M. Pérez-Ortiz, C. Dormann, Y. Rogers, Sahan Bulathwela, S. Kreitmayer, Emine Yilmaz, R. Noss, J. Shawe-Taylor
X5Learn (available at https://x5learn.org ) is a human-centered AI-powered platform for supporting access to free online educational resources. X5Learn provides users with a number of educational tools for interacting with open educational videos, and a set of tools adapted to suit the pedagogical preferences of users. It is intended to support both teachers and students, alike. For teachers, it provides a powerful platform to reuse, revise, remix, and redistribute open courseware produced by others. These can be videos, pdfs, exercises and other online material. For students, it provides a scaffolded and informative interface to select content to watch, read, make notes and write reviews, as well as a powerful personalised recommendation system that can optimise learning paths and adjust to the user’s learning preferences. What makes X5Learn stand out from other educational platforms, is how it combines human-centered design with AI algorithms and software tools with the goal of making it intuitive and easy to use, as well as making the AI transparent to the user. We present the core search tool of X5Learn, intended to support exploring open educational materials.
{"title":"X5Learn: A Personalised Learning Companion at the Intersection of AI and HCI","authors":"M. Pérez-Ortiz, C. Dormann, Y. Rogers, Sahan Bulathwela, S. Kreitmayer, Emine Yilmaz, R. Noss, J. Shawe-Taylor","doi":"10.1145/3397482.3450721","DOIUrl":"https://doi.org/10.1145/3397482.3450721","url":null,"abstract":"X5Learn (available at https://x5learn.org ) is a human-centered AI-powered platform for supporting access to free online educational resources. X5Learn provides users with a number of educational tools for interacting with open educational videos, and a set of tools adapted to suit the pedagogical preferences of users. It is intended to support both teachers and students, alike. For teachers, it provides a powerful platform to reuse, revise, remix, and redistribute open courseware produced by others. These can be videos, pdfs, exercises and other online material. For students, it provides a scaffolded and informative interface to select content to watch, read, make notes and write reviews, as well as a powerful personalised recommendation system that can optimise learning paths and adjust to the user’s learning preferences. What makes X5Learn stand out from other educational platforms, is how it combines human-centered design with AI algorithms and software tools with the goal of making it intuitive and easy to use, as well as making the AI transparent to the user. We present the core search tool of X5Learn, intended to support exploring open educational materials.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123440049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Glowacka, E. Milios, Axel J. Soto, O. Mokryn, F. Paulovich, Denis Parra
This is the fourth edition of the Workshop on Exploratory Search and Interactive Data Analytics (ESIDA). This series of workshops emerged as a response to the growing interest in developing new methods and systems that allow users to interactively explore large volumes of data, such as documents, multimedia, or specialized collections, such as biomedical datasets. There are various approaches to supporting users in this interactive environment, ranging from developing new algorithms through visualization methods to analyzing users’ search patterns. The overarching goal of ESIDA is to bring together researchers working in areas that span across multiple facets of exploratory search and data analytics to discuss and outline research challenges for this novel area.
{"title":"Fourth Workshop on Exploratory Search and Interactive Data Analytics (ESIDA)","authors":"D. Glowacka, E. Milios, Axel J. Soto, O. Mokryn, F. Paulovich, Denis Parra","doi":"10.1145/3397482.3450711","DOIUrl":"https://doi.org/10.1145/3397482.3450711","url":null,"abstract":"This is the fourth edition of the Workshop on Exploratory Search and Interactive Data Analytics (ESIDA). This series of workshops emerged as a response to the growing interest in developing new methods and systems that allow users to interactively explore large volumes of data, such as documents, multimedia, or specialized collections, such as biomedical datasets. There are various approaches to supporting users in this interactive environment, ranging from developing new algorithms through visualization methods to analyzing users’ search patterns. The overarching goal of ESIDA is to bring together researchers working in areas that span across multiple facets of exploratory search and data analytics to discuss and outline research challenges for this novel area.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"570 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122931377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Email and other forms of electronic communication are becoming increasingly more essential to our everyday lives. However, with this growth comes the paralleled increased risk of email harassment, exacerbated by the current lack of platform support for managing these harmful messages. This paper explores different interfaces for the automated detection and management of email harassment using artificial intelligence in order to investigate what degree of platform intervention email users prefer when navigating their email platform. Through conducting user studies involving three different email platform prototypes based on the Gmail platform, we employ mixed-method analysis to evaluate how varying levels of platform intervention affect users’ perceived sense of safety, agency, and trust with their email platform. Our primary findings suggest that users generally benefited from each of the system intervention strategies and desired higher intervention features when combating email harassment, as well as ways of managing this intervention based on their unique preferences.
{"title":"Evaluating Automated System Interventions Against Email Harassment","authors":"Nina Chen, Cassandra Kane, Elisa Zhao Hang","doi":"10.1145/3397482.3450724","DOIUrl":"https://doi.org/10.1145/3397482.3450724","url":null,"abstract":"Email and other forms of electronic communication are becoming increasingly more essential to our everyday lives. However, with this growth comes the paralleled increased risk of email harassment, exacerbated by the current lack of platform support for managing these harmful messages. This paper explores different interfaces for the automated detection and management of email harassment using artificial intelligence in order to investigate what degree of platform intervention email users prefer when navigating their email platform. Through conducting user studies involving three different email platform prototypes based on the Gmail platform, we employ mixed-method analysis to evaluate how varying levels of platform intervention affect users’ perceived sense of safety, agency, and trust with their email platform. Our primary findings suggest that users generally benefited from each of the system intervention strategies and desired higher intervention features when combating email harassment, as well as ways of managing this intervention based on their unique preferences.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130549730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The motivation and support of a patient in a robot-instructed therapy is not easy, but is made more difficult if another person has to help with the execution of the exercises. This paper highlights a phd research project in which a social robot keeps two people motivated and engaged at the same time, while they carry out collaborative rehabilitative exercises. After describing the opportunity for social robots in these scenarios, we present the research questions, relevant literature, individual steps how such a personalized robot system can be created and work so far.
{"title":"Design of a Patient-Therapist-Social Robot Therapy System in Neurorehabilitation Therapies for Engagement and Motivation","authors":"Alexandru Bundea","doi":"10.1145/3397482.3450712","DOIUrl":"https://doi.org/10.1145/3397482.3450712","url":null,"abstract":"The motivation and support of a patient in a robot-instructed therapy is not easy, but is made more difficult if another person has to help with the execution of the exercises. This paper highlights a phd research project in which a social robot keeps two people motivated and engaged at the same time, while they carry out collaborative rehabilitative exercises. After describing the opportunity for social robots in these scenarios, we present the research questions, relevant literature, individual steps how such a personalized robot system can be created and work so far.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125582398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent years have witnessed the emerging of conversational systems, including both physical devices and mobile-based applications. Both the research community and industry believe that conversational systems will have a major impact on human-computer interaction, and specifically, the CHI/IR/DM/RecSys communities have begun to explore Conversational Recommendation Systems. Conversational recommendation aims at finding or recommending the most relevant information (e.g., web pages, answers, movies, products) for users based on textual- or spoken-dialogs, through which users can communicate with the system more efficiently using natural language conversations. Due to users’ constant need to look for information to support both work and daily life, conversational recommendation system will be one of the key techniques towards an intelligent web. The tutorial focuses on the foundations and algorithms for conversational recommendation, as well as their applications in real-world systems such as search engine, e-commerce and social networks. The tutorial aims at introducing and communicating conversational recommendation methods to the community, as well as gathering researchers and practitioners interested in this research direction for discussions, idea communications, and research promotions.
{"title":"IUI 2021 Tutorial on Conversational Recommendation Systems","authors":"Zuohui Fu, Yikun Xian, Yongfeng Zhang, Yi Zhang","doi":"10.1145/3397482.3450621","DOIUrl":"https://doi.org/10.1145/3397482.3450621","url":null,"abstract":"Recent years have witnessed the emerging of conversational systems, including both physical devices and mobile-based applications. Both the research community and industry believe that conversational systems will have a major impact on human-computer interaction, and specifically, the CHI/IR/DM/RecSys communities have begun to explore Conversational Recommendation Systems. Conversational recommendation aims at finding or recommending the most relevant information (e.g., web pages, answers, movies, products) for users based on textual- or spoken-dialogs, through which users can communicate with the system more efficiently using natural language conversations. Due to users’ constant need to look for information to support both work and daily life, conversational recommendation system will be one of the key techniques towards an intelligent web. The tutorial focuses on the foundations and algorithms for conversational recommendation, as well as their applications in real-world systems such as search engine, e-commerce and social networks. The tutorial aims at introducing and communicating conversational recommendation methods to the community, as well as gathering researchers and practitioners interested in this research direction for discussions, idea communications, and research promotions.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133041927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Philip R. Doyle, D. Rough, Justin Edwards, Benjamin R. Cowan, L. Clark, Martin Porcheron, Stephan Schlögl, M. I. Torres, Cosmin Munteanu, Christine Murad, Jaisie Sin, Minha Lee, M. Aylett, Heloisa Candello
This workshop aims to bring together the Intelligent User Interface (IUI) and Conversational User Interface (CUI) communities to understand the theoretical and methodological challenges in designing, deploying and evaluating CUIs. CUIs have continued to prosper with the increased use and technological developments in both text-based chatbots and speech-based systems. However, challenges remain in creating established theoretical and methodological approaches for CUIs, and how these can be used with recent engineering advances. These include assessing the impact of interface design on user behaviours and perceptions, developing design guidelines, understanding the role of personalisation and issues of ethics and privacy. Our half-day multidisciplinary workshop brings together researchers and practitioners from the IUI and CUI communities in academia and industry. We aim to (1) identify and map out key focus areas and research challenges to address these critical theoretical and methodological gaps and (2) foster strong relationships between disciplines within and related to Artificial Intelligence (AI) and Human-Computer Interaction (HCI).
{"title":"CUI@IUI: Theoretical and Methodological Challenges in Intelligent Conversational User Interface Interactions","authors":"Philip R. Doyle, D. Rough, Justin Edwards, Benjamin R. Cowan, L. Clark, Martin Porcheron, Stephan Schlögl, M. I. Torres, Cosmin Munteanu, Christine Murad, Jaisie Sin, Minha Lee, M. Aylett, Heloisa Candello","doi":"10.1145/3397482.3450706","DOIUrl":"https://doi.org/10.1145/3397482.3450706","url":null,"abstract":"This workshop aims to bring together the Intelligent User Interface (IUI) and Conversational User Interface (CUI) communities to understand the theoretical and methodological challenges in designing, deploying and evaluating CUIs. CUIs have continued to prosper with the increased use and technological developments in both text-based chatbots and speech-based systems. However, challenges remain in creating established theoretical and methodological approaches for CUIs, and how these can be used with recent engineering advances. These include assessing the impact of interface design on user behaviours and perceptions, developing design guidelines, understanding the role of personalisation and issues of ethics and privacy. Our half-day multidisciplinary workshop brings together researchers and practitioners from the IUI and CUI communities in academia and industry. We aim to (1) identify and map out key focus areas and research challenges to address these critical theoretical and methodological gaps and (2) foster strong relationships between disciplines within and related to Artificial Intelligence (AI) and Human-Computer Interaction (HCI).","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129206711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Passwords are the most common user authentication methods. Password policies regulate passwords to a certain degree of complexity, which also makes it difficult for users to create and remember passwords. Password managers improve both security and usability by allowing users to memorize only one master password. However, authenticating to the password manager with the master password has the risk of exposing all passwords when the security of the password manager is breached. We present a password manager, MonoPass, that leverages a master password to regenerate consistent passwords across a variety of devices and passes password metadata through a central server. MonoPass enables users to synchronize passwords without storing user data on the server and without using authentication with the master password.
{"title":"MonoPass: A Password Manager without Master Password Authentication","authors":"Hyeon-Cheol Jeong, Hyunggu Jung","doi":"10.1145/3397482.3450720","DOIUrl":"https://doi.org/10.1145/3397482.3450720","url":null,"abstract":"Passwords are the most common user authentication methods. Password policies regulate passwords to a certain degree of complexity, which also makes it difficult for users to create and remember passwords. Password managers improve both security and usability by allowing users to memorize only one master password. However, authenticating to the password manager with the master password has the risk of exposing all passwords when the security of the password manager is breached. We present a password manager, MonoPass, that leverages a master password to regenerate consistent passwords across a variety of devices and passes password metadata through a central server. MonoPass enables users to synchronize passwords without storing user data on the server and without using authentication with the master password.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121182886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Werner Geyer, Lydia B. Chilton, Justin D. Weisz, M. Maher
Recent advances in generative AI have resulted in a rapid and dramatic increase to the fidelity of created artifacts, from realistic-looking images of faces [10] to antimicrobial peptide sequences that treat diseases [5] to faked videos of prominent business leaders [4, 11]. We believe that people skilled within their creative domain can realize great benefits by incorporating generative models into their own work: as a source of inspiration, as a tool for manipulation, or as a creative partner. Our workshop will bring together researchers and practitioners from both the HCI and AI disciplines to explore and better understand the opportunities and challenges in building, using, and evaluating human-AI co-creative systems.
{"title":"HAI-GEN 2021: 2nd Workshop on Human-AI Co-Creation with Generative Models","authors":"Werner Geyer, Lydia B. Chilton, Justin D. Weisz, M. Maher","doi":"10.1145/3397482.3450707","DOIUrl":"https://doi.org/10.1145/3397482.3450707","url":null,"abstract":"Recent advances in generative AI have resulted in a rapid and dramatic increase to the fidelity of created artifacts, from realistic-looking images of faces [10] to antimicrobial peptide sequences that treat diseases [5] to faked videos of prominent business leaders [4, 11]. We believe that people skilled within their creative domain can realize great benefits by incorporating generative models into their own work: as a source of inspiration, as a tool for manipulation, or as a creative partner. Our workshop will bring together researchers and practitioners from both the HCI and AI disciplines to explore and better understand the opportunities and challenges in building, using, and evaluating human-AI co-creative systems.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129462752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Augmented Reality (AR), with its potential to bridge the virtual and real environments, creates new possibilities to develop more engaging and productive learning experiences. Evidence is beginning to emerge that this sophisticated technology offers new ways to improve the learning process for better interaction and engagement with students. Recently, AR has garnered much attention as an interactive technology that facilitates direct interaction with virtual objects in the real world. These virtual objects can be surrogates for real world teaching resources, allowing for virtual labs. Thus AR could allow learning experiences that would not be possible in impoverished educational systems around the world. Interestingly though, concepts such as virtual hand interaction and techniques such as machine learning are still not widely investigated in the domain of AR learning. The need for touchless interaction technologies has exceptionally increased in this post-COVID world. There are also existing pedagogical approaches that have not been explored in great detail in this new medium, such as Kinesthetic learning or ”Learning by Doing”. Using the touchless interaction hand interaction technology and machine learning agents, this research aims to address this gap by exploring these underutilised technologies to demonstrate the efficiency of AR learning. It will explore the different hand tracking APIs to integrate the virtual hand interaction, testing the devices’ compatibility with these APIs and integrating machine learning agents using reinforcement learning to develop an AR learning framework that can provide more productive and interactive learning experiences.
{"title":"Investigating Challenges and Opportunities of the Touchless Hand Interaction and Machine Learning Agents to Support Kinesthetic Learning in Augmented Reality","authors":"Muhammad Zahid Iqbal, A. Campbell","doi":"10.1145/3397482.3450713","DOIUrl":"https://doi.org/10.1145/3397482.3450713","url":null,"abstract":"Augmented Reality (AR), with its potential to bridge the virtual and real environments, creates new possibilities to develop more engaging and productive learning experiences. Evidence is beginning to emerge that this sophisticated technology offers new ways to improve the learning process for better interaction and engagement with students. Recently, AR has garnered much attention as an interactive technology that facilitates direct interaction with virtual objects in the real world. These virtual objects can be surrogates for real world teaching resources, allowing for virtual labs. Thus AR could allow learning experiences that would not be possible in impoverished educational systems around the world. Interestingly though, concepts such as virtual hand interaction and techniques such as machine learning are still not widely investigated in the domain of AR learning. The need for touchless interaction technologies has exceptionally increased in this post-COVID world. There are also existing pedagogical approaches that have not been explored in great detail in this new medium, such as Kinesthetic learning or ”Learning by Doing”. Using the touchless interaction hand interaction technology and machine learning agents, this research aims to address this gap by exploring these underutilised technologies to demonstrate the efficiency of AR learning. It will explore the different hand tracking APIs to integrate the virtual hand interaction, testing the devices’ compatibility with these APIs and integrating machine learning agents using reinforcement learning to develop an AR learning framework that can provide more productive and interactive learning experiences.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132130540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Soliha Rahman, Vinoth Pandian Sermuga Pandian, M. Jarke
In the User Interface (UI) design process, designers sketch the UI design (low fidelity prototype) with minimal focus on visual appearances before converting them to higher fidelities. Contrary to low-fidelity, higher fidelity prototypes require better layout and aesthetic quality, during which designers adhere to design laws and conventions. Numerous research studies attempt to automate this transformation of low fidelity sketches to higher fidelities using Deep Neural Networks. However, these studies seldom focus on the layout quality and aesthetics of the generated higher fidelity prototype. As a solution, this paper proposes RUITE, a UI layout refinement engine that optimizes layouts using a Transformer Encoder. We trained RUITE by adding noise to misalign 35,369 UI layouts from the RICO dataset as input and the original aligned layout annotation as ground-truth. Upon evaluation with 4,421 misaligned UI layouts, RUITE provides 77% accuracy in aligning them. RUITE improves the existing research on transforming low-fidelity sketches to higher fidelities by beautifying generated UI layouts.
{"title":"RUITE: Refining UI Layout Aesthetics Using Transformer Encoder","authors":"Soliha Rahman, Vinoth Pandian Sermuga Pandian, M. Jarke","doi":"10.1145/3397482.3450716","DOIUrl":"https://doi.org/10.1145/3397482.3450716","url":null,"abstract":"In the User Interface (UI) design process, designers sketch the UI design (low fidelity prototype) with minimal focus on visual appearances before converting them to higher fidelities. Contrary to low-fidelity, higher fidelity prototypes require better layout and aesthetic quality, during which designers adhere to design laws and conventions. Numerous research studies attempt to automate this transformation of low fidelity sketches to higher fidelities using Deep Neural Networks. However, these studies seldom focus on the layout quality and aesthetics of the generated higher fidelity prototype. As a solution, this paper proposes RUITE, a UI layout refinement engine that optimizes layouts using a Transformer Encoder. We trained RUITE by adding noise to misalign 35,369 UI layouts from the RICO dataset as input and the original aligned layout annotation as ground-truth. Upon evaluation with 4,421 misaligned UI layouts, RUITE provides 77% accuracy in aligning them. RUITE improves the existing research on transforming low-fidelity sketches to higher fidelities by beautifying generated UI layouts.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121778620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：