Sharif Digital Repository

Twitter sentiment analysis, which often focuses on predicting the polarity of tweets, has attracted increasing attention over the last years, in particular with the rise of deep learning (DL). In this paper, we propose a new task: predicting the predominant sentiment among (first-order) replies to a given tweet. Therefore, we created RETwEET, a large dataset of tweets and replies manually annotated with sentiment labels. As a strong baseline, we propose a two-stage DL-based method: first, we create automatically labeled training data by applying a standard sentiment classifier to tweet replies and aggregating its predictions for each original tweet; our rationale is that individual errors... 

The growing popularity of community question answering websites can be seen by the growing number of users. Many methods are proposed to identify talented users in these communities, but many of them suffer from vocabulary mismatches. The solution to this problem can be found in translation approaches. The present paper proposes two translation methods for extracting more relevant translations. The proposed methods rely on the attention mechanism. The methods use multi-label classifiers that take each question as input and predict the skills related to the question. Using the attention mechanism, the model is able to focus on specific parts of the given input and predict the correct labels.... 

This paper addresses the issue of finding and accessing desired items when a large amount of data items are concerned, by proposing some concepts based on Tree Search Structure -a hierarchical structure for information retrieval. The proposed concepts are applicable to several environments such as File Managers on PCs, help tree views, site maps, taxonomies, and cell phones. A software tool, FTS (File Tree Search), that is developed to utilize the proposed concepts is also presented  

Locating critical objects is crucial in various security applications and industries. For example, in security applications, such as in airports, these objects might be hidden or covered under shields or secret sheaths. Millimeter-wave images can be utilized to discover and recognize the critical objects out of the hidden cases without any health risk due to their non-ionizing features. However, millimeter-wave images usually have waves in and around the detected objects, making object recognition difficult. Thus, regular image processing and classification methods cannot be used for these images and additional pre-processings and classification methods should be introduced. This paper... 

Vulnerability detection is an important challenge in the security community. Many different techniques have been proposed, ranging from symbolic execution to fuzzing in order to help in identifying vulnerabilities. Even though there has been considerable improvement in these approaches, they perform poorly on a large scale code basis. There has also been an alternate approach, where software metrics are calculated on the overall code structure with the hope of predicting code segments more likely to be vulnerable. The logic has been that more complex code with respect to the software metrics, will be more likely to contain vulnerabilities. In this paper, we conduct an empirical study with a... 

The amount of high dimensional data produced by visual sensors in the smart environments and by autonomous vehicles is increasing exponentially. In order to search and model this data for real-time applications, the dimensionality of the data should be reduced. In this paper, a novel dimensionality reduction algorithm based on fuzzy rough set theory, called Centralized Binary Mapping (CBM), is proposed. The fuzzy CBM kernel is used for extracting the central elements and the memory cells from the blocks of high dimensional data. The proposed applications of CBM in this paper include hashing and generative modelling of multimedia big data. The robustness of the proposed CBM based hashing... 

Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad range of real-world scenarios, a number of large-scale benchmark datasets have been established, on which considerable methods have been developed and demonstrated with significant progress in recent years - predominantly by recent deep learning (DL)-based methods. This survey aims to systematically investigate the current DL-based visual tracking methods, benchmark datasets, and evaluation metrics. It also extensively evaluates and analyzes the leading visual tracking methods. First, the fundamental... 

Semantic segmentation is one of the basic, yet essential scene understanding tasks for an autonomous agent. The recent developments in supervised machine learning and neural networks have enjoyed great success in enhancing the performance of the state-of-the-art techniques for this task. However, their superior performance is highly reliant on the availability of a large-scale annotated dataset. In this letter, we propose a novel fully unsupervised semantic segmentation method, the so-called Information Maximization and Adversarial Regularization Segmentation (InMARS). Inspired by human perception which parses a scene into perceptual groups, rather than analyzing each pixel individually, our... 

Several reasons such as no free lunch theorem indicates that any learning algorithm in combination with a specific feature selection (FS) technique may give more accurate estimation than other learning algorithms. Therefore, there is not a universal approach that outperforms other algorithms. Moreover, due to the large number of FS techniques, some recommended solutions such as using synthetic dataset or combining different FS techniques are very tedious and time consuming. In this study to tackle the issue of more accurate estimation of NPPs parameters, the performance of the major supervised learning algorithms in combination with the different FS techniques which are appropriate for... 

The k-means is the most popular clustering algorithm, but, as it needs too many distance computations, its speed is dramatically fall down against high-dimensional data. Although, there are some quite fast variants proposed in literature, but, there is still much room for improvement against high-dimensional large-scale datasets. What proposed here, k-means-g*, is based on a simple geometric concept. For four distinct points, if distance between all pairs except one pair are known, then, a lower bound can be determined for the unknown distance. Utilizing this technique in the assignment step of the k-means, many high-dimensional distance computations can be easily ignored, where small amount... 

Breast cancer is the most common malignancy in women worldwide, and is responsible for more than half a million deaths each year. The appropriate therapy depends on the evaluation of the expression of various biomarkers, such as the human epidermal growth factor receptor 2 (HER2) transmembrane protein, through specialized techniques, such as immunohistochemistry or in situ hybridization. In this work, we present the HER2 on hematoxylin and eosin (HEROHE) challenge, a parallel event of the 16th European Congress on Digital Pathology, which aimed to predict the HER2 status in breast cancer based only on hematoxylin–eosin-stained tissue samples, thus avoiding specialized techniques. The... 

Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad range of real-world scenarios, a number of large-scale benchmark datasets have been established, on which considerable methods have been developed and demonstrated with significant progress in recent years - predominantly by recent deep learning (DL)-based methods. This survey aims to systematically investigate the current DL-based visual tracking methods, benchmark datasets, and evaluation metrics. It also extensively evaluates and analyzes the leading visual tracking methods. First, the fundamental... 

Data streams have some unique properties which make them applicable in precise modeling of many real data mining applications. The most challenging property of data streams is the occurrence of "concept drift". Recurring concepts is a type of concept drift which can be seen in most of real world problems. Detecting recurring concepts makes it possible to exploit previous knowledge obtained in the learning process. This leads to quick adaptation of the learner whenever a concept reappears. In this paper, we propose a learning algorithm called Pool and Accuracy based Stream Classification with some variations, which takes the advantage of maintaining a pool of classifiers to track recurring... 

In the last decade, there has been a growing interest in distance function learning for semi-supervised clustering settings. In addition to the earlier methods that learn Mahalanobis metrics (or equivalently, linear transformations), some nonlinear metric learning methods have also been recently introduced. However, these methods either allow limited choice of distance metrics yielding limited flexibility or learn nonparametric kernel matrices and scale very poorly (prohibiting applicability to medium and large data sets). In this paper, we propose a novel method that learns low-rank kernel matrices from pairwise constraints and unlabeled data. We formulate the proposed method as a trace... 

Clustering is the problem of finding relations in a data set in an supervised manner. These relations can be extracted using the density of a data set, where density of a data point is defined as the number of data points around it. To find the number of data points around another point, region queries are adopted. Region queries are the most expensive construct in density based algorithm, so it should be optimized to enhance the performance of density based clustering algorithms specially on large data sets. Finding the optimum set of region queries to cover all the data points has been proven to be NP-complete. This optimum set is called the skeletal points of a data set. In this paper, we... 

In the past few years, the application of surveillance for security and smart cities are growing rapidly. The human detection based on the surveillance videos is a complex task and traditional clothing such as headscarf makes this task even more difficult. The surveillance systems designed for many countries are required to be able to recognize the people with these traditional clothing. In this paper, a computer vision system for partially covered face detection in low resolution surveillance videos containing traditional Middle Eastern clothing including the headscarf is presented. The proposed framework uses a combination of Haar cascade and Locally Binary Patterns Histogram (LBPH) for... 

Poisson Factorization (PF) is the gold standard framework for recommendation systems with implicit feedback whose variants show state-of-the-art performance on real-world recommendation tasks. However, they do not explicitly take into account the temporal behavior of users which is essential to recommend the right item to the right user at the right time. In this paper, we introduce Recurrent Poisson Factorization (RPF) framework that generalizes the classical PF methods by utilizing a Poisson process for modeling the implicit feedback. RPF treats time as a natural constituent of the model, and takes important factors for recommendation into consideration to provide a rich family of... 

The human impact on the coastal ecosystems is a global environmental concern. Due to the growing urbanization, industrialization, and transportation, this impact on the living and non-living components of the coastal area is expected to further increase in the coming years. Artificial intelligence based automation of the coastal monitoring, including data collection, analysis and decision making, provides real-time insights and opportunities for large-scale coastal management and governance. In this paper, a framework for autonomous litter surveying and human activity monitoring for governance intelligence in coastal eco-cyber-physical systems (ecoCystem) is presented. A large dataset of... 

Common Spatial Pattern (CSP) is a powerful feature extraction method in brain-computer interface (BCI) systems. However, the CSP method has some deficiencies that limit its beneficiary. First, this method is not useful when data is noisy, and it is necessary to have a large dataset because CSP is inclined to overfit. Second, the CSP method uses just the spatial information of the data, and it cannot incorporate the temporal and spectral information. In this paper, we propose a new CSP-based algorithm which is capable of employing the information in all dimensions of data. Also, by defining the regularization term for each mode of information, we can diminish the noise effects and overfitting... 

Sparse-view computed tomography (CT) is recently proposed as a promising method to speed up data acquisition and alleviate the issue of CT high dose delivery to the patients. However, traditional reconstruction algorithms are time-consuming and suffer from image degradation when faced with sparse-view data. To address this problem, we propose a new framework based on deep learning (DL) that can quickly produce high-quality CT images from sparsely sampled projections and is able for clinical use. Our DL-based proposed model is based on the convolution, and residual neural networks in a parallel manner, named the parallel residual neural network (PARS-Net). Besides, our proposed PARS-Net model...