{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:31:02Z","timestamp":1767339062200,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3689094.3689468","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T18:25:52Z","timestamp":1728411952000},"page":"18-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Scene Classification on Fine Arts with Style Transfer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9159-6139","authenticated-orcid":false,"given":"Haiting","family":"Huang","sequence":"first","affiliation":[{"name":"Pattern Recognition Lab, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4366-5216","authenticated-orcid":false,"given":"Mathias","family":"Zinnen","sequence":"additional","affiliation":[{"name":"Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7509-2275","authenticated-orcid":false,"given":"Shumei","family":"Liu","sequence":"additional","affiliation":[{"name":"Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9550-5284","authenticated-orcid":false,"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[{"name":"Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0455-3799","authenticated-orcid":false,"given":"Vincent","family":"Christlein","sequence":"additional","affiliation":[{"name":"Pattern Recognition Lab, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1093\/llc\/fqz013"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575865"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025197"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9060120"},{"volume-title":"Iconclass: a key to collaboration in the digital humanities","author":"Brandhorst Hans","key":"e_1_3_2_1_5_1","unstructured":"Hans Brandhorst and Etienne Posthumus. 2016. Iconclass: a key to collaboration in the digital humanities. In The Routledge Companion to Medieval Iconography. Routledge, 201--218."},{"key":"e_1_3_2_1_6_1","first-page":"26561","article-title":"Artistic Style Transfer with Internal-external Learning and Contrastive Learning","volume":"34","author":"Chen Haibo","year":"2021","unstructured":"Haibo Chen, Lei Zhao, Zhizhong Wang, Huiming Zhang, Zhiwen Zuo, Ailin Li, Wei Xing, and Dongming Lu. 2021. Artistic Style Transfer with Internal-external Learning and Contrastive Learning. Advances in Neural Information Processing Systems 34 (2021), 26561--26573.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","volume-title":"Fast patch-based style transfer of arbitrary style. arXiv preprint arXiv:1612.04337 abs\/1612.04337","author":"Chen Tian Qi","year":"2016","unstructured":"Tian Qi Chen and Mark Schmidt. 2016. Fast patch-based style transfer of arbitrary style. arXiv preprint arXiv:1612.04337 abs\/1612.04337 (2016)."},{"volume-title":"Advanced Concepts for Intelligent Vision Systems, Jacques Blanc-Talon","author":"Condorovici Razvan George","key":"e_1_3_2_1_8_1","unstructured":"Razvan George Condorovici, Corneliu Florea, and Constantin Vertan. 2013. Painting Scene Recognition Using Homogenous Shapes. In Advanced Concepts for Intelligent Vision Systems, Jacques Blanc-Talon, Andrzej Kasinski, Wilfried Philips, Dan Popescu, and Paul Scheunders (Eds.). Springer International Publishing, Cham, 262--273."},{"key":"e_1_3_2_1_9_1","volume-title":"Iconclass: an iconographic classification system. Art libraries journal 8, 2","author":"Couprie Leendert D","year":"1983","unstructured":"Leendert D Couprie. 1983. Iconclass: an iconographic classification system. Art libraries journal 8, 2 (1983), 32--49."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_11_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11894"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59126-1_28"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-015-0017-1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.68"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280951"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596770"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08547-4"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"volume-title":"Analyzing gesture in digital art history","author":"Impett Leonardo","key":"e_1_3_2_1_23_1","unstructured":"Leonardo Impett. 2020. Analyzing gesture in digital art history. In The Routledge Companion to Digital Humanities and Art History. Routledge, 386--407."},{"volume-title":"Improving object detection in art images using only style transfer. In 2021 international joint conference on neural networks (IJCNN)","author":"Kadish David","key":"e_1_3_2_1_24_1","unstructured":"David Kadish, Sebastian Risi, and Anders Sundnes L\u00f8vlie. 2021. Improving object detection in art images using only style transfer. In 2021 international joint conference on neural networks (IJCNN). IEEE, 1--8."},{"key":"e_1_3_2_1_25_1","first-page":"2755","article-title":"Context Based Emotion Recognition Using EMOTIC Dataset","volume":"42","author":"Kosti Ronak","year":"2020","unstructured":"Ronak Kosti, Jose M. Alvarez, Adria Recasens, and Agata Lapedriza. 2020. Context Based Emotion Recognition Using EMOTIC Dataset. IEEE Transactions on Pattern Analysis and Machine Intelligence 42, 11 (2020), 2755--2766. https:\/\/doi.org\/10. 1109\/TPAMI.2019.2916866","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_26_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.272"},{"key":"e_1_3_2_1_29_1","volume-title":"Trends and Topics in Computer Vision: ECCV 2010 Workshops, Heraklion, Crete, Greece, September 10--11","author":"Li Li-Jia","year":"2010","unstructured":"Li-Jia Li, Hao Su, Yongwhan Lim, and Li Fei-Fei. 2012. Objects as attributes for scene classification. In Trends and Topics in Computer Vision: ECCV 2010 Workshops, Heraklion, Crete, Greece, September 10--11, 2010, Revised Selected Papers, Part I 11. Springer, 57--69."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740-- 755."},{"key":"e_1_3_2_1_31_1","unstructured":"Shumei Liu Haiting Huang Mathias Zinnen Andreas Maier and Vincent Christlein. 2024. Novel Artistic Scene-Centric Datasets for Effective Transfer Learning in Fragrant Spaces. arXiv:2407.11701 [cs.CV] https:\/\/arxiv.org\/abs\/ 2407.11701"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.090"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3347317.3357242"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109153"},{"key":"e_1_3_2_1_35_1","first-page":"1","article-title":"Enhancing human pose estimation in ancient vase paintings via perceptuallygrounded style transfer learning","volume":"16","author":"Madhu Prathmesh","year":"2022","unstructured":"Prathmesh Madhu, Angel Villar-Corrales, Ronak Kosti, Torsten Bendschus, Corinna Reinhardt, Peter Bell, Andreas Maier, and Vincent Christlein. 2022. Enhancing human pose estimation in ancient vase paintings via perceptuallygrounded style transfer learning. ACM Journal on Computing and Cultural Heritage 16, 1 (2022), 1--17.","journal-title":"ACM Journal on Computing and Cultural Heritage"},{"key":"e_1_3_2_1_36_1","volume-title":"William Tullett, Cecilia Bembibre, and Inger Leemans.","author":"Marx Lizzie","year":"2023","unstructured":"Lizzie Marx, Mathias Zinnen, Sofia Collette Ehrich, William Tullett, Cecilia Bembibre, and Inger Leemans. 2023. Seeing Smell: Sourcing Olfactory Imagery Using Artificial Intelligence. Arts et Savoirs 20 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS48705.2020.9074460"},{"key":"e_1_3_2_1_38_1","volume-title":"Smell and Emotion: Recognising emotions in smell-related artworks. arXiv preprint arXiv:2407.04592","author":"Patoliya Vishal","year":"2024","unstructured":"Vishal Patoliya, Mathias Zinnen, Andreas Maier, and Vincent Christlein. 2024. Smell and Emotion: Recognising emotions in smell-related artworks. arXiv preprint arXiv:2407.04592 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Recognizing Indoor Scenes. In 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 413--420","author":"Quattoni Ariadna","year":"2009","unstructured":"Ariadna Quattoni and Antonio Torralba. 2009. Recognizing Indoor Scenes. In 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 413--420."},{"key":"e_1_3_2_1_40_1","volume-title":"European Conference on Computer Vision. Springer, 218--233","author":"Reshetnikov Artem","year":"2022","unstructured":"Artem Reshetnikov, Maria-Cristina Marinescu, and Joaquim More Lopez. 2022. Deart: Dataset of european art. In European Conference on Computer Vision. Springer, 218--233."},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Machine Learning. PMLR, 29441-- 29454","author":"Ryali Chaitanya","year":"2023","unstructured":"Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, et al. 2023. Hiera: A hierarchical vision transformer without the bellsand- whistles. In International Conference on Machine Learning. PMLR, 29441-- 29454."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"e_1_3_2_1_43_1","volume-title":"Bugra Gedik, Raj Prateek Kosaraju, Dhruv Mahajan, Ross Girshick, Piotr Doll\u00e1r, and Laurens van der Maaten.","author":"Singh Mannat","year":"2022","unstructured":"Mannat Singh, Laura Gustafson, Aaron Adcock, Vinicius de Freitas Reis, Bugra Gedik, Raj Prateek Kosaraju, Dhruv Mahajan, Ross Girshick, Piotr Doll\u00e1r, and Laurens van der Maaten. 2022. Revisiting Weakly Supervised Pre-Training of Visual Perception Models. In CVPR."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00357"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548371"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3273022"},{"key":"e_1_3_2_1_47_1","volume-title":"Texture Networks: Feed-forward Synthesis of Textures and Stylized Images. In International Conference on Machine Learning. PMLR, 1349--1357","author":"Ulyanov Dmitry","year":"2016","unstructured":"Dmitry Ulyanov, Vadim Lebedev, Victor Lempitsky, et al. 2016. Texture Networks: Feed-forward Synthesis of Textures and Stylized Images. In International Conference on Machine Learning. PMLR, 1349--1357."},{"key":"e_1_3_2_1_48_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00508"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2666739"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5220\/0010288206010610"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18146\/tmg.815"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142018"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0748-y"},{"key":"e_1_3_2_1_55_1","volume-title":"Sun Database: Large-Scale Scene Recognition from Abbey to Zoo. In 2010 IEEE computer society conference on computer vision and pattern recognition","author":"Xiao Jianxiong","year":"2010","unstructured":"Jianxiong Xiao, James Hays, Krista A Ehinger, Aude Oliva, and Antonio Torralba. 2010. Sun Database: Large-Scale Scene Recognition from Abbey to Zoo. In 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 3485--3492."},{"key":"e_1_3_2_1_56_1","volume-title":"2012 IEEE conference on computer vision and pattern recognition. IEEE, 702--709","author":"Yao Jian","year":"2012","unstructured":"Jian Yao, Sanja Fidler, and Raquel Urtasun. 2012. Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation. In 2012 IEEE conference on computer vision and pattern recognition. IEEE, 702--709."},{"key":"e_1_3_2_1_57_1","volume-title":"Deep learning for scene classification: A survey. arXiv preprint arXiv:2101.10531","author":"Zeng Delu","year":"2021","unstructured":"Delu Zeng, Minyu Liao, Mohammad Tavakolian, Yulan Guo, Bolei Zhou, Dewen Hu, Matti Pietik\u00e4inen, and Li Liu. 2021. Deep learning for scene classification: A survey. arXiv preprint arXiv:2101.10531 (2021), arXiv--2101."},{"key":"e_1_3_2_1_58_1","volume-title":"Places: A 10 million image database for scene recognition","author":"Zhou Bolei","year":"2017","unstructured":"Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. 2017. Places: A 10 million image database for scene recognition. IEEE transactions on pattern analysis and machine intelligence 40, 6 (2017), 1452--1464."},{"key":"e_1_3_2_1_59_1","volume-title":"Learning Deep Features for Scene Recognition using Places Database. Advances in neural information processing systems 27","author":"Zhou Bolei","year":"2014","unstructured":"Bolei Zhou, Agata Lapedriza, Jianxiong Xiao, Antonio Torralba, and Aude Oliva. 2014. Learning Deep Features for Scene Recognition using Places Database. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3607542.3617357"},{"key":"e_1_3_2_1_61_1","volume-title":"Transfer Learning for Olfactory Object Detection. arXiv preprint arXiv:2301.09906","author":"Zinnen Mathias","year":"2023","unstructured":"Mathias Zinnen, Prathmesh Madhu, Peter Bell, Andreas Maier, and Vincent Christlein. 2023. Transfer Learning for Olfactory Object Detection. arXiv preprint arXiv:2301.09906 (2023), arXiv--2301."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124576"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 6th workshop on the analySis, Understanding and proMotion of heritAge Contents"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689094.3689468","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689094.3689468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:37:33Z","timestamp":1755974253000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689094.3689468"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":62,"alternative-id":["10.1145\/3689094.3689468","10.1145\/3689094"],"URL":"https:\/\/doi.org\/10.1145\/3689094.3689468","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}