Catálogo de publicaciones - revistas

<jats:p>Face recognition is one of the most popular and long-standing topics in computer vision. With the recent development of deep learning techniques and large-scale datasets, deep face recognition has made remarkable progress and been widely used in many real-world applications. Given a natural image or video frame as input, an end-to-end deep face recognition system outputs the face feature for recognition. To achieve this, a typical end-to-end system is built with three key elements: face detection, face alignment, and face representation. The face detection locates faces in the image or frame. Then, the face alignment is proceeded to calibrate the faces to the canonical view and crop them with a normalized pixel size. Finally, in the stage of face representation, the discriminative features are extracted from the aligned face for recognition. Nowadays, all of the three elements are fulfilled by the technique of deep convolutional neural network. In this survey article, we present a comprehensive review about the recent advance of each element of the end-to-end deep face recognition, since the thriving deep learning techniques have greatly improved the capability of them. To start with, we present an overview of the end-to-end deep face recognition. Then, we review the advance of each element, respectively, covering many aspects such as the to-date algorithm designs, evaluation metrics, datasets, performance comparison, existing challenges, and promising directions for future research. Also, we provide a detailed discussion about the effect of each element on its subsequent elements and the holistic system. Through this survey, we wish to bring contributions in two aspects: first, readers can conveniently identify the methods which are quite strong-baseline style in the subcategory for further exploration; second, one can also employ suitable methods for establishing a state-of-the-art end-to-end face recognition system from scratch.</jats:p>

<jats:p>AI is widely thought to be poised to transform business, yet current perceptions of the scope of this transformation may be myopic. Recent progress in natural language processing involving transformer language models (TLMs) offers a potential avenue for AI-driven business and societal transformation that is beyond the scope of what most currently foresee. We review this recent progress as well as recent literature utilizing text mining in top IS journals to develop an outline for how future IS research can benefit from these new techniques. Our review of existing IS literature reveals that suboptimal text mining techniques are prevalent and that the more advanced TLMs could be applied to enhance and increase IS research involving text data, and to enable new IS research topics, thus creating more value for the research community. This is possible because these techniques make it easier to develop very powerful custom systems and their performance is superior to existing methods for a wide range of tasks and applications. Further, multilingual language models make possible higher quality text analytics for research in multiple languages. We also identify new avenues for IS research, like language user interfaces, that may offer even greater potential for future IS research.</jats:p>

<jats:p>The performance of face analysis and recognition systems depends on the quality of the acquired face data, which is influenced by numerous factors. Automatically assessing the quality of face data in terms of biometric utility can thus be useful to detect low-quality data and make decisions accordingly. This survey provides an overview of the face image quality assessment literature, which predominantly focuses on visible wavelength face image input. A trend towards deep learning based methods is observed, including notable conceptual differences among the recent approaches, such as the integration of quality assessment into face recognition models. Besides image selection, face image quality assessment can also be used in a variety of other application scenarios, which are discussed herein. Open issues and challenges are pointed out, i.a. highlighting the importance of comparability for algorithm evaluations, and the challenge for future work to create deep learning approaches that are interpretable in addition to providing accurate utility predictions.</jats:p>

<jats:p> Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks <jats:italic>e.g.</jats:italic> , Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities ( <jats:italic>e.g.</jats:italic> , images, videos, text and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. We then cover extensive applications of transformers in vision including popular recognition tasks ( <jats:italic>e.g.</jats:italic> , image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks ( <jats:italic>e.g.</jats:italic> , visual-question answering, visual reasoning, and visual grounding), video processing ( <jats:italic>e.g.</jats:italic> , activity recognition, video forecasting), low-level vision ( <jats:italic>e.g.</jats:italic> , image super-resolution, image enhancement, and colorization) and 3D analysis ( <jats:italic>e.g.</jats:italic> , point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works. We hope this effort will ignite further interest in the community to solve current challenges towards the application of transformer models in computer vision. </jats:p>

<jats:p>Recent advancements in deep learning architecture have increased its utility in real-life applications. Deep learning models require a large amount of data to train the model. In many application domains, there is a limited set of data available for training neural networks as collecting new data is either not feasible or requires more resources such as in marketing, computer vision, and medical science. These models require a large amount of data to avoid the problem of overfitting. One of the data space solutions to the problem of limited data is data augmentation. The purpose of this study focuses on various data augmentation techniques that can be used to further improve the accuracy of a neural network. This saves the cost and time consumption required to collect new data for the training of deep neural networks by augmenting available data. This also regularizes the model and improves its capability of generalization. The need for large datasets in different fields such as computer vision, natural language processing, security and healthcare is also covered in this survey paper. The goal of this paper is to provide a comprehensive survey of recent advancements in data augmentation techniques and their application in various domains.</jats:p>

<jats:p>Decision trees have the particularity of being machine learning models that are visually easy to interpret and understand. Therefore, they are primarily suited for sensitive domains like medical diagnosis, where decisions need to be explainable. However, if used on complex problems, decision trees can become large, making them hard to grasp. In addition to this aspect, when learning decision trees, it may be necessary to consider a broader class of constraints, such as the fact that two variables should not be used in a single branch of the tree. This motivates the need to enforce constraints in learning algorithms of decision trees. We propose a survey of works that attempted to solve the problem of learning decision trees under constraints. Our contributions are fourfold. First, to the best of our knowledge, this is the first survey that deals with constraints on decision trees. Second, we define a flexible taxonomy of constraints applied to decision trees and methods for their treatment in the literature. Third, we benchmark state-of-the art depth-constrained decision tree learners with respect to predictive accuracy and computational time. Fourth, we discuss potential future research directions that would be of interest for researchers who wish to conduct research in this field.</jats:p>

<jats:p>Huge amount of unstructured data including image, video, audio, and text are ubiquitously generated and shared, it is a challenge to protect sensitive personal information in them, such as human faces, voiceprints, and authorships. Differential privacy is the standard privacy protection technology that provides rigorous privacy guarantees for various data. This survey summarizes and analyzes differential privacy solutions to protect unstructured data content before they are shared with untrusted parties. These differential privacy methods obfuscate unstructured data after they are represented with vectors, and then reconstruct them with obfuscated vectors. We summarize specific privacy models and mechanisms together with possible challenges in them. We also conclude their privacy guarantees against AI attacks and utility losses. Finally, we discuss several possible directions for future research.</jats:p>

<jats:p> <jats:bold>Context:</jats:bold> The mobile app market is continually growing offering solutions to almost all aspects of people’s lives, e.g., healthcare, business, entertainment, as well as the stakeholders’ demand for apps that are more secure, portable, easy to use, among other non-functional requirements (NFRs). Therefore, manufacturers should guarantee that their mobile apps achieve high-quality levels. A good strategy is to include software testing and quality assurance activities during the whole life cycle of such solutions. </jats:p> <jats:p> <jats:bold>Problem:</jats:bold> Systematically warranting NFRs is not an easy task for any software product. Software engineers must take important decisions before adopting testing techniques and automation tools to support such endeavors. </jats:p> <jats:p> <jats:bold>Proposal:</jats:bold> To provide to the software engineers with a broad overview of existing dynamic techniques and automation tools for testing mobile apps regarding NFRs. </jats:p> <jats:p> <jats:bold>Methods:</jats:bold> We planned and conducted a Systematic Mapping Study (SMS) following well-established guidelines for executing secondary studies in software engineering. </jats:p> <jats:p> <jats:bold>Results:</jats:bold> We found 56 primary studies and characterized their contributions based on testing strategies, testing approaches, explored mobile platforms, and the proposed tools. </jats:p> <jats:p> <jats:bold>Conclusions:</jats:bold> The characterization allowed us to identify and discuss important trends and opportunities that can benefit both academics and practitioners. </jats:p>

<jats:p>Several image processing tasks, such as image classification and object detection, have been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and EfficientNet, many architectures have achieved outstanding results in at least one dataset by the time of their creation. A critical factor in training concerns the network’s regularization, which prevents the structure from overfitting. This work analyzes several regularization methods developed in the last few years, showing significant improvements for different CNN models. The works are classified into three main areas: the first one is called “data augmentation”, where all the techniques focus on performing changes in the input data. The second, named “internal changes”, which aims to describe procedures to modify the feature maps generated by the neural network or the kernels. The last one, called “label”, concerns transforming the labels of a given input. This work presents two main differences comparing to other available surveys about regularization: (i) the first concerns the papers gathered in the manuscript, which are not older than five years, and (ii) the second distinction is about reproducibility, i.e., all works refered here have their code available in public repositories or they have been directly implemented in some framework, such as TensorFlow or Torch.</jats:p>

<jats:p>Containerization is a lightweight application virtualization technology, providing high environmental consistency, operating system distribution portability, and resource isolation. Existing mainstream cloud service providers have prevalently adopted container technologies in their distributed system infrastructures for automated application management. To handle the automation of deployment, maintenance, autoscaling, and networking of containerized applications, container orchestration is proposed as an essential research problem. However, the highly dynamic and diverse feature of cloud workloads and environments considerably raises the complexity of orchestration mechanisms. Machine learning algorithms are accordingly employed by container orchestration systems for behavior modelling and prediction of multi-dimensional performance metrics. Such insights could further improve the quality of resource provisioning decisions in response to the changing workloads under complex environments. In this paper, we present a comprehensive literature review of existing machine learning-based container orchestration approaches. Detailed taxonomies are proposed to classify the current researches by their common features. Moreover, the evolution of machine learning-based container orchestration technologies from the year 2016 to 2021 has been designed based on objectives and metrics. A comparative analysis of the reviewed techniques is conducted according to the proposed taxonomies, with emphasis on their key characteristics. Finally, various open research challenges and potential future directions are highlighted.</jats:p>