In this paper, we address the problem of shot-level video summarization, which aims at selecting a subset of video shots as a summary to represent the original video contents compactly and completely. Most existing methods rely on various network architectures to learn a single score predictor for shot ranking and selection. Different from these methods, we plug network feature learning into a binary

Extracting mentions of Adverse Drug Reaction (ADR) from biomedical texts, aiming to support pharmacovigilance and drug safety surveillance, remains a challenging task as many ADR mentions are nested, discontinuous and overlapping. To solve these issues, in this paper, we propose a deep neural model for Complex Adverse Drug Reaction Mentions Extraction, called DeepCADRME. It first transforms the ADR

In this paper, we propose to embed edges instead of nodes using state-of-the-art neural/factorization methods (DeepWalk, node2vec, NetMF). These methods produce latent representations based on co-ocurrence statistics by simulating fixed-length random walks and then taking bags-of-vectors as the input to the Skip Gram Learning with Negative Sampling (SGNS). We commence by expressing commute times embedding

The Transformer model has achieved very good results in machine translation tasks. In this paper, we adopt the Transformer model for the image captioning task. To promote the performance of image captioning, we improve the Transformer model from two aspects. First, we augment the maximum likelihood estimation (MLE) with an extra Kullback-Leibler (KL) divergence term to distinguish the difference between

Person re-identification (re-id) addresses the problem of whether “a query image corresponds to an identity in the database” and is believed to play a fundamental role in security enforcement in the near future, particularly in crowded urban environments. Due to many possibilities in selecting appropriate model architectures, datasets, and settings, the performance reported by the state-of-the-art

Oral cancer is one of the common cancer types which scales higher in death rate every year. The connectivity of two different cavities like oral cavity and nasal cavity is known as Upper Aero-Digestive Tract (UADT). Both oral and nasal cavities consist of thirteen connecting sites from mouth to up-per stomach. The traditional pathological analysis like manual microscopic review brings out major intra

We introduce a new attack against face verification systems based on Deep Neural Networks (DNN). The attack relies on the introduction into the network of a hidden backdoor, whose activation at test time induces a verification error allowing the attacker to impersonate any user. The new attack, named Master Key backdoor attack, operates by interfering with the training phase, so to instruct the DNN

This paper presents graphkit-learn, the first Python library for efficient computation of graph kernels based on linear patterns, able to address various types of graphs. Graph kernels based on linear patterns are thoroughly implemented, each with specific computing methods, as well as two well-known graph kernels based on non-linear patterns for comparative analysis. Since computational complexity

Network representation learning (NRL) methods have received significant attention over the last years thanks to their success in several graph analysis problems, including node classification, link prediction and clustering. Such methods aim to map each vertex of the network into a low dimensional space in a way that the structural information of the network is preserved. Of particular interest are

With the increasing complexity of scientific research, it has gradually turned to a collaborative approach, which can promote knowledge sharing, resource sharing and improve the efficiency of scientific research achievements. Therefore, It is of great significance to study the internal organizational structure and evolution mechanism of scientific research collaboration, which plays a crucial role

With the continuous development of artificial intelligence, machine learning, the necessary way to achieve artificial intelligence, is also constantly improving, of which deep learning is one of the contents. The purpose of this paper is to evaluate and warn the security risk of large-scale group activities based on the random forest algorithm. This paper uses the methods of calculating the importance

Cornea is the outmost layer of an eye helps to focuses the light rays towards the retinal layer of the eye. The irregular thickness of the corneal layer results in poor focus of light rays over the retinal layer and hence it results in blur vision. Lasik is a surgical procedure made for correcting the irregular thickness of the cornea to certain extent for making the light rays to fall exactly on the

Human mind processes the different primitive components of image signals such as color, shape, texture, and symmetry in a parallel and complex fashion. Deep neural networks aim to learn all these components from the image in an unsupervised manner. However, learning the primitive features is not formally assured in a deep learning formulation, and, adding these feature explicitly would improve the

Considerable interest has been recently devoted to the exploitation of brain activity as biometric identifier in automatic recognition systems, with a major focus on data acquired through electroencephalography (EEG). Several researches have in fact confirmed the presence of discriminative characteristics within brain signals recorded while performing specific mental tasks. Yet, to make EEG-based recognition

In human-machine interfaces (HMI), deep learning (DL) techniques such as convolutional neural networks (CNN), long-short term memory networks (LSTM) and the hybrid CNN-LSTM framework have been exploited for hand kinematics estimation using surface electromyography (sEMG). However, these DL techniques only capture the relationship between sEMG and hand kinematics, but ignores the prior knowledge of

Soft biometrics, although not discriminant enough for person recognition provides additional information that aids traditional person recognition. Initially, attempts were made to integrate appearance-based facial soft biometrics, such as facial marks, skin color, and hair color/style, but more recently behavior-based facial soft biometrics, such as head dynamics, visual speech, and facial expressions

The calibration of a zoom lens camera depends on the precision of the localization of control points. At a long focal length, the narrow depth-of-field (DOF) causes defocused blurring and an inevitable decrease in accuracy in control points localization. In particular, the camera calibration requires multiple control points defined on calibration patterns acquired at various camera angles. However

In this paper, we discuss a novel graph matching problem, namely the parameterized Koopmans–Beckmann’s graph matching (KBGMw). KBGMw is defined by a weighted linear combination of a series of Koopmans–Beckmann’s graph matching. First, we show that KBGMw can be taken as a special case of the parameterized Lawler’s graph matching, subject to certain conditions. Second, based on structured SVM, we propose

We consider the problem of data clustering with unidentified feature quality and when a small amount of labelled data is provided. An unsupervised sparse clustering method can be employed in order to detect the subgroup of features necessary for clustering and a semi-supervised method can use the labelled data to create constraints and enhance the clustering solution. In this paper we propose a K-Means

Deep learning demonstrated major abilities in solving many kinds of different real-world problems in computer vision literature. However, they are still strained by simple reasoning tasks that humans consider easy to solve. In this work, we probe current state-of-the-art convolutional neural networks on a difficult set of tasks known as the same-different problems. All the problems require the same

With the emergence of Generative Adversarial Networks, great progress has been made in image inpainting. However, most existing methods can produce plausible results, but fail to generate finer textures and structures. This is mainly due to the fact that (1) the generation of finer content in the masked region of an image is not constrained enough during network training, and (2) many different alternative

Optic neuropathy is kind of common eye diseases, which usually causes irreversible vision loss. Early diagnosis is key to saving patients’ vision. Due to the similar early clinical manifestations of common optic neuropathy, it may cause misdiagnosis and delays in treatment. Worse, most diagnoses rely on experienced doctors. In this paper, we proposed a novel deep learning architecture GroupFusionNet

In this paper we propose a simple new algorithm to perform clustering, based on the Alter algorithm proposed in [1] but lowering significantly the algorithmic complexity with respect to the number of clusters. An empirical study states the relevance of our iterative process and a confrontation on simulated multivariate and functional data shows the benefits of our algorithm.

This paper is the editorial of the virtual special issue (VSI) “Artificial Intelligence for Distributed Smart Systems” (AI4DSS), of which the authors of this paper have been the guest editors. It aims to bring together the work of experts from the fields of artificial intelligence and that of smart sensing. Smart Sensing and, more generally, Smart Cyber Physical Systems are nowadays significantly impacting

Malignant melanoma is considered to be one of the deadliest types of skin cancers which is responsible for the massive number of deaths worldwide. According to the American Cancer Society (ACS), more than a million Americans are living with this melanoma. Since 2019, 192,310 new cases of melanoma are registered, where 95,380 are noninvasive, and 96,480 are invasive. The numbers of deaths due to melanoma

Face-based age estimation systems are commonly considered in biometric applications as well as in other fields such as forensics or healthcare. For security purposes, features extracted from the face can be used to verify or estimate the age of individuals in order to control their access to physical or logical resources. The main problem in using facial biometrics is its sensitivity, to acquisition

Active learning (AL) selects the most beneficial unlabeled samples to label, and hence a better machine learning model can be trained from the same number of labeled samples. Most existing active learning for regression (ALR) approaches are supervised, which means the sampling process must use some label information, or an existing regression model. This paper considers completely unsupervised ALR

With the emergence of the concept of “safe city”, security construction has gradually been valued by various cities, and video surveillance technology has also been continuously developed and applied. However, as the functional requirements of actual applications become more and more diverse, video surveillance systems also need to be more intelligent. The purpose of this article is to study methods

With the emergence of large-scale datasets and deep learning systems, person re-identification(Re-ID) has made many significant breakthroughs. Meanwhile, Visible-Thermal person re-identification(V-T Re-ID) between visible and thermal images has also received ever-increasing attention. However, most of typical visible-visible person re-identification(V-V Re-ID) algorithms are difficult to be directly

Relief patterns represent a surface characteristic that is well distinct from the 3D object shape. They can be seen as the 3D counterpart of the texture concept in the 2D images. A large part of texture analysis, in 2D image state-of-the-art, relies on some convolution-based filtering. Thus, the idea of extending such techniques to the mesh manifold domain is quite natural. Nevertheless, defining a

At present, a need for an integrated event focused crawling system for obtaining web data regarding key events is felt. At the time of a disaster or any other important event, several users attempt to find updated information regarding the event. The work has proposed a new and efficient method for such keyword set enhancement. Today, information has been growing rapidly, and it can be very challenging

Fashion is a multi-billion-dollar industry, which is directly related to social, cultural, and economic implications in the real world. While computer vision has demonstrated remarkable success in the applications of the fashion domain, natural language processing technology has become contributed in the area, so that it can build the connection between clothes image and human semantic understandings

Recent advances in imagined speech recognition from EEG signals have shown their capability of enabling a new natural form of communication, which is posed to improve the lives of subjects with motor disabilities. However, differences among subjects may be an obstacle to the applicability of a previously trained classifier to new users, since a significant amount of labeled samples must be acquired

To improve the quality of multi-focus image fusion in photography applications, a multi-focus image fusion algorithm based on supervised learning for fully convolutional network is proposed. The aim of this algorithm is to make the neural network learn the complementary relationship between different focusing areas of source images, which is to select different focusing positions of the source images

The problem of image segmentation is often considered in the framework of graphs. In this context, two main paradigms exist: in the first, the vertices of a non-directed graph represent the pixels (leading e.g. to the watershed, the random walker or the graph cut approaches); in the second, the vertices of a directed graph represent the connected regions, leading to the so-called morphological trees

Generalizing over temporal variations is a prerequisite for effective action recognition in videos. Despite significant advances in deep neural networks, it remains a challenge to focus on short-term discriminative motions in relation to the overall performance of an action. We address this challenge by allowing some flexibility in discovering relevant spatio-temporal features. We introduce Squeeze

For the problems of inconsistent sample duration and unbalance of sample categories in the speech emotion corpus, this paper proposes a speech emotion recognition model based on Bi-GRU (Bidirection Gated Recurrent Unit) and Focal Loss. The model has been improved on the basis of learning CRNN (Convolutional Recurrent Neural Network) deeply. In CRNN, Bi-GRU is used to effectively lengthen the samples

The factorization machine models attract significant attention nowadays since they improve recommendation performance by incorporating context information into recommendation modeling. However, traditional factorization machine models often adopt the point-wise learning method for model parameter learning, as well as only model the linear interactions between features. They substantially fail to capture

The development of depth cameras, e.g., the Kinect sensor, provides new opportunities for human computer interaction (HCI). Although the Kinect sensor has been extensively applied for human tracking, human action recognition and hand gesture recognition, real time hand gesture recognition is still a challenging problem. In this paper, a new real time hand gesture recognition method is proposed. Since

Generative Adversarial Nets (GANs) are currently the dominant model for high fidelity image synthesis. GANs suffer from two major drawbacks: complicated dynamics and the requirement for an auxiliary network for training (discriminator). However, if we train a decoder-only network we circumvent both drawbacks. To achieve that, the decoder should capture high-order correlations that exist between the

In many real-world prediction tasks, class labels include information about the relative ordering between labels, which is not captured by commonly-used loss functions such as multi-category cross-entropy. Recently, the deep learning community adopted ordinal regression frameworks to take such ordering information into account. Neural networks were equipped with ordinal regression capabilities by transforming

Current face recognition systems achieve high progress on several benchmark tests. Despite this progress, recent works showed that these systems are strongly biased against demographic sub-groups. Consequently, an easily integrable solution is needed to reduce the discriminatory effect of these biased systems. Previous work mainly focused on learning less biased face representations, which comes at

Computing a consensus object from a set of given objects is a core problem in machine learning and pattern recognition. One commonly used approach is to formulate it as an optimization problem using the generalized median. However, in many domains the construction of a median object is NP-hard, requiring approximate solutions instead. In these cases a lower bound is helpful to assess the quality of

Automated surveillance is essential for the protection of Critical Infrastructures (CIs) in future Smart Cities. The dynamic environments and bandwidth requirements demand systems that adapt themselves to react when events of interest occur. We present a reconfigurable Cyber Physical System for the protection of CIs using distributed cloud-edge smart video surveillance. Our local edge nodes perform

Computer aided diagnosis systems are playing an important part in clinical treatment. They can help the doctors and physicians to verify the diagnosis decisions. In this study, a new classification algorithm for the brain magnetic resonance image is proposed. Initially, we utilized a MobileNetV2 to extract features from the input brain images, which was pre-trained on ImageNet dataset. Instead of training

Due to the influence of various conditions and uncertain difficulties for remote sensing images, image registration is still a challenging task. Considering the registration accuracy of pixel level cannot satisfy the requirements of some related applications, we put forward a sub-pixel image registration method based on speeded up robust features and M-estimator sample consensus. It mainly involves

Interactive image segmentation has considerably evolved from techniques that do not learn the parameters of the model to methods that pre-train a model and adapt it from user inputs during the process. However, user control over segmentation still requires significant improvements to avoid that corrections in one part of the object cause errors in other parts. We address this problem by presenting

In image set classification, dual linear regression classification (DLRC) has shown the excellent performance on face image data without the interference of the complex background. However, DLRC could not well identify the data set with the complex background. The complex background means that the background is cluttered and the viewpoint is unusual or the object is partially occluded. This paper proposes

To improve the attack success rate and image perceptual quality of adversarial examples against deep neural networks(DNNs), we propose a new Generative Adversarial Network (GAN) based attacker, named Elastic-net Regularized Boundary Equilibrium Generative Adversarial Network(ERBEGAN). Recent studies have shown that DNNs are easy to attack by adversarial examples(AEs) where benign images with small-magnitude

Photo Response Non-Uniformity (PRNU) based source camera attribution is an effective method to determine an image or a video’s origin camera. However, modern devices, especially smartphones, capture images and videos at different resolutions using the same sensor array, PRNU attribution can become ineffective as the camera fingerprint and query object can be misaligned. While capturing visual objects

As enhance of safety requirement in the smart cities, biometrics recognition, as an approach for society safety, has been greatly researched and developed. The identification of working status of welders will help judge whether they are wearing personal protective equipment correctly. We proposed an improved algorithm based on SSD (Single Shot Multibox Detector) that can identify three mainstream manual

Various information-theoretic divergences have been proposed for the cost function in tasks such as matrix factorization and clustering. One class of divergence is called the Beta divergence. By varying a real-valued parameter β, the Beta divergence connects several well-known divergences, such as the Euclidean distance, Kullback-Leibler divergence, and Itakura-Saito divergence. Unfortunately, the

The most recently-proposed concept of capsule network consists of capsules, a structural group of neurons with activation, as building blocks, and dynamic routing between them as connections. Semantic information for final tasks can be extracted by stacking such capsule layers as construction of deep models. In this paper, we formulate the dynamic routing problem from the perspective of feature compression

Dot-product kernels is a large family of kernel functions based on dot-product between examples. A recent result states that any dot-product kernel can be decomposed as a non-negative linear combination of homogeneous polynomial kernels of different degrees, and it is possible to learn the coefficients of the combination by exploiting the Multiple Kernel Learning (MKL) paradigm. In this paper it is

The kernel matrix used in kernel methods encodes all the information required for solving complex nonlinear problems defined on data representations in the input space using simple, but implicitly defined, solutions. Spectral analysis on the kernel matrix defines an explicit nonlinear mapping of the input data representations to a subspace of the kernel space, which can be used for directly applying

Deep learning has attracted significant attention for its applications to a variety of classification problems, such as handwritten recognition, image classification and document categorization. One reason behind the success of deep learning can be attributed to its strong representation power with multiple layers of hidden variables. However, complex models are often encompassed with overfitting problems