Results for "Shervin Minaee"

total 83took 0.12s
Image Segmentation Using Overlapping Group SparsityNov 23 2016Nov 26 2016Sparse decomposition has been widely used for different applications, such as source separation, image classification and image denoising. This paper presents a new algorithm for segmentation of an image into background and foreground text and graphics ... More
Palmprint Recognition Using Deep Scattering Convolutional NetworkMar 30 2016Palmprint recognition has drawn a lot of attention during the recent years. Many algorithms have been proposed for palmprint recognition in the past, majority of them being based on features extracted from the transform domain. Many of these transform ... More
Screen Content Image Segmentation Using Sparse Decomposition and Total Variation MinimizationFeb 07 2016Jul 26 2016Sparse decomposition has been widely used for different applications, such as source separation, image classification, image denoising and more. This paper presents a new algorithm for segmentation of an image into background and foreground text and graphics ... More
Fingerprint Recognition Using Translation Invariant Scattering NetworkSep 11 2015Nov 26 2015Fingerprint recognition has drawn a lot of attention during last decades. Different features and algorithms have been used for fingerprint recognition in the past. In this paper, a powerful image representation called scattering transform/network, is ... More
Screen Content Image Segmentation Using Robust Regression and Sparse DecompositionJul 08 2016This paper considers how to separate text and/or graphics from smooth background in screen content and mixed document images and proposes two approaches to perform this segmentation task. The proposed methods make use of the fact that the background in ... More
Image Decomposition Using a Robust Regression ApproachSep 13 2016This paper considers how to separate text and/or graphics from smooth background in screen content and mixed content images and proposes an algorithm to perform this segmentation task. The proposed methods make use of the fact that the background in each ... More
Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional NetworkFeb 04 2019Facial expression recognition has been an active research area over the past few decades, and it is still challenging due to the high intra-class variation. Traditional approaches for this problem rely on hand-crafted features such as SIFT, HOG and LBP, ... More
Screen Content Image Segmentation Using Least Absolute Deviation FittingJan 15 2015Feb 19 2015We propose an algorithm for separating the foreground (mainly text and line graphics) from the smoothly varying background in screen content images. The proposed method is designed based on the assumption that the background part of the image is smoothly ... More
Image Segmentation Using Overlapping Group SparsityNov 23 2016Sparse decomposition has been widely used for different applications, such as source separation, image classification and image denoising. This paper presents a new algorithm for segmentation of an image into background and foreground text and graphics ... More
MTBI Identification From Diffusion MR Images Using Bag of Adversarial Visual FeaturesJun 27 2018In this work, we propose bag of adversarial features (BAF) for identifying mild traumatic brain injury (MTBI) patients from their diffusion magnetic resonance images (MRI) (obtained within one month of injury) by incorporating unsupervised feature learning ... More
Identifying Mild Traumatic Brain Injury Patients From MR Images Using Bag of Visual WordsOct 18 2017Feb 14 2018Mild traumatic brain injury (mTBI) is a growing public health problem with an estimated incidence of one million people annually in US. Neurocognitive tests are used to both assess the patient condition and to monitor the patient progress. This work aims ... More
Face Recognition Using Scattering Convolutional NetworkJul 30 2016Face recognition has been an active research area in the past few decades. In general, face recognition can be very challenging due to variations in viewpoint, illumination, facial expression, etc. Therefore it is essential to extract features which are ... More
Iris Recognition Using Scattering Transform and Textural FeaturesJul 08 2015Iris recognition has drawn a lot of attention since the mid-twentieth century. Among all biometric features, iris is known to possess a rich set of features. Different features have been used to perform iris recognition in the past. In this paper, two ... More
A Geometric Approach For Fully Automatic Chromosome SegmentationDec 18 2011Sep 01 2014A fundamental task in human chromosome analysis is chromosome segmentation. Segmentation plays an important role in chromosome karyotyping. The first step in segmentation is to remove intrusive objects such as stain debris and other noises. The next step ... More
Deep-Sentiment: Sentiment Analysis Using Ensemble of CNN and Bi-LSTM ModelsApr 08 2019With the popularity of social networks, and e-commerce websites, sentiment analysis has become a more active area of research in the past few years. On a high level, sentiment analysis tries to understand the public opinion about a specific product or ... More
A Robust Regression Approach for Background/Foreground SegmentationDec 16 2014Sep 01 2015Background/foreground segmentation has a lot of applications in image and video processing. In this paper, a segmentation algorithm is proposed which is mainly designed for text and line extraction in screen content. The proposed method makes use of the ... More
Screen Content Image Segmentation Using Sparse-Smooth DecompositionNov 21 2015Sparse decomposition has been extensively used for different applications including signal compression and denoising and document analysis. In this paper, sparse decomposition is used for image segmentation. The proposed algorithm separates the background ... More
Multispectral Palmprint Recognition Using a Hybrid FeatureDec 27 2011Dec 11 2015Personal identification problem has been a major field of research in recent years. Biometrics-based technologies that exploit fingerprints, iris, face, voice and palmprints, have been in the center of attention to solve this problem. Palmprints can be ... More
A Machine Learning Approach For Identifying Patients with Mild Traumatic Brain Injury Using Diffusion MRI ModelingAug 27 2017While diffusion MRI has been extremely promising in the study of MTBI, identifying patients with recent MTBI remains a challenge. The literature is mixed with regard to localizing injury in these patients, however, gray matter such as the thalamus and ... More
A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRIFeb 08 2018Mild traumatic brain injury (mTBI) is a growing public health problem with an estimated incidence of one million people annually in US. Neurocognitive tests have been used to both assess the patient condition and to monitor the patient progress. This ... More
Egocentric Meets Top-viewAug 30 2016Sep 14 2016Thanks to the availability and increasing popularity of Egocentric cameras such as GoPro cameras, glasses, and etc. we have been provided with a plethora of videos captured from the first person perspective. Surveillance cameras and Unmanned Aerial Vehicles(also ... More
Single Stage DOA-Frequency Representation of the Array Data with Source Reconstruction CapabilityMay 03 2019In this paper, a new signal processing framework is proposed, in which the array time samples are represented in DOA-frequency domain through a single stage problem. It is shown that concatenated array data is well represented in a $\mathbf{G}$ dictionary ... More
Detecting Hate Speech in Social MediaDec 18 2017Dec 26 2017In this paper we examine methods to detect hate speech in social media, while distinguishing this from general profanity. We aim to establish lexical baselines for this task by applying supervised classification methods using a recently released dataset ... More
Ego2Top: Matching Viewers in Egocentric and Top-view VideosJul 24 2016Aug 13 2016Egocentric cameras are becoming increasingly popular and provide us with large amounts of videos, captured from the first person perspective. At the same time, surveillance cameras and drones offer an abundance of visual information, often captured from ... More
A framework for computing effective boundary conditions at the interface between free fluid and a porous mediumApr 11 2016Nov 08 2016Interfacial boundary conditions determined from empirical or ad-hoc models remain the standard approach to model fluid flows over porous media, even in situations where the topology of the porous medium is known. We propose a non-empirical and accurate ... More
On the strict endoscopic part of modular Siegel threefoldsMay 19 2013In this paper we study the non-holomorphic strict endoscopic parts of inner cohomology spaces of a modular Siegel threefold respect to local systems. First we show that there is a non-zero subspace of the strict endoscopic part such that it is constructed ... More
Challenges in Discriminating Profanity from Hate SpeechMar 14 2018In this study we approach the problem of distinguishing general profanity from hate speech in social media, something which has not been widely considered. Using a new dataset annotated specifically for this task, we employ supervised classification along ... More
A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRIFeb 08 2018Apr 11 2018Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. This work ... More
Interaction between hairy surfaces and turbulence for different surface time scalesJun 25 2018Nov 16 2018Surfaces with filamentous structures are ubiquitous in nature on many different scales, ranging from forests to micrometer-sized cilia in organs. Hairy surfaces are elastic and porous, and it is not fully understood how they modify turbulence near a wall. ... More
A framework for computing effective boundary conditions at the interface between free fluid and a porous mediumApr 11 2016Jun 28 2016Interfacial boundary conditions determined from empirical or ad-hoc models remain the standard approach to model fluid flows over porous media, even in situations where the topology of the porous medium is known. We propose a non-empirical and accurate ... More
Robust One-Class Kernel Spectral RegressionFeb 06 2019The kernel null-space technique and its regression-based formulation (called one-class kernel spectral regression, a.k.a. OC-KSR) is known to be an effective and computationally attractive one-class classification framework. Despite its outstanding performance, ... More
Client-Specific Anomaly Detection for Face Presentation Attack DetectionJul 02 2018The one-class anomaly detection approach has previously been found to be effective in face presentation attack detection, especially in an \textit{unseen} attack scenario, where the system is exposed to novel types of attacks. This work follows the same ... More
Multi-Task Kernel Null-Space for One-Class ClassificationMay 22 2019The one-class kernel spectral regression (OC-KSR), the regression-based formulation of the kernel null-space approach has been found to be an effective Fisher criterion-based methodology for one-class classification (OCC), achieving state-of-the-art performance ... More
One-Class Kernel Spectral RegressionJul 03 2018Feb 10 2019The paper introduces a new efficient nonlinear one-class classifier formulated as the Rayleigh quotient criterion optimisation. The method, operating in a reproducing kernel Hilbert space, minimises the scatter of target distribution along an optimal ... More
A stable fluid-structure-interaction solver for low-density rigid bodies using the immersed boundary projection methodOct 16 2015Nov 05 2015Dispersion of low-density rigid particles with complex geometries is ubiquitous in both natural and industrial environments. We show that while explicit methods for coupling the incompressible Navier-Stokes equations and Newton's equations of motion are ... More
EgoTransfer: Transferring Motion Across Egocentric and Exocentric Domains using Deep Neural NetworksDec 17 2016Mirror neurons have been observed in the primary motor cortex of primate species, in particular in humans and monkeys. A mirror neuron fires when a person performs a certain action, and also when he observes the same action being performed by another ... More
Edge state modulation by mean viscosity gradientsDec 14 2017Motivated by the relevance of edge state solutions as mediators of transition, we use direct numerical simulations to study the effect of spatially non-uniform viscosity on their energy and stability in minimal channel flows. What we seek is a theoretical ... More
A Portuguese Native Language Identification DatasetApr 30 2018In this paper we present NLI-PT, the first Portuguese dataset compiled for Native Language Identification (NLI), the task of identifying an author's first language based on their second language writing. The dataset includes 1,868 student essays written ... More
Construction of Solenoidal Immersed Velocity Vectors Using the Kinematic Velocity--Vorticity RelationApr 09 2012The present paper suggests a method for obtaining incompressible solenoidal velocity vectors that satisfy approximately the desired immersed velocity boundary conditions. The method employs merely the mutual kinematic relations between the velocity and ... More
SRCLock: SAT-Resistant Cyclic Logic Locking for Protecting the HardwareApr 24 2018In this paper, we claim that cyclic obfuscation, when properly implemented, poses exponential complexity on SAT or CycSAT attack. The CycSAT, in order to generate the necessary cycle avoidance clauses, uses a pre-processing step. We show that this pre-processing ... More
Modeling Language Change in Historical Corpora: The Case of PortugueseSep 30 2016This paper presents a number of experiments to model changes in a historical Portuguese corpus composed of literary texts for the purpose of temporal text classification. Algorithms were trained to classify texts with respect to their publication date ... More
A computational continuum model of poroelastic bedsJan 13 2017Despite the ubiquity of fluid flows interacting with porous and elastic materials, we lack a validated non-empirical macroscale method for characterizing the flow over and through a poroelastic medium. We propose a computational tool to describe such ... More
Transfer of mass and momentum at rough and porous surfacesDec 21 2018The surface texture of materials plays a critical role in wettability, lubrication, turbulence and transport phenomena. In order to design surfaces for these fluid applications, it is desirable to characterise non-smooth and porous materials by their ... More
EgoReID: Cross-view Self-Identification and Human Re-identification in Egocentric and Surveillance VideosDec 24 2016Human identification remains to be one of the challenging tasks in computer vision community due to drastic changes in visual features across different viewpoints, lighting conditions, occlusion, etc. Most of the literature has been focused on exploring ... More
UTFPR at SemEval-2019 Task 5: Hate Speech Identification with Recurrent Neural NetworksApr 16 2019In this paper we revisit the problem of automatically identifying hate speech in posts from social media. We approach the task using a system based on minimalistic compositional Recurrent Neural Networks (RNN). We tested our approach on the SemEval-2019 ... More
Classifying Patent Applications with Ensemble MethodsNov 12 2018We present methods for the automatic classification of patent applications using an annotated dataset provided by the organizers of the ALTA 2018 shared task - Classifying Patent Applications. The goal of the task is to use computational methods to categorize ... More
On a generalization of McCoy RingsOct 13 2014We introduce Central McCoy rings, which are a generalization of McCoy rings and investigate their properties. For a ring R, we prove that R is right Central McCoy if and only if the polynomial ring R[x] is right Central McCoy. Also, we give some examples ... More
Complex Word Identification: Challenges in Data Annotation and System PerformanceOct 13 2017This paper revisits the problem of complex word identification (CWI) following up the SemEval CWI shared task. We use ensemble classifiers to investigate how well computational methods can discriminate between complex and non-complex words. Furthermore, ... More
Passive control of a falling sphere by elliptic-shaped appendagesOct 12 2016Jan 26 2017The majority of investigations characterizing the motion of single or multiple particles in fluid flows consider canonical body shapes, such as spheres, cylinders, discs, etc. However, protrusions on bodies -- being either as surface imperfections or ... More
On A Generalization of Weak Armendariz RingsOct 06 2014We introduce the notion of J-Armendariz rings, which are a generalization of weak Armendariz rings and investigate their properties. We show that any local ring is J-Armendariz, and then fined a local ring that is not weak Armendariz.
From Third Person to First Person: Dataset and Baselines for Synthesis and RetrievalDec 01 2018First-person (egocentric) and third person (exocentric) videos are drastically different in nature. The relationship between these two views have been studied in recent years, however, it has yet to be fully explored. In this work, we introduce two datasets ... More
Near-Optimal Edge Evaluation in Explicit Generalized Binomial GraphsJun 28 2017Robotic motion-planning problems, such as a UAV flying fast in a partially-known environment or a robot arm moving around cluttered objects, require finding collision-free paths quickly. Typically, this is solved by constructing a graph, where vertices ... More
Passive control of a falling sphere by elliptic-shaped appendagesOct 12 2016The majority of investigations characterizing the motion of single or multiple particles in fluid flows consider canonical body shapes, such as spheres, cylinders, discs, etc. However, protrusions on bodies -- being either as surface imperfections or ... More
Discriminating Similar Languages: Evaluations and ExplorationsSep 30 2016We present an analysis of the performance of machine learning classifiers on discriminating between similar languages and language varieties. We carried out a number of experiments using the results of the two editions of the Discriminating between Similar ... More
Passive control of a falling sphere by elliptic-shaped appendagesOct 12 2016Oct 21 2016The majority of investigations characterizing the motion of single or multiple particles in fluid flows consider canonical body shapes, such as spheres, cylinders, discs, etc. However, protrusions on bodies -- being either as surface imperfections or ... More
Automatic Method for Identifying Photospheric Bright Points and Granules Observed by SunriseJul 09 2014In this study, we propose methods for the automatic detection of photospheric features (bright points and granules) from ultra-violet (UV) radiation, using a feature-based classifier. The methods use quiet-Sun observations at 214 nm and 525 nm images ... More
Transfer of mass and momentum at rough and porous surfacesDec 21 2018May 31 2019The surface texture of materials plays a critical role in wettability, turbulence and transport phenomena. In order to design surfaces for these applications, it is desirable to characterise non-smooth and porous materials by their ability to exchange ... More
On a generalization of NC-McCoy RingsOct 12 2014In the present paper we concentrate on a natural generalization of NC-McCoy rings that is called J-McCoy and investigate their properties. We prove that local rings are J-McCoy. Also, for an abelian ring R, we show that R is J-McCoy if and only if eR ... More
On Central Skew Armendariz ringsSep 29 2014For a ring endomirphism, we introduce the central skew Armendariz rings, which are a generalization of skew Armendariz rings and central Armendariz rings, and investigate their properties.
Including Dialects and Language Varieties in Author ProfilingJul 03 2017This paper presents a computational approach to author profiling taking gender and language variety into account. We apply an ensemble system with the output of multiple linear SVM classifiers trained on character and word $n$-grams. We evaluate the system ... More
Shared Autonomy via Hindsight OptimizationMar 26 2015Apr 17 2015In shared autonomy, user input and robot autonomy are combined to control a robot to achieve a goal. Often, the robot does not know a priori which goal the user wants to achieve, and must both predict the user's intended goal, and assist in achieving ... More
An Immersed Boundary Fourier Pseudo-spectral Method for Simulation of Confined Two-dimensional Incompressible FlowsOct 27 2011The present paper is devoted to implementation of the immersed boundary technique into the Fourier pseudo-spectral solution of the vorticity-velocity formulation of the two-dimensional incompressible Navier--Stokes equations. The immersed boundary conditions ... More
Experimental study of a three dimensional cylinder-filament systemJun 02 2015This experimental study reports on the behavior of a filament attached to the rear of a three- dimensional cylinder. The axis of the cylinder is placed normal to a uniform incoming flow and the filament is free to move in the cylinder wake. The mean position ... More
Improving the Sphere-Packing Bound for Binary Codes over Memoryless Symmetric ChannelsJul 26 2010A lower bound on the minimum required code length of binary codes is obtained. The bound is obtained based on observing a close relation between the Ulam's liar game and channel coding. In fact, Spencer's optimal solution to the game is used to derive ... More
German Dialect Identification Using Classifier EnsemblesJul 22 2018In this paper we present the GDI_classification entry to the second German Dialect Identification (GDI) shared task organized within the scope of the VarDial Evaluation Campaign 2018. We present a system based on SVM classifier ensembles trained on characters ... More
Classifier Ensembles for Dialect and Language Variety IdentificationAug 14 2018In this paper we present ensemble-based systems for dialect and language variety identification using the datasets made available by the organizers of the VarDial Evaluation Campaign 2018. We present a system developed to discriminate between Flemish ... More
Predicting the Type and Target of Offensive Posts in Social MediaFeb 25 2019As offensive content has become pervasive in social media, there has been much research on identifying potentially offensive messages. Previous work in this area, however, did not consider the problem as a whole, but rather focused on detecting very specific ... More
SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)Mar 19 2019This paper presents the results and main findings of the shared task on Identifying and Categorizing Offensive Language in Social Media (OffensEval). SemEval-2019 Task 6 provided participants with an annotated dataset containing English tweets. The competition ... More
Stability of a jet in crossflowOct 19 2010We have produced a fluid dynamics video with data from Direct Numerical Simulation (DNS) of a jet in crossflow at several low values of the velocity inflow ratio R. We show that, as the velocity ratio R increases, the flow evolves from simple periodic ... More
Predicting the Type and Target of Offensive Posts in Social MediaFeb 25 2019Apr 16 2019As offensive content has become pervasive in social media, there has been much research in identifying potentially offensive messages. However, previous work on this topic did not consider the problem as a whole, but rather focused on detecting very specific ... More
FaceBots: Steps Towards Enhanced Long-Term Human-Robot Interaction by Utilizing and Publishing Online Social InformationApr 30 2009Our project aims at supporting the creation of sustainable and meaningful longer-term human-robot relationships through the creation of embodied robots with face recognition and natural language dialogue capabilities, which exploit and publish social ... More
Near Optimal Bayesian Active Learning for Decision MakingFeb 24 2014How should we gather information to make effective decisions? We address Bayesian active learning and experimental design problems, where we sequentially select tests to reduce uncertainty about a set of hypotheses. Instead of minimizing uncertainty per ... More
Toward a language-theoretic foundation for planning and filteringJul 23 2018We address problems underlying the algorithmic question of automating the co-design of robot hardware in tandem with its apposite software. Specifically, we consider the impact that degradations of a robot's sensor and actuation suites may have on the ... More
Benchmarking the Capabilities and Limitations of SAT Solvers in Defeating Obfuscation SchemesApr 30 2018In this paper, we investigate the strength of six different SAT solvers in attacking various obfuscation schemes. Our investigation revealed that Glucose and Lingeling SAT solvers are generally suited for attacking small-to-midsize obfuscated circuits, ... More
Simultaneous Reduction of Dynamic and Static Power in Scan StructuresOct 25 2007Power dissipation during test is a major challenge in testing integrated circuits. Dynamic power has been the dominant part of power dissipation in CMOS circuits, however, in future technologies the static portion of power dissipation will outreach the ... More
Discriminating between Indo-Aryan Languages Using SVM EnsemblesJul 09 2018In this paper we present a system based on SVM ensembles trained on characters and words to discriminate between five similar languages of the Indo-Aryan family: Hindi, Braj Bhasha, Awadhi, Bhojpuri, and Magahi. We investigate the performance of individual ... More
Exploring the Use of Text Classification in the Legal DomainOct 25 2017In this paper, we investigate the application of text classification methods to support law professionals. We present several experiments applying machine learning techniques to predict with high accuracy the ruling of the French Supreme Court and the ... More
Efficient Touch Based Localization through SubmodularityAug 30 2012Apr 23 2013Many robotic systems deal with uncertainty by performing a sequence of information gathering actions. In this work, we focus on the problem of efficiently constructing such a sequence by drawing an explicit connection to submodularity. Ideally, we would ... More
SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)Mar 19 2019Apr 27 2019We present the results and the main findings of SemEval-2019 Task 6 on Identifying and Categorizing Offensive Language in Social Media (OffensEval). The task was based on a new dataset, the Offensive Language Identification Dataset (OLID), which contains ... More
A Report on the Complex Word Identification Shared Task 2018Apr 24 2018We report the findings of the second Complex Word Identification (CWI) shared task organized as part of the BEA workshop co-located with NAACL-HLT'2018. The second CWI shared task featured multilingual and multi-genre datasets divided into four tracks: ... More
Autonomy Infused Teleoperation with Application to BCI ManipulationMar 18 2015Jun 07 2015Robot teleoperation systems face a common set of challenges including latency, low-dimensional user commands, and asymmetric control inputs. User control with Brain-Computer Interfaces (BCIs) exacerbates these problems through especially noisy and erratic ... More
Using Distance Estimation and Deep Learning to Simplify Calibration in Food Calorie MeasurementFeb 11 2015Mar 23 2015High calorie intake in the human body on the one hand, has proved harmful in numerous occasions leading to several diseases and on the other hand, a standard amount of calorie intake has been deemed essential by dieticians to maintain the right balance ... More
Modal Analysis of Fluid Flows: Applications and OutlookMar 13 2019The present paper focused on presenting applications of modal analysis techniques to study, model, and control canonical aerodynamic flows. To illustrate how modal analysis techniques can provide physical insights in a complementary manner, we selected ... More