Catalogue Search | MBRL
هل أنت متأكد أنك تريد إزالة الكتاب من الرف؟
{{itemTitle}}
21,971
نتائج ل
"User Interfaces and Human Computer Interaction"
صنف حسب:
Interactive textures for architecture and landscaping : digital elements and technologies
\"This book addresses the phenomenon called \"interactive architecture that challenges artists, architects, designers, theorists, and geographers to develop a language and designs toward the \"use\" of these environments\"--Provided by publisher.
Book
Attention mechanisms in computer vision: A survey
Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system. Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image. Attention mechanisms have achieved great success in many visual tasks, including image classification, object detection, semantic segmentation, video understanding, image generation, 3D vision, multimodal tasks, and self-supervised learning. In this survey, we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach, such as channel attention, spatial attention, temporal attention, and branch attention; a related repository
https://github.com/MenghaoGuo/Awesome-Vision-Attentions
is dedicated to collecting related work. We also suggest future directions for attention mechanism research.
Journal Article
Visual attention network
While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in computer vision: (1) treating images as 1D sequences neglects their 2D structures; (2) the quadratic complexity is too expensive for high-resolution images; (3) it only captures spatial adaptability but ignores channel adaptability. In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings. Furthermore, we present a neural network based on LKA, namely Visual Attention Network (VAN). While extremely simple, VAN achieves comparable results with similar size convolutional neural networks (CNNs) and vision transformers (ViTs) in various tasks, including image classification, object detection, semantic segmentation, panoptic segmentation, pose estimation, etc. For example, VAN-B6 achieves 87.8% accuracy on ImageNet benchmark, and sets new state-of-the-art performance (58.2 PQ) for panoptic segmentation. Besides, VAN-B2 surpasses Swin-T 4 mIoU (50.1 vs. 46.1) for semantic segmentation on ADE20K benchmark, 2.6 AP (48.8 vs. 46.2) for object detection on COCO dataset. It provides a novel method and a simple yet strong baseline for the community. The code is available at
https://github.com/Visual-Attention-Network
.
Journal Article
Interacting with educational chatbots: A systematic review
Chatbots hold the promise of revolutionizing education by engaging learners, personalizing learning activities, supporting educators, and developing deep insight into learners’ behavior. However, there is a lack of studies that analyze the recent evidence-based chatbot-learner interaction design techniques applied in education. This study presents a systematic review of 36 papers to understand, compare, and reflect on recent attempts to utilize chatbots in education using seven dimensions: educational field, platform, design principles, the role of chatbots, interaction styles, evidence, and limitations. The results show that the chatbots were mainly designed on a web platform to teach computer science, language, general education, and a few other fields such as engineering and mathematics. Further, more than half of the chatbots were used as teaching agents, while more than a third were peer agents. Most of the chatbots used a predetermined conversational path, and more than a quarter utilized a personalized learning approach that catered to students’ learning needs, while other chatbots used experiential and collaborative learning besides other design principles. Moreover, more than a third of the chatbots were evaluated with experiments, and the results primarily point to improved learning and subjective satisfaction. Challenges and limitations include inadequate or insufficient dataset training and a lack of reliance on usability heuristics. Future studies should explore the effect of chatbot personality and localization on subjective satisfaction and learning effectiveness.
Journal Article
Large language models in education: A focus on the complementary relationship between human teachers and ChatGPT
Artificial Intelligence (AI) is developing in a manner that blurs the boundaries between specific areas of application and expands its capability to be used in a wide range of applications. The public release of ChatGPT, a generative AI chatbot powered by a large language model (LLM), represents a significant step forward in this direction. Accordingly, professionals predict that this technology will affect education, including the role of teachers. However, despite some assumptions regarding its influence on education, how teachers may actually use the technology and the nature of its relationship with teachers remain under-investigated. Thus, in this study, the relationship between ChatGPT and teachers was explored with a particular focus on identifying the complementary roles of each in education. Eleven language teachers were asked to use ChatGPT for their instruction during a period of two weeks. They then participated in individual interviews regarding their experiences and provided interaction logs produced during their use of the technology. Through qualitative analysis of the data, four ChatGPT roles (interlocutor, content provider, teaching assistant, and evaluator) and three teacher roles (orchestrating different resources with quality pedagogical decisions, making students active investigators, and raising AI ethical awareness) were identified. Based on the findings, an in-depth discussion of teacher-AI collaboration is presented, highlighting the importance of teachers’ pedagogical expertise when using AI tools. Implications regarding the future use of LLM-powered chatbots in education are also provided.
Journal Article
PVT v2: Improved baselines with Pyramid Vision Transformer
Transformers have recently lead to encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision Transformer (PVT v1) by adding three designs: (i) a linear complexity attention layer, (ii) an overlapping patch embedding, and (iii) a convolutional feed-forward network. With these modifications, PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification, detection, and segmentation. In particular, PVT v2 achieves comparable or better performance than recent work such as the Swin transformer. We hope this work will facilitate state-of-the-art transformer research in computer vision. Code is available at
https://github.com/whai362/PVT
.
Journal Article
Ethical principles for artificial intelligence in education
The advancement of artificial intelligence in education (AIED) has the potential to transform the educational landscape and influence the role of all involved stakeholders. In recent years, the applications of AIED have been gradually adopted to progress our understanding of students’ learning and enhance learning performance and experience. However, the adoption of AIED has led to increasing ethical risks and concerns regarding several aspects such as personal data and learner autonomy. Despite the recent announcement of guidelines for ethical and trustworthy AIED, the debate revolves around the key principles underpinning ethical AIED. This paper aims to explore whether there is a global consensus on ethical AIED by mapping and analyzing international organizations’ current policies and guidelines. In this paper, we first introduce the opportunities offered by AI in education and potential ethical issues. Then, thematic analysis was conducted to conceptualize and establish a set of ethical principles by examining and synthesizing relevant ethical policies and guidelines for AIED. We discuss each principle and associated implications for relevant educational stakeholders, including students, teachers, technology developers, policymakers, and institutional decision-makers. The proposed set of ethical principles is expected to serve as a framework to inform and guide educational stakeholders in the development and deployment of ethical and trustworthy AIED as well as catalyze future development of related impact studies in the field.
Journal Article
The Chatbot Usability Scale: the Design and Pilot of a Usability Scale for Interaction with AI-Based Conversational Agents
Standardised tools to assess a user’s satisfaction with the experience of using chatbots and conversational agents are currently unavailable. This work describes four studies, including a systematic literature review, with an overall sample of 141 participants in the survey (experts and novices), focus group sessions and testing of chatbots to (i) define attributes to assess the quality of interaction with chatbots and (ii) the designing and piloting a new scale to measure satisfaction after the experience with chatbots. Two instruments were developed: (i) A diagnostic tool in the form of a checklist (BOT-Check). This tool is a development of previous works which can be used reliably to check the quality of a chatbots experience in line with commonplace principles. (ii) A 15-item questionnaire (BOT Usability Scale, BUS-15) with estimated reliability between .76 and .87 distributed in five factors. BUS-15 strongly correlates with UMUX-LITE by enabling designers to consider a broader range of aspects usually not considered in satisfaction tools for non-conversational agents, e.g. conversational efficiency and accessibility, quality of the chatbot’s functionality and so on. Despite the convincing psychometric properties, BUS-15 requires further testing and validation. Designers can use it as a tool to assess products, thus building independent databases for future evaluation of its reliability, validity and sensitivity.
Journal Article
Impacts of digital technologies on education and factors influencing schools' digital capacity and transformation: A literature review
Digital technologies have brought changes to the nature and scope of education and led education systems worldwide to adopt strategies and policies for ICT integration. The latter brought about issues regarding the quality of teaching and learning with ICTs, especially concerning the understanding, adaptation, and design of the education systems in accordance with current technological trends. These issues were emphasized during the recent COVID-19 pandemic that accelerated the use of digital technologies in education, generating questions regarding digitalization in schools. Specifically, many schools demonstrated a lack of experience and low digital capacity, which resulted in widening gaps, inequalities, and learning losses. Such results have engendered the need for schools to learn and build upon the experience to enhance their digital capacity and preparedness, increase their digitalization levels, and achieve a successful digital transformation. Given that the integration of digital technologies is a complex and continuous process that impacts different actors within the school ecosystem, there is a need to show how these impacts are interconnected and identify the factors that can encourage an effective and efficient change in the school environments. For this purpose, we conducted a non-systematic literature review. The results of the literature review were organized thematically based on the evidence presented about the impact of digital technology on education and the factors that affect the schools’ digital capacity and digital transformation. The findings suggest that ICT integration in schools impacts more than just students’ performance; it affects several other school-related aspects and stakeholders, too. Furthermore, various factors affect the impact of digital technologies on education. These factors are interconnected and play a vital role in the digital transformation process. The study results shed light on how ICTs can positively contribute to the digital transformation of schools and which factors should be considered for schools to achieve effective and efficient change.
Journal Article
Virtual reality consumer experience escapes: preparing for the metaverse
Virtual Reality (VR) experience escapes allow individuals to spend hours on end in immersive virtual environments and interact with content in a world that is providing shelter and illusion of an alternative reality – the metaverse. Discussions on possible risks have largely remained limited to usability challenges, while only a few studies reflect on social, psychological and physical implications this immersive technology exposes and the considerations consumers and businesses need to take. This paper critically reviews literature on escapism to discuss issues in the design and employment of virtual reality consumer experience escapes. Key issues relating to VR experience escapes and resulting effects on consumer health and well-being are discussed, emphasizing needed consumer-centered research and design. Future considerations include (1) Self-indulgent escapism through VR consumer experiences, (2) Ethical considerations in the design of VR consumer experience escapes, and (3) Purposeful design of VR consumer experiences escapes. A sequential research agenda is presented that integrates antecedents of VR experience escapes that connect to three main future research streams; designing purpose-driven VR consumer experience escapes, complementing methodologies for VR consumer experience research, and meaningful VR consumer experience escapes.
Journal Article