检索结果-内蒙古大学图书馆

24th International Conference on human-computer interaction, HCII 2022

作者： Palacios, Antonio Av. Universitaria 1801 San Miguel Lima15088 Peru Prolongación Primavera 2390 Surco Lima15023 Peru

ISBN: (纸本)9783031064166

Brutalist websites are a contemporary trend that uses anti-aesthetic interface elements to create a high-impact visual product. Since the web is a communications product, this research sought to understand if the aesthetics of Brutalist sites overshadow their usability, defined as the ability of a user to effortlessly navigate through the contents of a digital interface to achieve a goal or retrieve information. Triangulation was applied to obtain a solid understanding of the problem. Consequently, three experiments were conducted on a Brutalist website using a group of thirty-one participants. First, Nielsen’s Attributes of Usability Questionnaire (NAU), a test that focuses on five key aspects of usability: learning, efficiency, memorisation, errors, and satisfaction. Second, Brooke’s System Usability Scale (SUS) test to gain deeper insight into the users’ perspective. Third, the Thinking Aloud (TA) protocol to obtain qualitative information to complement the first two experiments. After analysing the data of the NAU and SUS experiments, a numeric score was given to the perused website to objectively evaluate its usability and assign it to five categories, ranging from Deficient (E) to Excellent (A). Those results were complemented by the TA protocol. The findings highlight difficulties to retrieve information, navigation issues, and a lack of orientation. The use of an unconventional graphical user interface impacts the user experience. This study demonstrates that heuristics are necessary to develop robust interfaces and that deviating from these norms is detrimental to the user experience. The visual features of Brutalist websites, though striking, do not deliver a user-centred project. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Pareidolia in the Machine: Unintended Figuration in AI-Generated Video from Abstract visual Music 25

Pareidolia in the Machine: Unintended Figuration in AI-Gener...

引用

Proceedings of the 2025 Conference on Creativity and Cognition

作者： Sean Zhai Rebecca Ruige Xu School of Design Syracuse University Syracuse New York USA College of Visual & Performing Arts Syracuse University Syracuse New York USA

ISBN: (纸本)9798400712890

This pictorial explores the interplay between algorithmic abstraction and AI-driven figuration in generative visual art. Using an AI video synthesis model, the authors transformed abstract visual music frames—created with the Processing programming language—into dynamic video sequences, aiming to preserve their non-representational aesthetic. However, the AI often reinterpreted geometric and fluid forms as representational entities, such as human figures, birds, and insects, despite the absence of such subjects in the source material. This phenomenon reveals two key dynamics: technical bias, in which AI, trained on representational datasets, prioritizes figuration and mirrors human pareidolia; and creative negotiation, where the artist's abstract intent is continually reinterpreted, raising questions about authorship and the boundaries of procedural art. This study prompts deeper inquiry into whether natural language is inherently sufficient to evoke abstract aesthetics—a fundamental question that merits further exploration.

关键词： Computational creativity

来源：评论

学校读者我要写书评

暂无评论

Theories and Principles Matter: Towards visually Appealing and Effective Abstraction of Property Graph Queries

引用

Proceedings of the ACM on Management of Data 2023年第2期1卷 1-26页

作者： Jiebing Ma Sourav S Bhowmick Byron Choi Lester Tay Nanyang Technological University Singapore Singapore Hong Kong Baptist University Hong Kong Hong Kong

Existing visual abstraction of a property graph query by representing it as a labeled atomic graph (LAG) has great potential to democratize the usage of property graph databases as it enables user-friendly visual query formulation without demanding the need to learn a property graph query language e.g., Cypher. Unfortunately, existing LAG-based query interfaces do not embrace HCI principles and psychology theories to inform their design and as a result may have adverse impact on their usability and aesthetics. In this paper, we depart from the classical theory- and principles-oblivious LAG abstraction to present a novel theory-informed visual abstraction called labeled composite graph (LCG) to address this limitation. It realizes a novel and extensible visual shape definition language called VEDA to create and maintain an LCG systematically, guided by a variety of theories and principles from HCI, visualization and psychology. We build a novel LCG-based visual property graph query interface for Cypher called SIERRA and demonstrate through a user study its superiority to an industrial-strength LAG-based query interface for property graphs w.r.t. usability, aesthetics and efficient query formulation.

关键词： counterfactual thinking human-computer interaction principles property graph queries psychology theories visual abstraction visualization

来源：评论

学校读者我要写书评

暂无评论

Designing a Mobile App with Patients with Discordant Chronic Comorbidities (DCCs): a Usability study 22

Designing a Mobile App with Patients with Discordant Chronic...

引用

12th Nordic Conference on human-computer interaction: Participative Computing for Sustainable Futures, NordiCHI 2022

作者： Li, Tianshuo Haynes, Mason Juhring, Josephine Rucker, Bradley Prabhakar, Ashwin Ongwere, Tom University of Dayton United States Computer Science University of Dayton United States University of Washington United States

ISBN: (纸本)9781450396998

Patients with complex conditions and treatment plans often find it challenging to prioritize various management tasks. The challenge is even greater for patients with discordant chronic comorbidities (DCCs). DCCs occur when a patient has conditions that have unrelated and/or conflicting treatment plans. In our prior work, we explored patients' perspectives and providers' perspectives on DCCs care and proposed a conceptual care model. The model suggested tools to support patients with DCCs in every stage of management. We used these findings to guide a design of a mobile application (App). We then conducted a usability study with 12 DCCs patients to understand how they might use this App to navigate through their complex needs. The participants provided insightful comments regarding: i) visual aesthetics user interfaces, ii) prioritization and goal setting, iii) and user experience. We incorporated these suggestions when re-designing our App and suggestion future design directions. © 2022 ACM.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Cross-Media Colour Correction Framework with Integrated Emotional Perception

SSRN

引用

SSRN 2025年

作者： Qian, Yi Xue, Wenlinag Donghua University China

This study introduces an intelligent cross-media colour correction framework that integrates colour perception, emotional response, and machine learning to enhance colour accuracy and emotional consistency in digital environments. Traditional colour correction methods primarily focus on physical colour differences, often neglecting variations in human perception, affective responses, and user experience, which are crucial for interactive digital applications. To address this limitation, we incorporate three key emotional colour dimensions—"warm/cool", "heavy/light" and "active/passive"—into the correction process. By leveraging Random Forest, XGBoost, and Multi-Layer Perceptron models, we develop an adaptive evaluation metric (S) that simultaneously optimises colour accuracy and emotional coherence. The framework consists of four core modules: colour perception modelling, emotional deviation assessment, AI-driven correction, and personalised user interaction, enabling context-aware and user-adaptive colour adjustments. Experimental results demonstrate that our approach effectively reduces emotional reversals, enhances colour emotion alignment, and improves overall user-perceived accuracy. By bridging computational colour science, affective computing, and human-computer interaction, this study provides a novel AI-driven solution for intelligent colour management. The findings have potential applications in e-commerce, digital content creation, interactive design, and personalised visual systems, advancing research in human-centred AI and adaptive digital aesthetics. © 2025, The Authors. All rights reserved.

关键词： Color computer graphics

来源：评论

学校读者我要写书评

暂无评论

Automated UI Interface Generation via Diffusion Models: Enhancing Personalization and Efficiency

Automated UI Interface Generation via Diffusion Models: Enha...

引用

computer Applications and Information Technology (ISCAIT), International Symposium on

作者： Yifei Duan Liuqingqing Yang Tong Zhang Zhijun Song Fenghua Shao University of Pennsylvania Philadelphia USA University of Michigan Ann Arbor USA Loughborough University Loughborough United Kingdom Parsons school of Design New york USA Independent Researcher Toronto Canada

ISBN: (数字)9798331542856

ISBN: (纸本)9798331542863

This study proposes a UI interface generation method based on a diffusion model, aiming to achieve high-quality, diversified, and personalized interface design through generative artificial intelligence technology. The diffusion model is based on its step-by-step denoising generation process. By combining the conditional generation mechanism, design optimization module, and user feedback mechanism, the model can generate a UI interface that meets the requirements based on multimodal inputs such as text descriptions and sketches provided by users. In the study, a complete experimental evaluation framework was designed, and mainstream generation models (such as GAN, VAE, DALL·E, etc.) were selected for comparative experiments. The generation results were quantitatively analyzed from indicators such as PSNR, SSIM, and FID. The results show that the model proposed in this study is superior to other models in terms of generation quality and user satisfaction, especially in terms of logical clarity of information transmission and visual aesthetics. The ablation experiment further verifies the key role of conditional generation and design optimization modules in improving interface quality. This study provides a new technical path for UI design automation and lays the foundation for the intelligent and personalized development of human-computer interaction interfaces. In the future, the application potential of the model in virtual reality, game design, and other fields will be further explored.

关键词： human computer interaction Solid modeling Adaptation models visualization Design automation Virtual reality Games Diffusion models Optimization Design optimization

来源：评论

学校读者我要写书评

暂无评论

Dynamic User Interface Generation for Enhanced human-computer interaction Using Variational Autoencoders

Dynamic User Interface Generation for Enhanced Human-Compute...

引用

Communication Technology and Information Technology (ICCTIT), International Conference on

作者： Runsheng Zhang Shixiao Wang Tianfang Xie Shiyu Duan Mengmeng Chen University of Southern California Los Angeles USA School of Visual Arts New York USA Georgia Institute of Technology Atlanta USA Carnegie Mellon University Pittsburgh USA New York University New York USA

ISBN: (数字)9798331528973

ISBN: (纸本)9798331528980

This study presents a novel approach for intelligent user interaction interface generation and optimization, grounded in the variational autoencoder (VAE) model. With the rapid advancement of intelligent technologies, traditional interface design methods struggle to meet the evolving demands for diversity and personalization, often lacking flexibility in real-time adjustments to enhance user experience. human-computer interaction (HCI) plays a critical role in addressing these challenges, as it focuses on creating interfaces that are not only functional but also intuitive and responsive to user needs. This research leverages the RICO dataset to train the VAE model, enabling the simulation and creation of user interfaces that align with user aesthetics and interaction habits. Through the integration of real-time user behavior data, the system dynamically refines and optimizes the interface to improve usability, thereby underscoring the importance of HCI in achieving a seamless user experience. The experimental findings indicate that the VAE-based approach significantly enhances the quality and precision of interface generation compared to other methods, including autoencoders (AE), generative adversarial networks (GAN), conditional generative adversarial networks (cGAN), deep belief networks (DBN), and variational autoencoder generative adversarial networks (VAE-GAN). This work contributes valuable insights into human-computer interaction (HCI), providing robust technical solutions for automated interface generation and enhanced user experience optimization.

关键词： human computer interaction Adaptation models Autoencoders User centered design Generative adversarial networks Real-time systems User experience Natural language processing Usability Optimization

来源：评论

学校读者我要写书评

暂无评论

Designing for interaction: Determining the Most Influential Aesthetic Factors for Effective visualisation of Uncertainty

Designing for Interaction: Determining the Most Influential ...

引用

Thematic area human Interface and the Management of Information, HIMI 2022 Part of the 24th HCI International Conference, HCII 2022

作者： Pinney, Joel Carroll, Fiona Cardiff School of Technologies Cardiff Metropolitan University Llandaff Campus Western Avenue CardiffCF5 2YB United Kingdom

ISBN: (纸本)9783031064234

visualisations offer a variety of novel ways to depict data to a wider range of users. Moreover, they provide the ability to transform raw data into intuitive visual mechanisms for communication. Despite the developments in visualisation techniques, an area of depiction that has struggled to advance is uncertainty. The visualisation of uncertainty offers an additional dimension for the data by presenting confidence and error rates. Whilst nearly all predictive data sets visualised contain uncertainties, there is still little impulse to actively represent uncertainty. A growing area of interest in the visualisation world is the field of aesthetics;the authors ask the question ‘could aesthetics be applied to address the issues surrounding visualising uncertainty’. This paper reports on the design and delivery of a study to evaluate the effectiveness of aesthetics for the depiction of uncertainty. In particular, the evaluation of how to practically determine how we assess the influence of aesthetic dimensions for the presentation of uncertainty. The paper reports on the strategies employed in this study to assess user’s decision around aesthetic designs, whilst determining what aesthetic combinations elicit the most uncertain visual representation. The findings show that certain aesthetic combinations in a line graph visualisation portrayed a higher level of uncertainty than others and that particular combinations triggered affective responses based on how the visualisation influenced/impacted a participant. In detail, how the textured line characteristics can be displayed aesthetically (combined with either emphasis or scale) to encourage optimal user experiences of uncertainty in a diverse participant group. The paper highlights how a user’s decision on which texture was most uncertain can be overturned when presented with varying levels of emphasis and scale. In summary, this paper contributes to a more in-depth understanding of how to design for and evaluate aesthe

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Dynamic User Interface Generation for Enhanced human-computer interaction Using Variational Autoencoders

arXiv

引用

arXiv 2024年

作者： Zhang, Runsheng Wang, Shixiao Xie, Tianfang Duan, Shiyu Chen, Mengmeng University of Southern California Los Angeles United States School of Visual Arts New York United States Georgia Institute of Technology Atlanta United States Carnegie Mellon University Pittsburgh United States New York University New York United States

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A visual Analysis of visual Style Research in Digital Media Arts from the Knowledge Graph Perspective

A Visual Analysis of Visual Style Research in Digital Media ...

引用

Intelligent Design (ICID), International Conference on

作者： Jie Gao Jun Yin Fangyi Chen School of Lifelong Education Nanjing University Nanjing China College of Design Jiangnan University Wuxi China

ISBN: (数字)9798331541491

ISBN: (纸本)9798331541507

This paper systematically reviews the current research status on the visual style of digital media art. It analyzes a selected set of 1604 articles retrieved from the Web of Science core collection database using visualization tools like VOSviewer and CiteSpace. Through knowledge map-based analysis across dimensions such as authors, journal publication volumes, sources, co-occurrence networks of keywords, keyword clustering, and bursts, this study uncovers hotspots, trends, and frontiers in this field, offering insights into future research avenues. Findings indicate four primary categories in studying the visual style of digital media art: science and technology, communication, aesthetics, and the art's historical aspects, marking a shift from generalization to specialization and disciplinary to interdisciplinary diversification. Emerging directions encompass human-computer interaction, artificial intelligence, algorithmic art, and NFT art. In summary, this paper contributes to comprehending the current landscape and acts as a compass in scientific literature, providing valuable perspectives for advancing ontology research in digital media art.

关键词： visualization Art Text analysis Reviews Knowledge graphs Media Ontologies Market research Software visual databases

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：