Sharif Digital Repository

Recent studies have demonstrated that high-level semantics in data can be captured using sparse representation. In this paper, we propose an approach to human body pose estimation in static images based on sparse representation. Given a visual input, the objective is to estimate 3D human body pose using feature space information and geometrical information of the pose space. On the assumption that each data point and its neighbors are likely to reside on a locally linear patch of the underlying manifold, our method learns the sparse representation of the new input using both feature and pose space information and then estimates the corresponding 3D pose by a linear combination of the bases... 

This paper introduces a novel framework for modeling temporal events with complex longitudinal dependency that are generated by dependent sources. This framework takes advantage of multidimensional point processes for modeling time of events. The intensity function of the proposed process is a mixture of intensities, and its complexity grows with the complexity of temporal patterns of data. Moreover, it utilizes a hierarchical dependent nonparametric approach to model marks of events. These capabilities allow the proposed model to adapt its temporal and topical complexity according to the complexity of data, which makes it a suitable candidate for real world scenarios. An online inference... 

Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be able to compare the strength of each property between images, relative attributes were introduced. However, since their introduction, hand-crafted and engineered features were used to learn increasingly complex models for the problem of relative attributes. This limits the applicability of those methods for more realistic cases. We introduce a deep neural network architecture for the task of relative attribute prediction. A convolutional neural network (ConvNet) is adopted to learn the features by including an... 

Estimation of 3D human pose from a single image is a challenging task because of ambiguities in projection from 3D space to the 2D image plane. A new two-stage deep convolutional neural network-based method is proposed for regressing the distance and angular difference matrices among body joints. Using the angular difference between body joints in addition to the distance between them in articulated objects such as human body can better model the structure of the shapes and increases the modelling capability of the learning method. Experimental results on HumanEva I and Human3.6M datasets show that the proposed method has substantial improvement in the mean per joint position error measure... 

Multiple human 3D pose estimation is a useful but challenging task in computer vison applications. The ambiguities in estimation of 2D and 3D poses of multiple persons can be verified by using multi-view frames, in which the occluded or self-occluded body parts of some persons might be visible in other camera views. But, when cameras are moving and uncalibrated, estimating the association of multiple human body parts among different camera views is a challenging task. This paper presents novel methods for multiple human 3D pose estimation and pose association in multi-view camera frames in an uncalibrated camera setup using an adversarial learning framework. The generator is a 3D pose... 

One of the main issues in colour image processing is changing objects' colour due to colour of illumination source. Colour constancy methods tend to modify overall image colour as if it was captured under natural light illumination. Without colour constancy, the colour would be an unreliable cue to object identity. Till now, many methods in colour constancy domain are presented. They are in two categories; statistical methods and learning-based methods. This paper presents a new statistical weighted algorithm for illuminant estimation. Weights are adjusted to highlight two key factors in the image for illuminant estimation, that is contrast and brightness. The focus was on the convex part of... 

One of the main issues in colour image processing is changing objects' colour due to colour of illumination source. Colour constancy methods tend to modify overall image colour as if it was captured under natural light illumination. Without colour constancy, the colour would be an unreliable cue to object identity. Till now, many methods in colour constancy domain are presented. They are in two categories; statistical methods and learning-based methods. This paper presents a new statistical weighted algorithm for illuminant estimation. Weights are adjusted to highlight two key factors in the image for illuminant estimation, that is contrast and brightness. The focus was on the convex part of... 

Many real-world systems and applications such as World Wide Web, and social interactions can be modeled as networks of interacting nodes. However, in many cases, one encounters the situation where the pattern of the node-to-node interactions (i.e., edges) or the structure of a network is unknown. We address this issue by studying the Network Reconstruction Problem: Given a network with missing edges, how is it possible to uncover the network structure based on certain observable quantities extracted from partial measurements? We propose a novel framework called CS-NetRec based on a newly emerged paradigm in sparse signal recovery called Compressive Sensing (CS). The results demonstrate that... 

The current multi-channel P2P video streaming architectures still suffer from several performance problems such as low Quality of Service (QoS) in unpopular channels. The P2P systems are inherently dynamic, and their performance problems could be categorized into four groups; peer churn, channel churn, uncooperative peers, and geographical distribution of peers. In this paper, for the first time, we develop a novel locality-incentive framework for multi-channel live video streaming. We propose a hierarchical overlay network architecture by utilizing a dual-mode locality-Awareness method (spatial and temporal). Moreover, an incentive mechanism for encouraging peers to dedicate their upload... 

Data streams are endless flow of data produced in high speed, large size and usually non-stationary environments. The main property of these streams is the occurrence of concept drifts. Using decision trees is shown to be a powerful approach for accurate and fast learning of data streams. In this paper, we present an incremental regression tree that can predict the target variable of newly incoming instances. The tree is updated in the case of occurring concept drifts either by altering its structure or updating its embedded models. Experimental results show the effectiveness of our algorithm in speed and accuracy aspects in comparison to the best state-of-the-art methods  

The spread of information cascades over social networks forms the diffusion networks. The latent structure of diffusion networks makes the problem of extracting diffusion links difficult. As observing the sources of information is not usually possible, the only available prior knowledge is the infection times of individuals. We confront these challenges by proposing a new method called DNE to extract the diffusion networks by using the time-series data. We model the diffusion process on information networks as a Markov random walk process and develop an algorithm to discover the most probable diffusion links. We validate our model on both synthetic and real data and show the low dependency... 

In this letter, we introduce a semi-supervised manifold regularization framework for human pose estimation. We utilize the unlabeled data to compensate for the complexities in the input space and model the underlying manifold by a nearest neighbor graph. We argue that the optimal graph is a subgraph of the k nearest neighbors (k-NN) graph. Then, we estimate distances in the output space to approximate this subgraph. In addition, we use the underlying manifold of the points in the output space to introduce a novel regularization term which captures the correlation among the output dimensions. The modified graph and the proposed regularization term are utilized for a smooth regression over... 

In this paper, we introduce a novel approach based on Tucker Decomposition and quasi-periodic nature of ECG signal for fetal ECG extraction from abdominal ECG mixture. We adapt variable periodicity constraint of the ECG components to main objective function of the Tucker Decomposition and shape it to matrix form in order to simply optimize the objective function. We form a 3rd order tensor by stacking the mixed multichannel ECG and reconstructed fetal and maternal subspaces using BSS methods in order to have the benefit of further artificial observations, and apply our proposed penalized decomposition on it. The proposed method is evaluated on synthetic and real datasets using the criteria... 

In this article, we look at early, recent, and state-of-the-art methods for registration of medical images using a range of high-performance computing (HPC) architectures including symmetric multiprocessing (SMP), massively multiprocessing (MMP), and architectures with distributed memory (DM), and nonuniform memory access (NUMA). The article is designed to be self-sufficient. We will take the time to define and describe concepts of interest, albeit briefly, in the context of image registration and HPC. We provide an overview of the registration problem and its main components in the section "Registration." Our main focus will be HPC-related aspects, and we will highlight relevant issues as... 

Online media play an important role in information societies by providing a convenient infrastructure for different processes. Information diffusion that is a fundamental process taking place on social and information networks has been investigated in many studies. Research on information diffusion in these networks faces two main challenges: (1) In most cases, diffusion takes place on an underlying network, which is latent and its structure is unknown. (2) This latent network is not fixed and changes over time. In this article, we investigate the diffusion network extraction (DNE) problem when the underlying network is dynamic and latent. We model the diffusion behavior (existence... 

Most of the supervised classification algorithms are proposed to classify newly seen instances based on their learned label space. However, in the case of data streams, conceptevolution is inevitable. In this paper we propose a support vector based approach for classification beyond the learned label space in data streams with regard to other challenges in data streams like concept-drift and infinite-length. We maintain the boundaries of observed classes through the stream by utilizing a support vector based method (SVDD). Newly arrived instances located outside these boundaries will be analyzed by constructing neighborhood graph to detect the emergence of a class beyond the learned label... 

Multiple human 3D pose estimation is a challenging task. It is mainly because of large variations in the scale and pose of humans, fast motions, multiple persons in the scene, and arbitrary number of visible body parts due to occlusion or truncation. Some of these ambiguities can be resolved by using multiview images. This is due to the fact that more evidences of body parts would be available in multiple views. In this work, a novel method for multiple human 3D pose estimation using evidences in multiview images is proposed. The proposed method utilizes a fully connected pairwise conditional random field that contains two types of pairwise terms. The first pairwise term encodes the spatial... 

Poisson factorization is a probabilistic model of users and items for recommendation systems, where the so-called implicit consumer data is modeled by a factorized Poisson distribution. There are many variants of Poisson factorization methods who show state-of-the-art performance on real-world recommendation tasks. However, most of them do not explicitly take into account the temporal behavior and the recurrent activities 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... 

One of the most challenging tasks in computer vision is human action recognition. The recent development of depth sensors has created new opportunities in this field of research. In this paper, a novel supervised spatio-temporal kernel descriptor (SSTKDes) is proposed from RGB-depth videos to establish a discriminative and compact feature representation of actions. To enhance the descriptive and discriminative ability of the descriptor, extracted primary kernel-based features are transformed into a new space by exploiting a supervised training strategy; i.e., large margin nearest neighbor (LMNN). The LMNN highly reduces the error of a nearest neighbor classifier by minimizing the intra-class... 

Adaptive thresholding methods have proved to yield a high signal-to-noise ratio (SNR) and fast convergence in sparse signal recovery. The robustness of a class of iterative sparse recovery algorithms, such as the iterative method with adaptive thresholding, has been found to outperform the state-of-art methods in respect of reconstruction quality, convergence speed, and sensitivity to noise. In this study, the authors introduce a new method for compressed sensing, using the sensing matrix and measurements. In our method, they iteratively threshold the signal and project the thresholded signal onto the translated null space of the sensing matrix. The threshold level is assigned adaptively....