Sharif Digital Repository

Visual object tracking remains an active research field in computer vision due to persisting challenges with various problem-specific factors in real-world scenes. Many existing tracking methods based on discriminative correlation filters (DCFs) employ feature extraction networks (FENs) to model the target appearance during the learning process. However, using deep feature maps extracted from FENs based on different residual neural networks (ResNets) has not previously been investigated. This paper aims to evaluate the performance of 12 state-of-the-art ResNet-based FENs in a DCF-based framework to determine the best for visual tracking purposes. First, it ranks their best feature maps and... 

Visual object tracking remains an active research field in computer vision due to persisting challenges with various problem-specific factors in real-world scenes. Many existing tracking methods based on discriminative correlation filters (DCFs) employ feature extraction networks (FENs) to model the target appearance during the learning process. However, using deep feature maps extracted from FENs based on different residual neural networks (ResNets) has not previously been investigated. This paper aims to evaluate the performance of 12 state-of-the-art ResNet-based FENs in a DCF-based framework to determine the best for visual tracking purposes. First, it ranks their best feature maps and... 

The prerequisite of developing countries’ economic growth is to move along the technological development trajectory through technological learning, and large firms as hubs of technological knowledge, play an important role in this transition. In this paper, we tried to bridge two main taxonomies in the field of technological development, one of them referring to taxonomies of firms, and the other one referring to technological learning processes. We have identified technological learning processes in several post catch-up large firms through content analysis and then by employing a survey approach, we explore technological learning processes of Iranian large firms. The results indicate that... 

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... 

Computer networks courses are hard to teach as there are many details in the protocols and techniques involved that are difficult to grasp. Employing programming assignments as part of the course helps students to obtain a better understanding and gain further insight into the theoretical lectures. In this paper, the Partov simulation engine and experience using this engine in a computer networks course are discussed. Since 2009, various programming assignments based on the Partov system have been set to help students in their learning process. Student feedback has been very good; this has been quantified in two surveys in which a majority of students expressed their satisfaction with this... 

One of the main challenges of data streams is the occurrence of concept drift. Concept drift is the change of target (or feature) distribution, and can occur in different types: sudden, gradual, incremental or recurring. Because of the forgetting mechanism existing in the data stream learning process, recurring concepts has received much attention recently, and became a challenging problem. This paper tries to exploit the existence of recurring concepts in the learning process and improve the classification of data streams. It uses a pool of concepts to detect the reoccurrence of a concept using two methods: a Bayesian, and a heuristic method. Two approaches are used in the classification... 

The first spoken dialogue system is developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (γ) on the learning speed is investigated as the second contribution of the research. The optimal values for γ were found and the variation pattern of the action-value function (Q) in the learning process was obtained. A probabilistic policy for selecting actions is used in this work for the first time instead of greedy... 

Human Brain is one of the most wonderful and complex systems which is designed for ever; A huge complex network composed of neurons as tiny biological and chemical processors which are distributed and work together as a super parallel system to do control and vital activities of human body. Brain learning simulation and hardware implementation is one of the most interesting research areas in order to make artificial brain. One of the researches in this area is Active Learning Method in brief ALM. ALM is an adaptive recursive fuzzy learning algorithm based on brain functionality and specification which models a complex Multi Input Multi Output System as a fuzzy combination of Single Input... 

In this article, a universal collaborative and competitive approach is introduced for deployment of digital collections in an ideal Digital Library for future's educational system. A hierarchical structure is proposed to be used for browsing and searching within mass of digital contents provided for union of curriculums worldwide. The collaborative and open-source aspects of the system guarantee the growth of the Digital Library. On the other hand, the competitive and reviewing aspects guarantee the accuracy of the novel library contents. Two experiments confirm the need for such a universal Digital Library worldwide to enhance learning capabilities, increase accessibility, avoid redundancy... 

Nowadays, e-learning platforms are widely used by universities and other research-based and educational institutions. Despite lots of advantages these educational environments provide for organizations, yet there are many unresolved problems which cause instructors and training managers with some difficulties to get proper information about the students' learning behavior. On one hand, lack of tools to measure, assess, and evaluate the performance of learners in educational activities has led the educators to fail to guarantee the success of learning process. On the other hand, strict structure of learning materials prevents students to acquire knowledge based on their learning style.... 

In feed forward neural networks, hidden layer neurons' saturation conditions, which are the cause of flat spots on the error surface, is one of the main disadvantages of any conventional gradient descent learning algorithm. In this paper, we propose a novel complementary scheme for the learning based on a suitable combination of anti saturated hidden neurons learning process and accelerating methods like the momentum term and the parallel tangent technique. In our proposed method, a normalized saturation criterion (NSC) of hidden neurons, which is introduced in this paper, is monitored during learning process. When the NSC is higher than a specified threshold, it means that the algorithm... 

Attention as a cognitive aspect of brain activity is one of the most popular areas of brain studies. It has significant impact on the quality of other activities such as learning process and critical activities (e.g. driving vehicles). Because of its crucial influence on the learning process, it is one of the main aspects of research in education. In this study, we propose a brand new protocol of brain signal recording in order to classify human attention in educational environments. Unlike other protocols used to record EEG signals, our protocol does not require strong memory and strong language knowledge to carry out. To this end, we have recorded EEG signals of 12 subjects using the... 

Hierarchical reinforcement learning (HRL) has had a vast range of applications in recent years. Preparing mechanisms for autonomous acquisition of skills has been a main topic of research in this area. While different methods have been proposed to achieve this goal, few methods have been shown to be successful both in performance and also efficiency in terms of time complexity of the algorithm. In this paper, a linear time algorithm is proposed to find subgoal states of the environment in early episodes of learning. Having subgoals available in early phases of a learning task, results in building skills that dramatically increase the convergence rate of the learning process. © 2009 Springer... 

Although Face detection is not a recent activity in the field of image processing, it is still an open area for research. The greatest step in this field is the work reported by Viola and the recent analogous one is proposed by Huang et al. Both of them use similar features and also similar training process. The former is just for detecting upright faces, but the latter can detect multi-view faces in still grayscale images using new features called 'sparse feature'. Finding these features is very time consuming and inefficient by proposed methods. Here, we propose a new approach for finding sparse features using a genetic algorithm system. This method requires less computational cost and...