Ascertaining the impact of research is significant for the research community and academia of all disciplines. The only prevalent measure associated with the quantification of research quality is the citation-count. Although a number of citations play a significant role in academic research, sometimes citations can be biased or made to discuss only the weaknesses and shortcomings of the research. By

The Pixel Non-Uniformity noise (PNU noise, for short) is a characteristic noise of digital camera sensors that has been originally used a mean to perform Source Camera Identification (SCI), that is, to identify the digital camera that has been used to take an image under scrutiny. Actually, its usage has been extended to other relevant application domains, such as carrying out sensor identification

In this paper, we propose a simple yet effective method to represent point clouds as sets of samples drawn from a cloud-specific probability distribution. This interpretation matches intrinsic characteristics of point clouds: the number of points and their ordering within a cloud is not important as all points are drawn from the proximity of the object boundary. We postulate to represent each cloud

To solve the problem of data sparsity and cold start, the cross-domain recommendation is a promising research direction in the recommender system. The goal of cross-domain recommendation is to transfer learned knowledge from the source domain to the target domain by different means to improve the performance of the recommendation. But most approaches face the distribution misalignment. In this paper

Establishing a human motion reconstruction system from very few constraints imposed on the body has been an interesting and important research topic because it significantly reduces the degrees of freedom to be managed. However, it is a well-known mathematically ill-posed problem as the dimension of constraints is much lower than that of the human pose to be determined. Therefore, it is challenging

Identification of image provenance is one of the crucial tasks to be tackled in the field of image forensics. Due to the rapid growth in technology, a huge amount of digital images are shared among users through social networks which facilitates many malicious activities. Establishing the provenance of downloaded images is an important task that could help focus investigations in a specific direction

Motion estimation is the basic need for the success of many video analysis algorithms such as moving object detection, human activity recognition, etc. Most of the motion estimation algorithms are prone to weather conditions and thus, they fail to estimate the motion in degraded weather. Severe weather situations like snow, rain, haze, smog, etc., degrades the performance and reliability of video analysis

Re-ranking is becoming a critical part of retrieved based Person re-identification algorithms. Existing re-ranking methods always require lots of queries and memory to go through the k-nearest neighbors. To solve this problem, we introduce a Feature Relation Map (FRM) to mine the latent relation between the k-neighbors through convolution neural network, and propose a metric learning based Similarity

RGB-Infrared (RGB-IR) person re-identification (ReID) is a technology where the system can automatically identify the same person appearing at different parts of a video when light is unavailable. The critical challenge of this task is the cross-modality gap of features under different modalities. To solve this challenge, we proposed a Teacher-Student GAN model (TS-GAN) to adopt different domains and

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training pairs. In this paper, a dynamic sampling strategy is proposed to organize the training pairs in an easy-to-hard order to feed into the network. It allows the network

In mental health assessment, it is validated that nonverbal cues like facial expressions can be indicative of depressive disorders. Recently, the multimodal fusion of facial appearance and dynamics based on convolutional neural networks has demonstrated encouraging performance in depression analysis. However, correlation and complementarity between different visual modalities have not been well studied

We present an approach for motion clustering based on a novel observation that a signature for putative pixel correspondences can be generated by collecting their residuals with respect to model hypotheses drawn randomly from the data. Inliers of the same motion cluster should have strongly correlated residuals, which are low when a hypothesis is consistent with the data in the cluster and high otherwise

The generation of morphological traits of plants such as the leaf length, width, perimeter, area, and petiole length are fundamental features of herbarium specimens, thus providing high-quality data to investigate plant responses to ongoing climatic change and plant history evolution. However, the existing measurement methods are primarily associated with manual analysis, which is labor-intensive and

Deep neural networks (DNNs) have achieved state-of-the-art results in a broad range of tasks, in particular the ones dealing with the perceptual data. However, full-scale application of DNNs in safety-critical areas is hindered by their black box-like nature, which makes their inner workings nontransparent. As a response to the black box problem, the field of explainable artificial intelligence (XAI)

Complexity measures are important to understand and analyze systems with one dimensional data. However, extension of these methods to images (two dimensional data) are much less usual. Bidimensional multiscale sample entropy (MSE2D) has recently been proposed as a new complexity measure for texture evaluation. However, MSE2D leads to undefined or unreliable values for small-sized textures and requires

Background COVID-19 has caused 3.34m deaths till 13/May/2021. It is now still causing confirmed cases and ongoing deaths every day. Method This study investigated whether fusing chest CT with chest X-ray can help improve the AI's diagnosis performance. Data harmonization is employed to make a homogeneous dataset. We create an end-to-end multiple-input deep convolutional attention network (MIDCAN) by

Visual Question Answering (VQA) in the medical domain has attracted more attention from research communities in the last few years due to its various applications. This paper investigates several deep learning approaches in building a medical VQA system based on ImageCLEF’s VQA-Med dataset, which consists of about 4K images with about 15K question-answer pairs. Due to the wide variety of the images

Many applications, such as robotics, are increasingly utilizing Reinforcement Learning (RL). The current implementation of RL typically assumes that the state update from the previous actions happens instantaneously, and thus can be used for making future decisions. However, this may not always be true. When the state update is not available, the decision is taken partly in the blind since it cannot

This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this

In ranking applications, AUCROC is widely used in measuring the performance of a discriminative model. But this is possible only if the labels are binary, like in {0,1}, as AUCROC is undefined for non-binary labels. In modelling applications where the labels are not from {0,1} but are probabilities of membership (p,1−p) to the binary classes, we generally use other metrics. In this paper, we propose

Detecting communities or the modular structure of real-life networks (e.g. a social network or a product purchase network) is an important task because the way a network functions is often determined by its communities. Traditional approaches to community detection involve modularity-based algorithms, which generally speaking, construct partitions based on heuristics that seek to maximize the ratio

Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects instead of the background. So far, computational methods for saliency estimation required the explicit generation of a saliency map, process which is usually achieved via eyetracking experiments on still images. This is a tedious process that needs to be repeated for each new dataset. In

Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior

Recently, data sparsity is still one of the critical problems faced by recommendation systems. Although many existing methods based on cross-domain can alleviate it to a certain extent, these methods only use the information of single-domain (e.g., user-side, item-side and rating-side) or dual-domain (e.g., user-rating-side, user-item-side and item-rating-side) to make recommendations, which results

In this paper, we tackle the task of improving biometric verification in the context of Human-Robot Interaction (HRI). A robot that wants to identify a specific person to provide a service can do so by either image verification or, if light conditions are not favourable, through voice verification. In our approach, we will take advantage of the possibility a robot has of recovering further data until

Several cyber-security data sources are collected in enterprise networks providing relational information between different types of nodes in the network, namely computers, users and ports. This relational data can be expressed as adjacency matrices detailing inter-type relationships corresponding to relations between nodes of different types and intra-type relationships showing relationships between

Relation Extraction (RE) aims at extracting meaningful relation facts between entities in texts. It is an important semantic processing task in the field of natural language processing (NLP) and has many applications. Traditional RE focuses on extracting entity relationships from a single input sentence. Recently, the research scope has been extended from sentence level to document level. However,

Deep Semi-NMF (DSN), which learns hierarchical representations by stacking multiple layers Semi-NMF, shows competitive performance in unsupervised data analysis. However, the features learned from DSN always lack of representativity and discriminativity. In this paper, we build a novel Deep Semi-NMF network (DSNnet) to address the issues of DSN. Specifically, DSNnet contains multiple fully-connected

Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we propose to jointly use scene text and visual channels for robust semantic interpretation of images. We not only extract and encode visual and scene text cues but

Modern quantitative challenges require to tackle problems on increasingly complex systems in which the relationships between the comprised entities cannot be modelled in a simple pairwise fashion, as graphs do. Such approximation of higher-order relations may lead to a substantial loss of information, hence the need to use more general models than graphs. The most natural choice is to use hypergraphs

The density-peak clustering (DPC) method ([15]) clusters the data efficiently by fast searching density peaks. Recently, an improved DPC algorithm named 3DC method ([11]) was proposed for automatically detecting the correct structure of the clusters. However, it is difficult to select correct parameters for the DPC and 3DC methods and the local property of data set can’t be revealed due to their global

Bangla, being the fifth most spoken language in the world has its own distinct sign language with two methods (one-handed and two-handed) of representation. However, a standard automatic recognition system of Bangla sign language (BdSL) is still to be achieved. Though widely studied and explored by researchers in the past years, certain unaddressed issues like identifying unseen signs and both types

We introduce a new outdoor urban 3D pointcloud dataset, covering a total area of 2.7km2, sampled from three Swiss cities with different characteristics. The dataset is manually annotated for semantic segmentation with per-point labels, and is built using photogrammetry from images acquired by multirotors equipped with high-resolution cameras. In contrast to datasets acquired with ground LiDAR sensors

Recently predictive models based on the Choquet integral have been applied successfully in machine learning and multi criteria decision making context. The ability of the Choquet integral to capture non-linear dependencies and its comprehensibility make it a very appealing tool. Yet, its complexity is often a barrier to estimate model parameters. In fact, the number of monotonicity constraints grows

Retinal images have important reference value for the analysis of cardiovascular diseases such as diabetes and hypertension. However, because of the large number of artifacts at the end of the blood vessel and the unclearness of the intersection of the blood vessel, it will cause the inaccuracy of the retinal blood vessel segmentation, thereby affecting the diagnosis of retinal diseases. To solve this

Recently, great progress has been made in the field of Few-Shot Learning (FSL). While many different methods have been proposed, one of the key factors leading to higher FSL performance is surprisingly simple. It is the backbone network architecture used to embed the images of the few-shot tasks. While first works on FSL resorted to small architectures with just a few convolution layers, recent works

In this paper, we briefly review the fractional-order circular moments, such as fractional-order Zernike moments, fractional-order Fourier–Mellin moments, fractional-order Legendre–Fourier moments, and fractional-order Chebyshev–Fourier moments, which can characterize, analyze, and manipulate the information contained in an image with minimal redundancy. Also, they depend on an α parameter for better

This letter introduces a generalization of Isolation Forest (IF) based on the existing Extended IF (EIF). EIF has shown some interest compared to IF being for instance more robust to some artefacts. However, some information can be lost when computing the EIF trees since the sampled threshold might lead to empty branches. This letter introduces a generalized isolation forest algorithm called Generalized

Segmentation of retinal blood vessels is important for the analysis of diabetic retinopathy (DR). Existing methods do not prioritize the small and disconnected vessels for DR. With the aim of paying attention to the small and disconnected vessel regions, this study introduced Euler characteristics (EC) from topology to calculate the number of isolated objects on segmented vessel regions, which is the

Three-way concept analysis (3WCA) has been an emerging and important methodology for knowledge discovery and data analysis. Particularly, 3WCA can efficiently characterize the information of “jointly possessed” and “jointly not possessed” compared to the classical formal concept only can describe common attributes owned by objects. This property, typical of 3WCA has a huge potential in the field of

Attention mechanisms have achieved success in video-based person re-identification (re-ID). However, current global attentions tend to focus on the most salient parts, e.g., clothes, and ignore other subtle but valuable cues, e.g., hair, bag, and shoes. They still do not make full use of valuable information from diverse parts of human bodies. To tackle this issue, we propose a Diverse Part Attentive

Learning from imbalanced training data represents a major challenge that has triggered recent interest from both academia and industry. As far as classification is concerned, it has been observed that several algorithms provide low accuracy when designed out of imbalanced data sets, among which regularized quadratic discriminant analysis (R-QDA) is the most illustrative example. Based on recent asymptotic

We propose the analysis of a scalable parallel MCMC algorithm for graph coloring aimed at balancing the color class sizes, provided that a suitable number of colors is made available. Firstly, it is shown that the Markov chain converges to the target distribution by repeatedly sampling from suitable proposed distributions over the neighboring colors of each node, independently and hence in parallel

The field of deep subspace clustering has advanced rapidly in recent years. Ideas such as self-expression and self-supervision have led to innovative network design and improved clustering performance. However, it is observed that the nonlinear low-dimensional manifold constraint is valid in not only the ambient but also the latent feature spaces. Meanwhile, the issue of robustness has been largely

During the last decade, more and more Artificial Intelligence systems have been designed using complex and sophisticated architectures to reach unprecedented predictive performance. The side effect is an increase in opacity of their inner workings which is inadmissible when such systems are applied in critical domains (healthcare, finance and so on). The eXplainable AI (XAI) research field aims to

The automatic generation of poems from images is a classic task in natural language processing. Recently, it has gained tremendous research interest due to the help of neural sequence-to-sequence networks. The current methods are not qualified to generate poems under the joint control of the theme and style conditions, while these two key factors are critical to the quality of Chinese poetry. This

We propose an end-to-end trainable network that can simultaneously localize and recognize irregular text from images. Specifically, we find the feature incompatibility problem, which arises from the contradiction between detection and recognition tasks for feature extraction of the convolutional neural network, and propose to introduce the larger-scale features for the recognition part to improve the

Existing pedestrian segmentation and detection methods often show a significant drop in performance when heavy occlusion and deformation happen because most approaches rely on holistic modeling. Unlike many previous deep models that directly learn a holistic detector, in this paper, we introduce a pedestrian instance segmentation method with a prior structure of semantic parts named Part Mask R-CNN

Recognition of daily human activities in various locomotion and transportation modes has numerous applications like coaching users for behavior modification and maintaining a healthy lifestyle. Besides, applications and user interfaces aware of user mobility through their smartphones can also aid in urban transportation planning, smart parking, and vehicular traffic monitoring. In this paper, we explored

Previous literature suggests that perceptual similarity is an emergent property shared across deep visual representations. Experiments conducted on a dataset of human-judged image distortions have proven that deep features outperform classic perceptual metrics. In this work we take a further step in the direction of a broader understanding of such property by analyzing the capability of deep visual

The dual stream-based human action recognition model offers the advantage of high recognition accuracy, but the algorithm is less robust in case of lighting changes. The human skeleton has a strong ability to express human behavior and actions; however, the scene information is ignored. Drawing on the idea of the dual-stream model, this paper proposes a human skeleton and scene image-based dual-stream

Although Deep Neural Networks (DNNs) have achieved tremendous success in the face recognition task, utilizing them in resource-constrained environments with limited networking and computing is challenging. Such environments often demand a small model capable of being effectively trained on a small number of labeled training data, with low training complexity, and low-resolution input images. To address

Object detection has attracted growing attention due to its extensive application prospect, in which bounding box regression is an essential component. Dedicated to collaborative learning in bounding box regression, we explore the unified framework of smooth ℓ1 and intersection over union, named SLIoU. On the basis of that, we propose a SLIoU loss as localization loss, which focuses on the geometric

Web user behavioural recognition is the process by which web users are identified and distinguished through behavioural features. In this work, two sources of behavioural biometric data are analyzed for the development of this web user identification model, touch dynamics and the characteristics extracted from the periocular area related to the pupils, blinks and fixations. The approach adopted used

Consider a domain-adaptive supervised learning setting, where a classifier learns from labeled data in a source domain and unlabeled data in a target domain to predict the corresponding target labels. If the classifier’s assumption on the relationship between domains (e.g. covariate shift, common subspace, etc.) is valid, then it will usually outperform a non-adaptive source classifier. If its assumption

Feature selection is an important preprocessing step in machine learning. It helps to better understand the importance of some features and to reduce the dimensionality of a dataset, which improves machine learning and information extraction. Among the different existing methods for selecting features, filters are popular because they are independent from the model, which will be learnt afterwards

In state-of-the-art text-independent speaker verification systems, a discriminative deep neural network (DNN) model learns speaker-discriminative representations (x-vectors) for utterances using labeled data. For the verification task, a Probabilistic Linear Discriminant Analysis (PLDA) model is used to decide whether two x-vectors come from the same speaker. The PLDA scoring model assumes Gaussian