Papers by Manolya Kavakli-Thorne
Proceedings of the 2006 international conference on Game research and development, Dec 4, 2006
The large pose discrepancy is one of the critical<br> challenges in face recognition during... more The large pose discrepancy is one of the critical<br> challenges in face recognition during video surveillance. Due to<br> the entanglement of pose attributes with identity information, the<br> conventional approaches for pose-independent representation lack<br> in providing quality results in recognizing largely posed faces. In<br> this paper, we propose a practical approach to disentangle the pose<br> attribute from the identity information followed by synthesis of a face<br> using a classifier network in latent space. The proposed approach<br> employs a modified generative adversarial network framework<br> consisting of an encoder-decoder structure embedded with a classifier<br> in manifold space for carrying out factorization on the latent<br> encoding. It can be further generalized to other face and non-face<br> attributes for real-life video frames containing faces with significant<br> attribute vari...
2012 45th Hawaii International Conference on System Sciences, 2012
Exam stress is a common predicament faced by students of all age groups and cultures. Unfortunate... more Exam stress is a common predicament faced by students of all age groups and cultures. Unfortunately, it has neither created much consternation in the society nor attracted much interest for serious research, perhaps due to its impulsive causal nature that disappears almost instantly after the exams are over. Stress in optimal level can stimulate students to achieve their personal best in their exams. However, one of the greatest threats to the well-being of students arises due to the fallout of excessive stress; which, if not addressed timely may not only lead to failure in exams, but result in serious debilitating consequences including insomnia, depression and even suicide. Our research aims to design a human computer interaction (HCI) interface using artificial intelligence (AI) techniques for modeling a virtual exam-stress counsellor ESCAP, an embodied conversational agent with facial animation, advice and intelligence of a professional psychologist to support undergraduate students in managing their exam stress.
CiteSeerX - Document Details (Isaac Councill, Lee Giles): The goal of this paper is to present a ... more CiteSeerX - Document Details (Isaac Councill, Lee Giles): The goal of this paper is to present a cognitive modelling approach to capturing the context of complex behaviour in gameplay. This cognitive model can be used for the implementation of goal-directed agents in computer ...
Abstract- This paper investigates the impacts of culture in gesture-based interface design. The a... more Abstract- This paper investigates the impacts of culture in gesture-based interface design. The aim is to identify basic cultural differences in using hand gestures between two cultures: Anglo-Celtics and Latin Americans. We videotaped and analyzed 10 participants in two groups, while describing two chairs by using their speech and hand gestures. We investigated the frequency, occurrence, and the type of gestures used by the two cultures, as well as the words most frequently used by the participants. Our findings state that there are cultural differences in hand gestures during the description of the objects. This may have implications for the development of gesture-based multimodal interfaces. Anglo-Celtics coming from a low context culture, describe objects using a larger number of gestures as well as a larger vocabulary in a longer period. On the other hand, Latin Americans coming from a high context culture, use smaller number of gestures more frequently in a shorter period. The...
This paper presents an empirical study investigating the gender differences in basic hand gesture... more This paper presents an empirical study investigating the gender differences in basic hand gestures for the design of user-centric and adaptive systems. Our goal is to target personalization of gesturebased interaction, devices and applications, using this feedback. First, we focus on gender differences in the perception of technology as well as the externalization of thoughts using natural hand gestures. We commence with an overview of what type of gestures are used and how they are defined in a gesture recognition system. In the empirical studies, we use both video analysis and surveys as the methodologies. We conducted a survey regarding the perception of Information Technology (IT) with 20 male and 20 female participants. Second, we focus on gender differences in gestures. We conducted an experiment involving 10 male and 10 female Australian adults whose age range between 25 to 30. In the experiment, they describe an object using hand gestures and speech. We analysed the results of both survey and experiments. In this paper, we point out the gender differences in the perception of IT, as well as gesture types, frequency and occurrences. Drawing conclusions from these comparisons, we discuss the potential effects of gender differences in the design of multimodal interfaces.
There is an increasing demand for motion capture and full body gesture recognition due to fast pa... more There is an increasing demand for motion capture and full body gesture recognition due to fast paced ubiquitous computing developments and their requirements for natural input modalities. Analysis and synthesis of human body movements are significant issues in bio-medical applications for rehabilitation and identification purposes as in post-stroke patient rehabilitation and gait recognition studies. This paper presents the development of a robust gesture and posture recognition algorithm based on an emerging research field Compressed Sensing (CS) and Sparse Representation (SR), in signal processing for the wearable sensing garment which consists of a sensor network having piezo-resistive properties. The gesture recognition algorithm presented in this study is highly accurate regardless of the signal acquisition method used and gives excellent results even for high dimensional signals and large gesture dictionaries. Our findings state that gestures can be recognized with over 99% accuracy rate using Sparse Representation-based Classification (SRC) algorithm. We tested the algorithm using 3 different gesture dictionaries acquired in 3 different gesture domains with user dependent and user independent test gesture and dictionaries. The system gives 100% recognition accuracy for the gestures performed by sensing t-shirt with two different gesture sets.
Lecture Notes in Computer Science
To generate a multi-faceted view, from a single image has always been a challenging problem for d... more To generate a multi-faceted view, from a single image has always been a challenging problem for decades. Recent developments in technology enable us to tackle this problem effectively. Previously, Several Generative Adversarial Network (GAN) based models have been used to deal with this problem as linear GAN, linear framework, a generator (generally encoder-decoder), followed by the discriminator. Such structures helped to some extent, but are not powerful enough to tackle this problem effectively.
Advances in life sciences, 2015
This paper reviews gender differences in gestural communication and perception of Information Tec... more This paper reviews gender differences in gestural communication and perception of Information Technology (IT) and investigates gender differences in basic hand gestures for the design of user-centric and gender-adaptive systems. If males and females associate themselves differently with technology, being masculine and feminine, then this would have a strong impact on their adoption of IT and would require the development of gender-adaptive gesturerecognition systems, devices and applications. In this paper, we present empirical studies to demonstrate gender differences in the perception of technology as well as gestural communication. We have conducted a survey with 20 male and 20 female participants and found differences in the perception of the gender of technology. Our association with IT may be driven by the way we identify ourselves with the gender of technology. If there are differences in the way we process information and males and females use different system architectures,...
Advances in life sciences, 2012
This paper investigates the impacts of culture in gesture-based interface design. The aim is to i... more This paper investigates the impacts of culture in gesture-based interface design. The aim is to identify basic cultural differences in using hand gestures between two cultures: Anglo-Celtics and Latin Americans. We videotaped and analyzed 10 participants in two groups, while describing two chairs by using their speech and hand gestures. We investigated the frequency, occurrence, and the type of gestures used by the two cultures, as well as the words most frequently used by the participants. Our findings state that there are cultural differences in hand gestures during the description of the objects. This may have implications for the development of gesture-based multimodal interfaces. AngloCeltics coming from a low context culture, describe objects using a larger number of gestures as well as a larger vocabulary in a longer period. On the other hand, Latin Americans coming from a high context culture, use smaller number of gestures more frequently in a shorter period. The difference...
HCI for Cybersecurity, Privacy and Trust
Human behavior is considered to be the weakest link in the field of cybersecurity. Despite the de... more Human behavior is considered to be the weakest link in the field of cybersecurity. Despite the development of a wide range of Augmented Reality (AR) applications in various domains, no AR application is available to educate users and increase their awareness of cybersecurity issues. Thus, we developed a game based on AR techniques as an Android app called CybAR. Since there have been few acceptance studies in the field of AR, it was particularly important to identify the factors that affect user acceptance of AR technology. This paper aims to identify whether gamification features influence users’ acceptance of the CybAR app and increase their cybersecurity awareness. The predictors of CybAR app usage were derived from the extended unified theory of acceptance and usage of technology (UTAUT2) with the addition of the gamification factor. In this paper, we present the preliminary results of a study addressing the impact of gamification features on acceptance of the CybAR game. The theoretical model was tested in a quantitative study using structural equation modelling, conducted in Australia, with 95 Macquarie University students. The findings indicate that there is a significant relationship between gamification factors and behavioural intention to use the CybAR app and actual use of the CybAR app.
ArXiv, 2019
Person re-identification is a basic subject in the field of computer vision. The traditional meth... more Person re-identification is a basic subject in the field of computer vision. The traditional methods have several limitations in solving the problems of person illumination like occlusion, pose variation and feature variation under complex background. Fortunately, deep learning paradigm opens new ways of the person re-identification research and becomes a hot spot in this field. Generative Adversarial Nets (GANs) in the past few years attracted lots of attention in solving these problems. This paper reviews the GAN based methods for person re-identification focuses on the related papers about different GAN based frameworks and discusses their advantages and disadvantages. Finally, it proposes the direction of future research, especially the prospect of person re-identification methods based on GANs.
Proceedings of the 2020 4th International Conference on Virtual and Augmented Reality Simulations, 2020
Human behavior is considered to be the weakest link in the field of cybersecurity. Despite the de... more Human behavior is considered to be the weakest link in the field of cybersecurity. Despite the development of a wide range of Augmented Reality (AR) applications in various domains, no AR application is available to educate users and increase their awareness of cybersecurity issues. Thus, we developed a game based on AR techniques as an Android app called CybAR. Since there have been few acceptance studies in the field of AR, it was particularly important to identify the factors that affect user acceptance of AR technology. Technology acceptance studies typically predict behavioral adoption by investigating the relationship between attitudes and intentions, even though intention may not be the best predictor of actual behavior. Personality constructs and dimensions of cultural difference have recently been found to explain even more variance in behavior and provide insights into user behavior. The objective of this study is to identify the personality traits that affect users' a...
ArXiv, 2020
Naturally, humans use multiple modalities to convey information. The modalities are processed bot... more Naturally, humans use multiple modalities to convey information. The modalities are processed both sequentially and in parallel for communication in the human brain, this changes when humans interact with computers. Empowering computers with the capability to process input multimodally is a major domain of investigation in Human-Computer Interaction (HCI). The advancement in technology (powerful mobile devices, advanced sensors, new ways of output, etc.) has opened up new gateways for researchers to design systems that allow multimodal interaction. It is a matter of time when the multimodal inputs will overtake the traditional ways of interactions. The paper provides an introduction to the domain of multimodal systems, explains a brief history, describes advantages of multimodal systems over unimodal systems, and discusses various modalities. The input modeling, fusion, and data collection were discussed. Finally, the challenges in the multimodal systems research were listed. The an...
Many Advisor Systems have been designed and developed to assist us in decision-making, each with ... more Many Advisor Systems have been designed and developed to assist us in decision-making, each with their strengths and weaknesses. A popular type of Advisor systems is Travel Advisor systems that assist travelers in their travel arrangements. We have designed and implemented a Travel Advisor system to assist travelers, evaluating a number of factors after analyzing the features of other Travel Advisor systems. These factors are travelers’ budgets, distance, their friends’ interests, individual and group interests, dislikes, transportation mode and travel histories. We demonstrate the validity of the solution using case studies and usability testing results. In this study, our major goal is to measure the system’s usability both with participants who previously travelled to the location and with participants who have never been there to investigate if familiarity correlates with positive rating of the system features. Our findings state that familiarity with the location correlates wit...
Human behavior is considered to be the weakest link in the field of cybersecurity. Despite the de... more Human behavior is considered to be the weakest link in the field of cybersecurity. Despite the development of a wide range of Augmented Reality (AR) applications in various domains, no AR application is available to educate users and increase their awareness of cybersecurity issues. Thus, we developed a game based on AR techniques as an Android app called CybAR. Since there have been few acceptance studies in the field of AR, it was particularly important to identify the factors that affect user acceptance of AR technology. This paper aims to identify whether gamification features influence users’ acceptance of the CybAR app and increase their cybersecurity awareness. The predictors of CybAR app usage were derived from the extended unified theory of acceptance and usage of technology (UTAUT2) with the addition of the gamification factor. In this paper, we present the preliminary results of a study addressing the impact of gamification features on acceptance of the CybAR game. The th...
In multimodal interfaces, hand gestures often help convey meaning to the spoken word; therefore, ... more In multimodal interfaces, hand gestures often help convey meaning to the spoken word; therefore, the cultural background of the gesturing person might be an influential factor in the interaction with these interfaces. This paper presents an empirical study aimed at singling out basic cultural differences in hand gesture performance between two cultures: Anglo-Celtics and Latin Americans. The focus in this paper is given to the video analysis of the two cultures describing two objects with their hands. The purpose is to use gesture segmentation to define predominant hand gestures by culture. Conclusions are drawn from the experiment and are linked to cultural attributes proposed by theorists like Hall and Hofstede. The findings state that cultural differences exist in the description of the object, which might have implications for the development of gesture-based multimodal interfaces. As Anglo-Celtics are low context cultures, they used more words and gestures in longer time. On th...
Uploads
Papers by Manolya Kavakli-Thorne