An intelligent epistemological tool for audiovisual analysis and mediation of video art archive

IF 3.5 2区综合性期刊 0 ARCHAEOLOGY

Journal of Cultural Heritage Pub Date : 2024-07-01 DOI:10.1016/j.culher.2024.06.011

Jana Horakova , Pavel Sikora , Stepan Miklanek , Dusan Barok , Jiri Schimmel , Kamil Riha

{"title":"An intelligent epistemological tool for audiovisual analysis and mediation of video art archive","authors":"Jana Horakova , Pavel Sikora , Stepan Miklanek , Dusan Barok , Jiri Schimmel , Kamil Riha","doi":"10.1016/j.culher.2024.06.011","DOIUrl":null,"url":null,"abstract":"<div><p>This article focuses on the development and application of intelligent software for image and sound recognition to perform iconographic and audiographic analyses of the work of video art pioneers Steina and Woody Vasulka (the Vasulkas). The AI epistemological tool <span>Vasulka Live Archive</span><svg><path></path></svg> is designed to provide unique results that benefit from the synthesis of automatic statistical analysis across the dataset and application of predefined categories that are the results of aesthetic evaluation of the Vasulkas’ videos and inspired by terminology of video art aesthetics (Weibel, Krauss). The advantages of this AI tool reveal themselves particularly when the tool is used for transmedia analysis of the whole dataset (the Vasulkas’ work) as the accuracy and completeness of its results are out of reach of an individual human researcher. We argue that this kind of AI tools can contribute to more exact and data-based findings on media art aesthetics, it can contribute to establishing a new field augmented iconology (Spratt) as well as expanding the sphere of AI tools application towards digital collections of experimental and conceptual art of 20th and 21st centuries.</p></div>","PeriodicalId":15480,"journal":{"name":"Journal of Cultural Heritage","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cultural Heritage","FirstCategoryId":"103","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1296207424001353","RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"ARCHAEOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

This article focuses on the development and application of intelligent software for image and sound recognition to perform iconographic and audiographic analyses of the work of video art pioneers Steina and Woody Vasulka (the Vasulkas). The AI epistemological tool Vasulka Live Archive is designed to provide unique results that benefit from the synthesis of automatic statistical analysis across the dataset and application of predefined categories that are the results of aesthetic evaluation of the Vasulkas’ videos and inspired by terminology of video art aesthetics (Weibel, Krauss). The advantages of this AI tool reveal themselves particularly when the tool is used for transmedia analysis of the whole dataset (the Vasulkas’ work) as the accuracy and completeness of its results are out of reach of an individual human researcher. We argue that this kind of AI tools can contribute to more exact and data-based findings on media art aesthetics, it can contribute to establishing a new field augmented iconology (Spratt) as well as expanding the sphere of AI tools application towards digital collections of experimental and conceptual art of 20th and 21st centuries.

查看原文本刊更多论文

用于视听分析和视频艺术档案调解的智能认识论工具

本文重点介绍图像和声音识别智能软件的开发和应用，以对视频艺术先驱 Steina 和 Woody Vasulka（瓦苏尔卡夫妇）的作品进行图标和声音分析。人工智能认识论工具 "瓦苏尔卡现场档案 "旨在通过对整个数据集进行自动统计分析，并应用预先确定的类别（这些类别是对瓦苏尔卡视频进行美学评估的结果，其灵感来自视频艺术美学术语（韦伯、克劳斯）），从而提供独特的结果。这种人工智能工具的优势在对整个数据集（瓦苏尔卡斯的作品）进行跨媒体分析时尤为明显，因为其结果的准确性和完整性是人类研究人员无法企及的。我们认为，这种人工智能工具有助于对媒体艺术美学进行更精确和以数据为基础的研究，有助于建立一个新的增强图标学（Spratt）领域，并将人工智能工具的应用领域扩展到 20 世纪和 21 世纪实验艺术和观念艺术的数字藏品。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Cultural Heritage 综合性期刊-材料科学：综合

CiteScore

6.80

自引率

9.70%

发文量

166

审稿时长

52 days

期刊介绍： The Journal of Cultural Heritage publishes original papers which comprise previously unpublished data and present innovative methods concerning all aspects of science and technology of cultural heritage as well as interpretation and theoretical issues related to preservation.