Sharif Digital Repository

In automatic image annotation (AIA) different features describe images from different aspects or views. Part of information embedded in some views is common for all views, while other parts are individual and specific. In this paper, we present the Mvg-NMF approach, a multi-view-group non-negative matrix factorization (NMF) method for an AIA system which considers both common and individual factors. The NMF framework discovers a latent space by decomposing data into a set of non-negative basis vectors and coefficients. The views divided into homogeneous groups and latent spaces are extracted for each group. After mapping the test images into these spaces, a unified distance matrix is... 

This paper presents a novel approach for detection and recognition of multi-view faces whose location is unknown and the illumination conditions are varying. The detection of faces is accomplished after canceling the effect of the various illumination conditions by using a proposed filter. Because of the independency of the approach to skin color of face, the persons with every kind of skin colors are detected even in completely dark environments. Next, the detected faces are recognized. It is a well known technique to combine the feature based methods with the template based methods in face recognition. Our experiments show that we can combine some proposed aspects of the feature based... 

This paper presents a novel approach for detection and recognition of multi-view faces whose location is unknown and the illumination conditions are varying. The illumination is a big problem in the face detection and recognition aspects. Our proposed method doesn't use the skin color information for face detection. The detection of faces is accomplished after canceling the effect of the various illumination conditions. Two completely different methods are proposed for face detection in this paper. Because of the independency of the approaches to the face's skin color, the persons with every kind of skin colors are detected even in completely dark environments. Next, the detected faces are... 

With thousands of new questions posted every day on popular Q&A websites, there is a need for automated and accurate software solutions to replace manual moderation. In this paper, we address the critical drawbacks of crowdsourcing moderation actions in Q&A communities and demonstrate the ability to automate moderation using the latest machine learning models. From a technical point, we propose a multi-view approach that generates three distinct feature groups that examine a question from three different perspectives: 1) question-related features extracted using a BERT-based regression model; 2) context-related features extracted using a named-entity-recognition model; and 3) general lexical... 

Connecting your system or device to an insecure network can create the possibility of infecting by the unwanted files. Malware is every malicious code that has the potential to harm any computer or network. So, detecting harmful files is a crucial duty and an important role in any system. Machine learning approaches use a variety of features such as Opcodes, Bytecodes, and System-calls to achieve accurate malware identification. Each of these feature sets provides a unique semantic view, while, considering the effect of altogether is more reliable to detect attacks. Malware can disguise itself in some views, but hiding in all views will be much more difficult. Multi-View Learning (MVL) is an... 

This paper presents a novel approach for detection and recognition of multi-view faces whose size and location is unknown and the illumination conditions are varying. The illumination is a big problem in face detection and recognition. In this paper, a new pre-processing method is proposed in order to cancel the effect of various illumination conditions on a face. Then, a binary face is obtained that its pixels are 0 or 1. Next, a fuzzy face model is produced from the distribution of zeros in the binary face. The model is used in order to detect faces in images by using a fuzzy approach. Because of the independency of the detection method to the skin color of face, persons with every kind of... 

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... 

Automatic Image Annotation (AIA) helps image retrieval systems by predicting tags for images. In this paper, we propose an AIA system using Non-negative Matrix Factorization (NMF) framework. The NMF framework discovers a latent space, by factorizing data into a set of non-negative basis and coefficients. To model the images, multiple features are extracted, each one represents images from a specific view. We use multi-view graph regularization NMF and allow NMF to choose a different number of basis vectors for each view. For tag prediction, each test image is mapped onto the multiple latent spaces. The distances of images in these spaces are used to form a unified distance matrix. The... 

In automatic image annotation (AIA) different features describe images from different aspects or views. Part of information embedded in some views is common for all views, while other parts are individual and specific. In this paper, we present the Mvg-NMF approach, a multi-view-group non-negative matrix factorization (NMF) method for an AIA system which considers both common and individual factors. The NMF framework discovers a latent space by decomposing data into a set of non-negative basis vectors and coefficients. The views divided into homogeneous groups and latent spaces are extracted for each group. After mapping the test images into these spaces, a unified distance matrix is... 

In large databases, availability of labeled training data is mostly prohibitive in classification. Semi-supervised algorithms are employed to tackle the lack of labeled training data problem. Video databases are the epitome for such a scenario; that is why semi-supervised learning has found its niche in it. Graph-based methods are a promising platform for semi-supervised video classification. Based on the multiview characteristic of video data, different features have been proposed (such as SIFT, STIP and MFCC) which can be utilized to build a graph. In this paper, we have proposed a new classification method which fuses the results of manifold regularization over different graphs. Our... 

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... 

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... 

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... 

This paper presents a novel approach for detection and recognition of multi-view faces whose location is unknown and the illumination conditions are varying. The illumination is a big problem in the face detection and recognition aspects. Two completely different methods are proposed for face detection in this paper. Our proposed methods do not use the skin colour information for face detection. The detection of faces is accomplished after cancelling the effect of the various illumination conditions. Because of the independency of the approaches to the face's skin colour, persons with every kind of skin colours are detected even in completely dark environments. Next, the detected faces are... 

Multi-view imaging and display systems has taken a divide and conquer approach to 3D sensing and visualization. We aim to make more reliable and robust automatic feature extraction and natural 3D feature construction from 2D features detected on a pair of frontal and profile view face images. We propose several heuristic algorithms to minimize possible errors introduced by prevalent imperfect orthogonal condition and non-coherent luminance trying to address the problems incurred with illumination discrepancies on common surface points in accommodation of multi-views. In our approach, we first extract the 2D features that are visible to both cameras in both views. Then, we estimate the... 

Multi view imaging has attracted increasing attention recently and has become one of the potential avenues in future video systems. We aim to make more reliable and robust automatic feature extraction and natural 3D feature construction from 2D features detected on a pair of frontal and profile view face images. We propose several heuristic algorithms to minimize possible errors introduced by prevalent non-perfect orthogonal condition and non-coherent luminance. In our approach, we first extract the 2D features that are visible to both cameras in both views. Then, we estimate the coordinates of the features in the hidden profile view based on the visible features extracted in the two... 

Multi view imaging has attracted increasing attention recently and has become one of the potential avenues in future video systems. We aim to make more reliable and robust automatic feature extraction and natural 3D feature construction from 2D features detected on a pair of frontal and profile view face images. We propose several heuristic algorithms to minimize possible errors introduced by prevalent non-perfect orthogonal condition and non-coherent luminance. In our approach, we first extract the 2D features that are visible to both cameras in both views. Then, we estimate the coordinates of the features in the hidden profile view based on the visible features extracted in the two...