Undergraduate computerscience programs worldwide struggle to attract and retain underrepresented students for many reasons. Culture, stereotype threats, uneven gender and racial representations, lack of role models, ...
详细信息
Isolated dynamic sign language recognition (IDSLR) has the potential to change accessibility and inclusion by enabling speech and/or hearing-impaired people to engage more completely in a variety of spheres of life, i...
详细信息
Isolated dynamic sign language recognition (IDSLR) has the potential to change accessibility and inclusion by enabling speech and/or hearing-impaired people to engage more completely in a variety of spheres of life, including social interactions, work, and more. IDSLR is a challenging task due to considering a sequence of image frame analysis with multiple linguistic features for a single gesture in cluttered backgrounds and an illumination variation environment. We have proposed a Hybrid Efficient Convolution (HEC) model that ensembles EfficientNet-B3 and a few modified layers as an alternative to traditional machine learning techniques with improved performances in cluttered backgrounds with illumination variation environments. The architecture of the HCE integrates pre-trained layers of EfficientNet-B3 loaded with customized weights and a new custom dense layer featuring 256 units, followed by batch normalization, dropout, and the final output layer. To enhance the robustness of the system, we employed the augmentation technique during pre-processing. Then, the system executes channel-wise feature transformation through point-wise convolution that reduces the computational complexity and increases the accuracy. The updated dense layer with 256 units processes the output from the standard EfficientNet-B3, shaping the model into a hybrid form to achieve better performance. We have created our own gesture dataset, called "BdSL_OPA_23_GESTURES," which consists of 6000 video clips of 100 isolated dynamic Bangla Sign Language words, with 60 videos for each word from 20 different people in the cluttered background with illumination variation environments to train and evaluate the performances of the proposed model. We have considered 80% of the total dataset for training purpose, while the remaining 20% is dedicated to testing and validation. In a small number of epochs, our proposed HEC model achieves a superior accuracy of 93.17% on our created "BdSL_OPA_23_GESTURES"
Virtual Reality (VR) allows users to flexibly choose the perspective through which they interact with a synthetic environment. Users can either adopt a first-person perspective, in which they see through the eyes of t...
详细信息
ISBN:
(数字)9798331516475
ISBN:
(纸本)9798331516482
Virtual Reality (VR) allows users to flexibly choose the perspective through which they interact with a synthetic environment. Users can either adopt a first-person perspective, in which they see through the eyes of their virtual avatar, or a third-person perspective, in which their viewpoint is detached from the virtual avatar. Prior research has shown that the visual perspective affects different interactions and influences core experiential factors, such as the user’s sense of embodiment. However, there is limited understanding of how auditory perspective mediates user experience in immersive virtual environments. In this paper, we conducted a controlled experiment $(N=24)$ on the effect of the user’s auditory perspective on their performance in a sound localization task and their sense of embodiment. Our results showed that when viewing a virtual avatar from a third-person visual perspective, adopting the auditory perspective of the avatar may increase agency and self-avatar merging, even when controlling for variations in task difficulty caused by shifts in auditory perspective. Additionally, our findings suggest that differences in auditory perspective generally have a smaller effect than differences in visual perspective. We discuss the implications of our empirical investigation of audio perspective for designing embodied auditory experiences in VR.
Trustworthy Graph Neural Networks (GNNs) for EEG emotion recognition should identify emotions accurately and elucidate corresponding rationales. Current GNNs have achieved notable performance by dynamically modeling e...
详细信息
Augmented Reality(AR) offers the potential for easy and efficient information access, reinforcing the wide belief that AR Glasses are the next-generation of personal computing devices. However, to realize this all-day...
详细信息
ISBN:
(纸本)9781665484039
Augmented Reality(AR) offers the potential for easy and efficient information access, reinforcing the wide belief that AR Glasses are the next-generation of personal computing devices. However, to realize this all-day AR vision, the AR interface must be able to address the challenges that constant and pervasive presence of virtual content can cause for the user. The optimal interface, that is the most efficient yet least intrusive, in one context may be the worst interface for another context. Throughout the day, as the user switches context, an optimal all-day interface must adapts its virtual content display and interactions as well. This work aims to propose a research agenda to design and validate different adaptation techniques and context-aware AR interfaces and introduce a framework for the design of such intelligent interfaces.
Digital health interventions that involve monitoring patient behaviour increasingly benefit from improvements in sensor technology. Eye tracking in particular can provide useful information for psychotherapy but an ef...
详细信息
The application of physiological signals in emotion recognition is a popular research topic in human-computerinteractions. Eye movement, as an important physiological signal, plays an essential role in medicine, psyc...
详细信息
Robot grasping is of paramount importance in industrial and service robotics. In recent years, various data-driven algorithms have been proposed to solve the problem of grasp detection and a part of them are based on ...
Robot grasping is of paramount importance in industrial and service robotics. In recent years, various data-driven algorithms have been proposed to solve the problem of grasp detection and a part of them are based on reinforcement learning (RL) approaches. In a variety of proposed algorithms, random key points are being employed which will make the learning process inefficient and time-consuming. In this paper, a geometry-based algorithm is presented which can find grasp poses based on the geometry of the unknown object and propose the ones which may lead to successful grasping. For the grasp contacts computation part, the presented algorithm produces a finite number of key points based on the 2D shape of the object from a specific point of view. Afterward, it will narrow down the candidate points and output a finite number of successful grasp poses based on three grasp quality metrics for various unknown objects. Three approaches are proposed in order to achieve center points which can describe different parts of a 2D shape. Then, the obtained points are used as the center of circles which are tangent to the 2D shape contour. Also, a new grasp quality metric is proposed. The time of the grasp and the amount of object disorientation after grasping are considered as a metric to evaluate the successfulness of the grasp. Simulation results demonstrate that the proposed algorithm for unknown object grasping can find a finite number of successful grasp poses for different seen or unseen objects without using any random point,
暂无评论