quality of the processed meshes is a crucial issue. In that context we introduce a full‐reference 3D mesh quality metric; this metric can compare two meshes with arbitrary connectivity or sampling density and produces a score that predicts the distortion visibility between them; a visual distortion map is also created. Our metric outperforms its counterparts from the state of the art, in term of correlation with mean opinion scores coming from subjective experiments on three existing databases. Additionally, we present an application of this new metric to the improvement of rate‐distortion evaluation of recent progressive compression algorithms.