{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T10:16:46Z","timestamp":1783073806638,"version":"3.54.6"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915710","type":"print"},{"value":"9783031915727","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-91572-7_18","type":"book-chapter","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T04:13:15Z","timestamp":1747973595000},"page":"295-311","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Approach for\u00a0Dataset Extension for\u00a0Object Detection in\u00a0Artworks Using Open-Vocabulary Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4559-0748","authenticated-orcid":false,"given":"Tetiana","family":"Yemelianenko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5551-1105","authenticated-orcid":false,"given":"Iuliia","family":"Tkachenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tess","family":"Masclef","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mihaela","family":"Scuturici","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7722-9899","authenticated-orcid":false,"given":"Serge","family":"Miguet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"18_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. ArXiv abs\/2004.10934 (2020)"},{"key":"18_CR2","doi-asserted-by":"publisher","unstructured":"Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3D human pose annotations. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1365\u20131372 (2009). https:\/\/doi.org\/10.1109\/ICCV.2009.5459303","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Bourdev, L.D., Maji, S., Brox, T., Malik, J.: Detecting people using mutually consistent poselet activations. In: European Conference on Computer Vision (2010)","DOI":"10.1007\/978-3-642-15567-3_13"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision \u2013 ECCV 2020, pp. 213\u2013229. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., Shan, Y.: YOLO-world: real-time open-vocabulary object detection. ArXiv abs\/2401.17270 (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"18_CR6","unstructured":"Crowley, E.J., Zisserman, A.: In search of art. In: Workshop on Computer Vision for Art Analysis, ECCV (2014)"},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol.\u00a01, pp. 886\u2013893 (2005). https:\/\/doi.org\/10.1109\/CVPR.2005.177","DOI":"10.1109\/CVPR.2005.177"},{"key":"18_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2019)"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Felzenszwalb, P., Girshick, R., Mcallester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1627\u201345 (2010). https:\/\/doi.org\/10.1109\/TPAMI.2009.167","DOI":"10.1109\/TPAMI.2009.167"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Garcia, N., Vogiatzis, G.: How to read paintings: semantic art understanding with multi-modal retrieval. ArXiv abs\/1810.09617 (2018)","DOI":"10.1007\/978-3-030-11012-3_52"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Ginosar, S., Haas, D., Brown, T., Malik, J.: Detecting people in cubist art. In: SIGAI (2014)","DOI":"10.1007\/978-3-319-16178-5_7"},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"18_CR13","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2013). https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Gonthier, N., Gousseau, Y., Ladjal, S., Bonfait, O.: Weakly supervised object detection in artworks. In: Computer Vision \u2013 ECCV 2018 Workshops, pp. 692\u2013709. Springer, Cham (2019)","DOI":"10.1007\/978-3-030-11012-3_53"},{"key":"18_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103299","volume":"214","author":"N Gonthier","year":"2022","unstructured":"Gonthier, N., Ladjal, S., Gousseau, Y.: Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts. Comput. Vis. Image Underst. 214, 103299 (2022). https:\/\/doi.org\/10.1016\/j.cviu.2021.103299","journal-title":"Comput. Vis. Image Underst."},{"key":"18_CR16","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Ibrahim, B.I.E., Eyharabide, V., Le\u00a0Page, V., Billiet, F.: Few-shot object detection: application to medieval musicological studies. J. Imag. 8(2) (2022). https:\/\/doi.org\/10.3390\/jimaging8020018","DOI":"10.3390\/jimaging8020018"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Kadish, D., Risi, S., L\u00f8vlie, A.S.: Improving object detection in art images using only style transfer. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138 (2021)","DOI":"10.1109\/IJCNN52387.2021.9534264"},{"key":"18_CR19","unstructured":"Karayev, S., T., et al.: Recognizing image style. ArXiv abs\/1311.3715 (2013)"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Khan, F., Beigpour, S.,Weijer, J., Felsberg, M.: Painting-91: a large scale database for computational painting categorization. Mach. Vis. Appl. 25, 1385\u20131397 (2014). https:\/\/doi.org\/10.1007\/s00138-014-0621-6","DOI":"10.1007\/s00138-014-0621-6"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10955\u201310965 (2021)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"18_CR22","unstructured":"Liao, P., Li, X., Liu, X., Keutzer, K.: The ArtBench dataset: benchmarking generative models with artworks. arXiv preprint arXiv:2206.11404 (2022)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2016)","DOI":"10.1109\/CVPR.2017.106"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. ArXiv abs\/2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: SSD: Single shot multibox detector. In: European Conference on Computer Vision (2015)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"Mao, H., Cheung, M., She, J.: DeepArt: learning joint representations of visual arts. In: Proceedings of the 25th ACM International Conference on Multimedia, MM 2017, pp. 1183\u20131191. Association for Computing Machinery, New York (2017). https:\/\/doi.org\/10.1145\/3123266.3123405","DOI":"10.1145\/3123266.3123405"},{"key":"18_CR28","doi-asserted-by":"publisher","unstructured":"Mensink, T., van Gemert, J.: The Rijksmuseum challenge: museum-centered visual recognition. In: Proceedings of International Conference on Multimedia Retrieval, ICMR 2014, pp. 451\u2013454. Association for Computing Machinery, New York (2014). https:\/\/doi.org\/10.1145\/2578726.2578791","DOI":"10.1145\/2578726.2578791"},{"key":"18_CR29","doi-asserted-by":"publisher","unstructured":"Meyer, L., et al.: Algorithmic ways of seeing: using object detection to facilitate art exploration. In: Proceedings of the CHI Conference on Human Factors in Computing Systems, CHI 2024. Association for Computing Machinery, New York (2024). https:\/\/doi.org\/10.1145\/3613904.3642157","DOI":"10.1145\/3613904.3642157"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Minderer, M., Gritsenko, A.A., Houlsby, N.: Scaling open-vocabulary object detection. ArXiv abs\/2306.09683 (2023)","DOI":"10.52202\/075280-3191"},{"key":"18_CR31","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection with vision transformers. ArXiv abs\/2205.06230 (2022)"},{"key":"18_CR32","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2015)","DOI":"10.1109\/CVPR.2016.91"},{"key":"18_CR34","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Reshetnikov, A., Marinescu, M.C.V., L\u00f3pez, J.M.: DEArt: dataset of European art. In: ECCV Workshops (2022)","DOI":"10.1007\/978-3-031-25056-9_15"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"Strezoski, G., Worring, M.: OmniArt: a large-scale artistic benchmark. ACM Trans. Multimedia Comput. Commun. Appl. 14, 1\u201321 (2018). https:\/\/doi.org\/10.1145\/3273022","DOI":"10.1145\/3273022"},{"key":"18_CR37","doi-asserted-by":"publisher","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9626\u20139635 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464\u20137475 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Westlake, N., Cai, H., Hall, P.: Detecting people in artwork with CNNs. In: ECCV Workshops (2016)","DOI":"10.1007\/978-3-319-46604-0_57"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Xiao, B., et al.: Florence-2: advancing a unified representation for a variety of vision tasks. ArXiv abs\/2311.06242 (2023)","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"18_CR41","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14393\u201314402 (2021)"},{"key":"18_CR42","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"18_CR43","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. ArXiv abs\/2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91572-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T09:26:27Z","timestamp":1783070787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91572-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915710","9783031915727"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91572-7_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}