Computational formalism : art history and machine learning
How the use of machine learning to analyze art images has revived formalism in art history, presenting a golden opportunity for art historians and computer scientists to learn from one another.Though formalism is an essential tool for art historians, much recent art history has focused on the social...
Uloženo v:
| Hlavní autor: | |
|---|---|
| Médium: | E-kniha Kniha |
| Jazyk: | angličtina |
| Vydáno: |
Cambridge
MIT Press
2023
The MIT Press |
| Vydání: | 1 |
| Edice: | Leonardo |
| Témata: | |
| ISBN: | 9780262545648, 0262545640, 0262374730, 9780262374736, 9780262374743, 0262374749 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | How the use of machine learning to analyze art images has revived formalism in art history, presenting a golden opportunity for art historians and computer scientists to learn from one another.Though formalism is an essential tool for art historians, much recent art history has focused on the social and political aspects of art. But now art historians are adopting machine learning methods to develop new ways to analyze the purely visual in datasets of art images. Amanda Wasielewski uses the term “computational formalism” todescribe this use of machine learning and computer vision technique in art historical research. At the same time that art historians are analyzing art images in new ways, computer scientists are using art images for experiments in machine learning and computer vision. Their research, says Wasielewski, would be greatly enriched by the inclusion of humanistic issues.The main purpose in applying computational techniques such as machine learning to art datasets is to automate the process of categorization using metrics such as style, a historically fraught concept in art history. After examining a fifteen-year trajectory in image categorization and art dataset creation in the fields of machine learning and computer vision, Wasielewski considers deep learning techniques that both create and detect forgeries and fakes in art. She investigates examples of art historical analysis in the fields of computer and information sciences, placing this research in the context of art historiography. She also raises questions as which artworks are chosen for digitization, and of those artworks that are born digital, which works gain acceptance into the canon of high art. |
|---|---|
| AbstractList | Though formalism is an essential tool for art historians, much recent art history has focused on the social and political aspects of art. But now art historians are adopting machine learning methods to develop new ways to analyze the purely visual in datasets of art images. Amanda Wasielewski uses the term "computational formalism" to describe this use of machine learning and computer vision technique in art historical research. At the same time that art historians are analyzing art images in new ways, computer scientists are using art images for experiments in machine learning and computer vision. Their research, says Wasielewski, would be greatly enriched by the inclusion of humanistic issues.
The main purpose in applying computational techniques such as machine learning to art datasets is to automate the process of categorization using metrics such as style, a historically fraught concept in art history. After examining a fifteen-year trajectory in image categorization and art dataset creation in the fields of machine learning and computer vision, Wasielewski considers deep learning techniques that both create and detect forgeries and fakes in art. She investigates examples of art historical analysis in the fields of computer and information sciences, placing this research in the context of art historiography. She also raises questions as which artworks are chosen for digitization, and of those artworks that are born digital, which works gain acceptance into the canon of high art. How the use of machine learning to analyze art images has revived formalism in art history, presenting a golden opportunity for art historians and computer scientists to learn from one another.Though formalism is an essential tool for art historians, much recent art history has focused on the social and political aspects of art. But now art historians are adopting machine learning methods to develop new ways to analyze the purely visual in datasets of art images. Amanda Wasielewski uses the term “computational formalism” todescribe this use of machine learning and computer vision technique in art historical research. At the same time that art historians are analyzing art images in new ways, computer scientists are using art images for experiments in machine learning and computer vision. Their research, says Wasielewski, would be greatly enriched by the inclusion of humanistic issues.The main purpose in applying computational techniques such as machine learning to art datasets is to automate the process of categorization using metrics such as style, a historically fraught concept in art history. After examining a fifteen-year trajectory in image categorization and art dataset creation in the fields of machine learning and computer vision, Wasielewski considers deep learning techniques that both create and detect forgeries and fakes in art. She investigates examples of art historical analysis in the fields of computer and information sciences, placing this research in the context of art historiography. She also raises questions as which artworks are chosen for digitization, and of those artworks that are born digital, which works gain acceptance into the canon of high art. Though formalism is an essential tool for art historians, much recent art history has focused on the social and political aspects of art. But now art historians are adopting machine learning methods to develop new ways to analyse the purely visual in datasets of art images. Amanda Wasielewski uses the term 'computational formalism' to describe this use of machine learning and computer vision technique in art historical research. At the same time that art historians are analysing art images in new ways, computer scientists are using art images for experiments in machine learning and computer vision. Their research, says Wasielewski, would be greatly enriched by the inclusion of humanistic issues. After examining image categorization and art dataset creation in the fields of machine learning and computer vision, Wasielewski considers deep learning techniques that both create and detect forgeries. Though formalism is an essential tool for art historians, much recent art history has focused on the social and political aspects of art. But now art historians are adopting machine learning methods to develop new ways to analyse the purely visual in datasets of art images. Amanda Wasielewski uses the term "computational formalism" to describe this use of machine learning and computer vision technique in art historical research. At the same time that art historians are analysing art images in new ways, computer scientists are using art images for experiments in machine learning and computer vision. Their research, says Wasielewski, would be greatly enriched by the inclusion of humanistic issues. The main purpose in applying computational techniques such as machine learning to art datasets is to automate the process of categorization using metrics such as style, a historically fraught concept in art history. After examining a fifteen-year trajectory in image categorization and art dataset creation in the fields of machine learning and computer vision, Wasielewski considers deep learning techniques that both create and detect forgeries and fakes in art. She investigates examples of art historical analysis in the fields of computer and information sciences, placing this research in the context of art historiography. She also raises such questions as which artworks are chosen for digitization, and of those artworks that are born digital, which works gain acceptance into the canon of high art. How the use of machine learning to analyze art images has revived formalism in art history, presenting a golden opportunity for art historians and computer scientists to learn from one another. Though formalism is an essential tool for art historians, much recent art history has focused on the social and political aspects of art. But now art historians are adopting machine learning methods to develop new ways to analyze the purely visual in datasets of art images. Amanda Wasielewski uses the term “computational formalism” to describe this use of machine learning and computer vision technique in art historical research. At the same time that art historians are analyzing art images in new ways, computer scientists are using art images for experiments in machine learning and computer vision. Their research, says Wasielewski, would be greatly enriched by the inclusion of humanistic issues. The main purpose in applying computational techniques such as machine learning to art datasets is to automate the process of categorization using metrics such as style, a historically fraught concept in art history. After examining a fifteen-year trajectory in image categorization and art dataset creation in the fields of machine learning and computer vision, Wasielewski considers deep learning techniques that both create and detect forgeries and fakes in art. She investigates examples of art historical analysis in the fields of computer and information sciences, placing this research in the context of art historiography. She also raises questions as which artworks are chosen for digitization, and of those artworks that are born digital, which works gain acceptance into the canon of high art. |
| Author | Wasielewski, Amanda |
| Author_xml | – sequence: 1 fullname: Wasielewski, Amanda |
| BackLink | https://cir.nii.ac.jp/crid/1130584002143762839$$DView record in CiNii https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-510403$$DView record from Swedish Publication Index (Uppsala universitet) |
| BookMark | eNqNkU1vEzEQho2giKbkHyCxBw4gkdbjb_dWQvmQKnFBvVrOxk5Md-2tvUvVf1-HrUDcKo3H8ryPXmtmFuhFTNEh9BbwqeQczvowDtmVcgaMCHWKMdSD4RlaaqkwEYRKJhl9_vfNGRdMHaEFwaSGFoq9RAugDAhgBvoVWpbyq3oQdUj6GJ2vUz9Mox1DirZrfMq97ULpm_PG5rHZhzKmfN_YuG162-5DdE3nbI4h7l6jI2-74paP9wm6_nL5c_1tdfXj6_f1xdXKEkY1X209lqCJd5q0QnkNUtqNwF55QrVXlrXeYeKxolr6WhFis9145oT1nLaU0hP0cTYud26YNmbIobf53iQbzOdwfWFS3plpMrz2iA_4hxm35cbdlX3qxmJ-d26T0k0x_03u6SwVlX0_s0NOt5Mro_mDtS6O2Xbm8tOa4toC5_IJaN2NpFiSir55RF3u3C6Z-WsOEiuu_snJDi6abbKzDgAC4yq_m-UYgmnDIQNQzBWr6wVGpSB1rPQBprirbA |
| ContentType | eBook Book |
| DBID | RYH V1H YSPEL ACNBI ADTPV BHHME BKCIP D8T DF2 |
| DEWEY | 702.85 |
| DOI | 10.7551/mitpress/14268.001.0001 |
| DatabaseName | CiNii Complete DOAB: Directory of Open Access Books Perlego SWEPUB Uppsala universitet full text SwePub SwePub Book full text SwePub Book SWEPUB Freely available online SWEPUB Uppsala universitet |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: V1H name: DOAB: Directory of Open Access Books url: https://directory.doabooks.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Visual Arts Computer Science Journalism & Communications |
| EISBN | 9780262374743 0262374749 9780262374736 0262374730 |
| Edition | 1 |
| ExternalDocumentID | oai_DiVA_org_uu_510403 9780262374743 9780262374736 EBC30397557 EBC29673072 5170858 111600 BD09659333 |
| Genre | Electronic books |
| GroupedDBID | 38. AABBV AAKNG AAOBU ABFEK ABVGD ACMPN ADBHD ALMA_UNASSIGNED_HOLDINGS BBABE CZZ ISLSO MCG MIJRL RYH V1H ACBYE YSPEL ACNBI ADTPV BHHME BKCIP D8T DF2 |
| ID | FETCH-LOGICAL-a24395-df07192fe92c68f9177ab60f8f239f8a4cfe02f08397f39f66bdbf4e6af53c333 |
| IEDL.DBID | V1H |
| ISBN | 9780262545648 0262545640 0262374730 9780262374736 9780262374743 0262374749 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001033431200007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Tue Nov 04 17:16:59 EST 2025 Sat Nov 16 04:05:22 EST 2024 Thu Nov 20 05:51:48 EST 2025 Wed Mar 12 00:03:57 EDT 2025 Sat May 31 00:09:16 EDT 2025 Tue Dec 02 16:09:59 EST 2025 Tue Oct 07 23:06:38 EDT 2025 Thu Jun 26 22:43:33 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| LCCN | 2022029684 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a24395-df07192fe92c68f9177ab60f8f239f8a4cfe02f08397f39f66bdbf4e6af53c333 |
| Notes | Content Type: text (ncrcontent), Media Type: unmediated (ncrmedia), Carrier Type: volume (ncrcarrier) Includes index |
| OCLC | 1341210419 |
| OpenAccessLink | https://directory.doabooks.org/handle/20.500.12854/111600 |
| PQID | EBC29673072 |
| PageCount | 200 |
| ParticipantIDs | swepub_primary_oai_DiVA_org_uu_510403 askewsholts_vlebooks_9780262374743 askewsholts_vlebooks_9780262374736 proquest_ebookcentral_EBC30397557 proquest_ebookcentral_EBC29673072 perlego_books_5170858 oapen_doabooks_111600 nii_cinii_1130584002143762839 |
| PublicationCentury | 2000 |
| PublicationDate | c2023 [2023] 2023 2023-05-23 |
| PublicationDateYYYYMMDD | 2023-01-01 2023-05-23 |
| PublicationDate_xml | – year: 2023 text: 2023 |
| PublicationDecade | 2020 |
| PublicationPlace | Cambridge |
| PublicationPlace_xml | – name: Cambridge, Massachsetts – name: Cambridge |
| PublicationSeriesTitle | Leonardo |
| PublicationYear | 2023 |
| Publisher | MIT Press The MIT Press |
| Publisher_xml | – name: MIT Press – name: The MIT Press |
| SSID | ssj0002800029 |
| Score | 2.3455505 |
| Snippet | How the use of machine learning to analyze art images has revived formalism in art history, presenting a golden opportunity for art historians and computer... Though formalism is an essential tool for art historians, much recent art history has focused on the social and political aspects of art. But now art... |
| SourceID | swepub askewsholts proquest perlego oapen nii |
| SourceType | Open Access Repository Aggregation Database Publisher |
| SubjectTerms | 19th century, c 1800 to c 1899 Art -- Expertising -- Methodology Art -- Historiography -- Data processing Art history Artificial Intelligence Artificiell intelligens authentication c 1500 onwards to present day Computer science Computing and Information Technology connoisseurship digital humanities Digital, video and new media arts formalism History of Art image database Konstvetenskap Machine learning Non-graphic and electronic art forms style The Arts The Arts: art forms The Arts: treatments and subjects Time period qualifiers |
| TableOfContents | Intro -- Series Page -- Title Page -- Copyright Page -- Dedication -- Table of Contents -- Series Foreword -- Acknowledgments -- Introduction: Return to Form -- Machine Learning and Computer Vision -- The New Science Wars -- Digital Art History -- Objectivity and Cultural Studies -- Art History and Objectivity -- Computational Formalism -- Questions of Style -- 1. The Shape of Data -- Digitization and Dataset Creation -- The Semantic Gap -- Artificial ArtHistorian -- Image Selection -- Image Categorization -- Stylistic Determinism -- Style Unsupervised -- Stylistic Devices -- 2. Deep Connoisseurship -- Cat, Dog, or Virgin Mary? -- Value, Fame, and the Artist's Hand -- Opening the Black Box -- The Business of Authenticity -- Next-Level Forgeries and Fakes -- An Artificial Artist? -- Poor Images -- 3. Conclusion: Man, Machine, Metaphor -- The Rise of the Humanities Lab -- Foreign Metaphors as Interdisciplinary Tool -- Appendix: Classification by Artistic Style, Publications in Computer Science, 2005-2021, Including the Development and Utilization of Fine Art Datasets -- Index Intro -- Contents -- Series Foreword -- Acknowledgments -- Introduction: Return to Form -- Machine Learning and Computer Vision -- The New Science Wars -- Digital Art History -- Objectivity and Cultural Studies -- Art History and Objectivity -- Computational Formalism -- Questions of Style -- 1. The Shape of Data -- Digitization and Dataset Creation -- The Semantic Gap -- Artificial ArtHistorian -- Image Selection -- Image Categorization -- Stylistic Determinism -- Style Unsupervised -- Stylistic Devices -- 2. Deep Connoisseurship -- Cat, Dog, or Virgin Mary? -- Value, Fame, and the Artist's Hand -- Opening the Black Box -- The Business of Authenticity -- Next-Level Forgeries and Fakes -- An Artificial Artist? -- Poor Images -- 3. Conclusion: Man, Machine, Metaphor -- The Rise of the Humanities Lab -- Foreign Metaphors as Interdisciplinary Tool -- Appendix: Classification by Artistic Style, Publications in Computer Science, 2005-2021, Including the Development and Utilization of Fine Art Datasets -- Notes -- Introduction -- Chapter 1 -- Chapter 2 -- Chapter 3 -- Appendix -- Index |
| Title | Computational formalism : art history and machine learning |
| URI | https://cir.nii.ac.jp/crid/1130584002143762839 https://directory.doabooks.org/handle/20.500.12854/111600 https://www.perlego.com/book/5170858/computational-formalism-art-history-and-machine-learning-pdf https://ebookcentral.proquest.com/lib/[SITE_ID]/detail.action?docID=29673072 https://ebookcentral.proquest.com/lib/[SITE_ID]/detail.action?docID=30397557 https://www.vlebooks.com/vleweb/product/openreader?id=none&isbn=9780262374736 https://www.vlebooks.com/vleweb/product/openreader?id=none&isbn=9780262374743 https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-510403 |
| WOSCitedRecordID | wos001033431200007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Nb9QwEB1By4G9tJRSAi1aEBzDJnHi2Me2dNUDqjigqDfLSWwpYptdbbL9_Tw72bI9gJB6seQPyYnHmXljT94QfQZgq2HW3ZW_YWFq4zosRR2FJU8zY7Q0qacvLr7nNzfi9lb-2En1NSjypYtqXmqHMzt_nT9QDsBT_5pFjhFBZOkMXyms9XPah4vDnd9VxNcPxyuJcIV0flgCCw_QzKKx4jBDOtI9PXTyP3XfL4ZYsByAYnbX9D4odRbDnLnQy9ixHsYTmujuF1QR1FTfwTa1TePSJumVaYGmV2YNx3_5GLnuspF6CzY_eMK7H9K-cb9EvKJnpj2ig20iiOmoF45oUjTdRi-m5-u-e00nw4DxlHE6d6h40XR3x1TMr35eXodj_oVQJ8ApWVhbABCZWCOTigsLzy7XJY-ssAmTVui0siZKLFCczC1aOC_r0qaGa5uxijH2hvbaZWve0tSIsq4ioTEAi6_T0vEcVhzqrdKMVVlAn3YWU90v_F1xpx7J6D8GpSygMwhCVY0rY5hoQCzPDIe5gKVkQMdeRGq7yGpYTLSPIlNDcxbnwKMioI9bASo_3xg1q64uLhNsPCjJ5F9jgBEktlEe0JdB-mo18Igox-z9rSnOFaSsNhtMCI3K3v3l-d7TS5fqfjj-OaW9fr0xZ_Siuu-bbv3B7_7fhTH3fg |
| linkProvider | Open Access Publishing in European Networks |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.title=Computational+formalism%3A+art+history+and+machine+learning&rft.au=Wasielewski%2C+Amanda&rft.date=2023-05-23&rft.pub=The+MIT+Press&rft.isbn=9780262374743&rft_id=info:doi/10.7551%2Fmitpress%2F14268.001.0001&rft.externalDocID=9780262374743 |
| thumbnail_l | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fwww.perlego.com%2Fbooks%2FRM_Books%2Fmit_press_bcfnihc%2F9780262374743.jpg |
| thumbnail_m | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fvle.dmmserver.com%2Fmedia%2F640%2F97802623%2F9780262374736.jpg http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fvle.dmmserver.com%2Fmedia%2F640%2F97802623%2F9780262374743.jpg |