Sharif Digital Repository

In this article we tackle the problem of multi-party conversation summarization. We investigate the role of discourse segmentation of a conversation on meeting summarization. First, an unsupervised function segmentation algorithm is proposed to segment the transcript into functionally coherent parts, such as Monologuei (which indicates a segment where speaker i is the dominant speaker, e.g., lecturing all the other participants) or Discussionx1x2,...,xn (which indicates a segment where speakers x 1 to xn involve in a discussion). Then the salience score for a sentence is computed by leveraging the score of the segment containing the sentence. Performance of our proposed segmentation and... 

We explore the dictionary learning problem for sparse representation when the signals are dependent. In this paper, a first-order Markovian model is considered for dependency of the signals, that has many applications especially in medical signals. It is shown that the considered dependency among the signals can degrade the performance of the existing dictionary learning algorithms. Hence, we propose a method using the Maximum Log-likelihood Estimator (MLE) and the Expectation Minimization (EM) algorithm to learn the dictionary from the signals generated under the first-order Markovian model. Simulation results show the efficiency of the proposed method in comparison with the... 

Since that heuristic state space planners have been very successful in classical planning, this approach is currently the most popular strategy in dealing with temporal planning, too. However, all current state-space temporal planners use a search method known as decision epoch planning, which is not complete for problems with required concurrency. In theory, this flaw can be overcome by employing another search method, called temporally lifted progression planning. In this paper, we show that there are two major problems which, if not tackled properly, can cause the latter method to be very inefficient in practice. The first problem is dealing with the remarkably large state space of... 

Aggregation services play an important role in the domain of Wireless Sensor Networks (WSNs) because they significantly reduce the number of required data transmissions, and improve energy efficiency on those networks. In most of the existing aggregation methods that have been developed based on the mathematical models or functions, the user of the WSN has not access to the original observations. In this paper, we propose an algorithm which let the base station access the observations by introducing a distributed method for computing the Principal Component Analysis (PCA). The proposed algorithm is based on transmission workload of the intermediate nodes. By using PCA, we aggregate the... 

In this paper, we aim to improve meeting summarization performance using discourse specific information. Since there are intrinsically different characteristics in utterances in different types of function segments, e.g., Monologue segments versus Discussion ones, we propose a new summarization framework where different summarizers are used for different segment types. For monologue segments, we adopt the integer linear programming-based summarization method; whereas for discussion segments, we use a graph-based method to incorporate speaker information. Performance of our proposed method is evaluated using the standard AMI meeting corpus. Results show a good improvement over previous... 

In this paper, the problem of convolutive source separation via multimodal soft Nonnegative Matrix Co-Factorization (NMCF) is addressed. Different aspects of a phenomenon may be recorded by sensors of different types (e.g., audio and video of human speech), and each of these recorded signals is called a modality. Since the underlying phenomenon of the modalities is the same, they have some similarities. Especially, they usually have similar time changes. It means that changes in one of them usually correspond to changes in the other one. So their active or inactive periods are usually similar. Assuming this similarity, it is expected that the activation coefficient matrices of their... 

In this research, a new metaheuristic optimization algorithm, inspired by biological nervous systems and artificial neural networks (ANNs) is proposed for solving complex optimization problems. The proposed method, named as neural network algorithm (NNA), is developed based on the unique structure of ANNs. The NNA benefits from complicated structure of the ANNs and its operators in order to generate new candidate solutions. In terms of convergence proof, the relationship between improvised exploitation and each parameter under asymmetric interval is derived and an iterative convergence of NNA is proved theoretically. In this paper, the NNA with its interconnected computing unit is examined... 

In this paper, we propose an algorithm for recovery of sparse and low-rank components of matrices using an iterative method with adaptive thresholding. In each iteration of the algorithm, the low-rank and sparse components are obtained using a thresholding operator. The proposed algorithm is fast and can be implemented easily. We compare it with the state-of-the-art algorithms. We also apply it to some applications such as background modeling in video sequences, removing shadows and specularities from face images, and image restoration. The simulation results show that the proposed algorithm has a suitable performance with low run-time. © 2017 Elsevier Inc  

Human action recognition from skeletal data is one of the most popular topics in computer vision which has been widely studied in the literature, occasionally with some very promising results. However, being supervised, most of the existing methods suffer from two major drawbacks; (1) too much reliance on massive labeled data and (2) high sensitivity to outliers, which in turn hinder their applications in such real-world scenarios as recognizing long-term and complex movements. In this paper, we propose a novel unsupervised 3D action recognition method called Sparseness Embedding in which the spatiotemporal representation of action sequences is nonlinearly projected into an unwarped feature... 

Embedded systems have migrated from special-purpose hardware to commodity hardware. These systems have also tended to Mixed-Criticality (MC) implementations, executing applications of different criticalities upon a shared platform. Multi-core processors, which are commonly used to design MC systems, bring out new challenges due to the process variations. Power and frequency asymmetry affects the predictability of embedded systems. In this work, variation-aware techniques are explored to not only improve the reliability of MC systems, but also aid the scheduling and energy saving of them. We leverage the core-to-core (C2C) variations to protect high-criticality tasks and provide full service... 

In this paper, we propose a new method to reconstruct a signal corrupted by noise where both signal and noise are sparse but in different domains. The main contribution of our algorithm is its low complexity; it has much lower run-time than most other algorithms. The reconstruction quality of our algorithm is both objectively (in terms of PSNR and SSIM) and subjectively better or comparable to other state-of-the-art algorithms. We provide a cost function for our problem, present an iterative method to find its local minimum, and provide the analysis of the algorithm. As an application of this problem, we apply our algorithm for Salt-and-Pepper noise (SPN) and Random-Valued Impulsive Noise... 

A state-of-the-art algorithm for perspective projection reconstruction of non-rigid surfaces from single-view and realistic videos is proposed. It overcomes the limitations arising from the usage of orthographic camera model and also the complexity and non-linearity issues of perspective projection equation. Unlike traditional non-rigid structure-from-motion (NRSfM) methods, which have been studied only on synthetic datasets and controlled lab environments that require some prior constraints (such as manually segmented objects, limited rotations and occlusions, and full-length trajectories); the proposed method can be used in realistic video sequences. In addition, contrary to previous... 

Given a social network modeled as a weighted graph GG, the influence maximization problem seeks kk vertices to become initially influenced, to maximize the expected number of influenced nodes under a particular diffusion model. The influence maximization problem has been proven to be NP-hard, and most proposed solutions to the problem are approximate greedy algorithms, which can guarantee a tunable approximation ratio for their results with respect to the optimal solution. The state-of-the-art algorithms are based on Reverse Influence Sampling (RIS) technique, which can offer both computational efficiency and non-trivial (1-1/e-ϵ)-approximation ratio guarantee for any epsilon >0ϵ>0.... 

In this letter, a new adaptive Gaussian process (GP) frame work for signal extrapolation is proposed. Signal extrapolation is an essential task in many applications such as concealment of corrupted data in image and video communications. While possessing many interesting properties, Gaussian process priors with inappropriate stationary kernels may create extremely blurred edges in concealed areas of the image. To address this problem, we propose adaptive non-stationary kernels in a Gaussian process framework. The proposed adaptive kernel functions are defined based on the hypothesized edges of the missing areas. Experimental results verify the effectiveness of the proposed method compared to... 

In this paper, we propose a Gaussian Process Regression (GPR) framework for concealment of corrupted motion vectors in predictive video coding of packet video systems. The problem of estimating the lost motion vectors is modelled as a kernel construction problem in a Bayesian framework. First, to describe the similarity between the neighboring motion vectors, a kernel function is defined. Then the parameters of the kernel function is estimated as the coefficients of a linear Bayesian estimator. The experimental results verify the superiority of the proposed algorithm over the conventional and state of the art motion vector concealment methods. Moreover, noticeable improvements on both... 

This letter proposes a sparse diffusion algorithm for 1-bit compressed sensing (CS) in wireless sensor networks, and the algorithm is inherently robust against impulsive noise. The approach exploits the diffusion strategy from distributed learning in the 1-bit CS framework. To estimate a common sparse vector cooperatively from only the sign of measurements, a steepest descent method that minimizes the suitable global and local convex cost functions is used. A diffusion strategy is suggested for distributive learning of the sparse vector. A new application of the proposed algorithm to sparse channel estimation is also introduced. The proposed sparse diffusion algorithm is compared with both... 

This paper considers the problem of interpolating signals defined on graphs. A major presumption considered by many previous approaches to this problem has been low-pass/band-limitedness of the underlying graph signal. However, inspired by the findings on sparse signal reconstruction, we consider the graph signal to be rather sparse/compressible in the Graph Fourier Transform (GFT) domain and propose the Iterative Method with Adaptive Thresholding for Graph Interpolation (IMATGI) algorithm for sparsity promoting interpolation of the underlying graph signal. We analytically prove convergence of the proposed algorithm. We also demonstrate efficient performance of the proposed IMATGI algorithm... 

In this paper, we study the problem of learning the structure of Bayesian networks from data, which takes a dataset and outputs a directed acyclic graph. This problem is known to be NP-hard. Almost most of the existing algorithms for structure learning can be classified into three categories: constraint-based, score-based, and hybrid methods. The K2 algorithm, as a score-based algorithm, takes a random order of variables as input and its efficiency is strongly dependent on this ordering. Incorrect order of variables can lead to learning an incorrect structure. Therefore, the main challenge of this algorithm is strongly dependency of output quality on the initial order of variables. The main... 

This letter deals with the problem of moving target localization in distributed multiple-input multiple-output (MIMO) radar systems using time delay (TD) and Doppler shift (DS) measurements. The proposed solution to this problem consists of two stages. In the first stage, an initial estimation of target location is obtained by solving the formulated maximum likelihood (ML) problem based on the TD measurements. In the second stage, by recognizing the obtained position estimate in the previous stage as a priori data and exploiting the DS measurements, another ML problem is formulated, which is efficiently solved via a tractable numerical method to produce a simultaneous estimation of target... 

A state-of-the-art algorithm for perspective projection reconstruction of non-rigid surfaces from single-view and realistic videos is proposed. It overcomes the limitations arising from the usage of orthographic camera model and also the complexity and non-linearity issues of perspective projection equation. Unlike traditional non-rigid structure-from-motion (NRSfM) methods, which have been studied only on synthetic datasets and controlled lab environments that require some prior constraints (such as manually segmented objects, limited rotations and occlusions, and full-length trajectories); the proposed method can be used in realistic video sequences. In addition, contrary to previous...