Pub Date : 2019-10-01DOI: 10.1109/VISAP.2019.8900858
Mahika Dubey, Jasmine Otto, A. Forbes
This paper introduces Data Brushes, an interactive web application to explore neural style transfer using models trained on data visualizations. Our application includes two distinct modes that invite casual creators to engage with deep convolutional neural networks to co-create custom artworks. The first mode, ‘magic markers’, mimics painting with a brush on a canvas, enabling users to paint a style onto selected areas of an image. The second mode, ‘compositing stamps’, uses a real-time method for applying style filters to selected portions of an image. Specifically, we focus on style transfer networks created from canonical and contemporary works of data visualization and data art in order to investigate the versatility and flexibility of the algorithm. In addition to enabling a novel creative workflow, the process of interactively modifying an image via multiple style transfer networks reveals meaningful features encoded within the networks, and provides insight into the effects particular networks have on different images, or different regions within a single image. To evaluate Data Brushes, we gathered expert feedback from participants of a data science symposium and ran an observational study, finding that our application facilitates the creative exploration of neural style transfer for data art and enhances user intuition regarding the expressive range of style transfer features.
{"title":"Data Brushes: Interactive Style Transfer for Data Art","authors":"Mahika Dubey, Jasmine Otto, A. Forbes","doi":"10.1109/VISAP.2019.8900858","DOIUrl":"https://doi.org/10.1109/VISAP.2019.8900858","url":null,"abstract":"This paper introduces Data Brushes, an interactive web application to explore neural style transfer using models trained on data visualizations. Our application includes two distinct modes that invite casual creators to engage with deep convolutional neural networks to co-create custom artworks. The first mode, ‘magic markers’, mimics painting with a brush on a canvas, enabling users to paint a style onto selected areas of an image. The second mode, ‘compositing stamps’, uses a real-time method for applying style filters to selected portions of an image. Specifically, we focus on style transfer networks created from canonical and contemporary works of data visualization and data art in order to investigate the versatility and flexibility of the algorithm. In addition to enabling a novel creative workflow, the process of interactively modifying an image via multiple style transfer networks reveals meaningful features encoded within the networks, and provides insight into the effects particular networks have on different images, or different regions within a single image. To evaluate Data Brushes, we gathered expert feedback from participants of a data science symposium and ran an observational study, finding that our application facilitates the creative exploration of neural style transfer for data art and enhances user intuition regarding the expressive range of style transfer features.","PeriodicalId":190247,"journal":{"name":"2019 IEEE VIS Arts Program (VISAP)","volume":"59 15","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113939053","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}
Pub Date : 2019-10-01DOI: 10.1109/VISAP.2019.8900903
Graham Wakefield, H. Ji
“Infranet” is a generative artwork interweaving data visualization and sonification, artificial intelligence, and evolutionary algorithms in a population of artificial life creatures, thriving upon geospatial data of the infrastructure of a city as its sustenance and canvas. Each exhibit of Infranet utilizes public data available on the host city; including Gwangju, South Korea (2018), New York, USA (2019), and Vancouver, Canada (2019). This paper documents the motivations behind the work, its design and subsequent implementation in details. At its heart is the speculative proposition of the data of a city as a habitat for new forms of life. Our design in response utilizes neural networks at individual, as well as population-wide scales, along with horizontal gene transfer and contagion/entrainment as means for the living beings to open-endedly discover the variety in the data habitat.
{"title":"Infranet: A Geospatial Data-Driven Neuro-Evolutionary Artwork","authors":"Graham Wakefield, H. Ji","doi":"10.1109/VISAP.2019.8900903","DOIUrl":"https://doi.org/10.1109/VISAP.2019.8900903","url":null,"abstract":"“Infranet” is a generative artwork interweaving data visualization and sonification, artificial intelligence, and evolutionary algorithms in a population of artificial life creatures, thriving upon geospatial data of the infrastructure of a city as its sustenance and canvas. Each exhibit of Infranet utilizes public data available on the host city; including Gwangju, South Korea (2018), New York, USA (2019), and Vancouver, Canada (2019). This paper documents the motivations behind the work, its design and subsequent implementation in details. At its heart is the speculative proposition of the data of a city as a habitat for new forms of life. Our design in response utilizes neural networks at individual, as well as population-wide scales, along with horizontal gene transfer and contagion/entrainment as means for the living beings to open-endedly discover the variety in the data habitat.","PeriodicalId":190247,"journal":{"name":"2019 IEEE VIS Arts Program (VISAP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126010322","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}
Pub Date : 2019-10-01DOI: 10.1109/VISAP.2019.8900822
Rodrigo Rosales González, Ana Carolina Robles Salvador
The purpose of this collaboration is to offer elements for discussion on the role of intersections among art, design, and technology for approaching the socialization environmental issue as an exercise of visualization praxis. Concretely, it is appealed the case of an interactive piece, expressly designed, called trasTocar (to disrupt) exhibited in Zanbatha, the municipal museum in the inner state of México. This artwork agglomerates multiple perspectives for discussion: the theoretical border between art and design to solve communication problems; to inform people about altered and polluted surroundings landscape because of their individual actions; the addressing to spectators through technology to modify their behavior; and, the possibility to obtain data from this interaction.
{"title":"Embroidering Translations between Digital Art and Design for a Sustainable Environment","authors":"Rodrigo Rosales González, Ana Carolina Robles Salvador","doi":"10.1109/VISAP.2019.8900822","DOIUrl":"https://doi.org/10.1109/VISAP.2019.8900822","url":null,"abstract":"The purpose of this collaboration is to offer elements for discussion on the role of intersections among art, design, and technology for approaching the socialization environmental issue as an exercise of visualization praxis. Concretely, it is appealed the case of an interactive piece, expressly designed, called trasTocar (to disrupt) exhibited in Zanbatha, the municipal museum in the inner state of México. This artwork agglomerates multiple perspectives for discussion: the theoretical border between art and design to solve communication problems; to inform people about altered and polluted surroundings landscape because of their individual actions; the addressing to spectators through technology to modify their behavior; and, the possibility to obtain data from this interaction.","PeriodicalId":190247,"journal":{"name":"2019 IEEE VIS Arts Program (VISAP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116490359","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：