{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:54:14Z","timestamp":1743040454899,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031704413"},{"type":"electronic","value":"9783031704420"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70442-0_21","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:09:40Z","timestamp":1725955780000},"page":"347-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fetch-A-Set: A Large-Scale OCR-Free Benchmark for\u00a0Historical Document Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0167-8756","authenticated-orcid":false,"given":"Adri\u00e0","family":"Molina","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3333-8812","authenticated-orcid":false,"given":"Oriol Ramos","family":"Terrades","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4533-4739","authenticated-orcid":false,"given":"Josep","family":"Llad\u00f3s","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Antonacopoulos, A., Bridson, D., Papadopoulos, C., Pletschacher, S.: A realistic dataset for performance evaluation of document layout analysis. In: 2009 10th International Conference on Document Analysis and Recognition. IEEE (2009)","DOI":"10.1109\/ICDAR.2009.271"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Arvanitopoulos, N., Chevassus, G., Maggetti, D., et\u00a0al.: A handwritten french dataset for word spotting: CFRAMUZ. In: Proceedings of the 4th International Workshop on Historical Document Imaging and Processing (2017)","DOI":"10.1145\/3151509.3151523"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Balntas, V., Riba, E., Ponsa, D., Mikolajczyk, K.: Learning local feature descriptors with triplets and shallow convolutional neural networks. In: BMVC (2016)","DOI":"10.5244\/C.30.119"},{"key":"21_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning (2020)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Christlein, V., Nicolaou, A., Seuret, M., Stutzmann, D., Maier, A.: ICDAR 2019 competition on image retrieval for historical handwritten documents (2019)","DOI":"10.1109\/ICDAR.2019.00242"},{"key":"21_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/978-3-030-68787-8_16","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"ND Cilia","year":"2021","unstructured":"Cilia, N.D., De Stefano, C., Fontanella, F., Marthot-Santaniello, I., Scotto di Freca, A.: PapyRow: a dataset of row images from ancient Greek papyri for writers identification. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12667, pp. 223\u2013234. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68787-8_16"},{"key":"21_CR7","doi-asserted-by":"publisher","unstructured":"Clausner, C., Papadopoulos, C., Pletschacher, S., Antonacopoulos, A.: The ENP image and ground truth dataset of historical newspapers, pp. 931\u2013935 (2015). https:\/\/doi.org\/10.1109\/ICDAR.2015.7333898","DOI":"10.1109\/ICDAR.2015.7333898"},{"key":"21_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale (2020)"},{"issue":"1","key":"21_CR9","doi-asserted-by":"publisher","first-page":"011010","DOI":"10.1117\/1.JEI.26.1.011010","volume":"26","author":"S En","year":"2016","unstructured":"En, S., Nicolas, S., Petitjean, C., Jurie, F., Heutte, L.: New public dataset for spotting patterns in medieval document images. J. Electron. Imaging 26(1), 011010 (2016). https:\/\/doi.org\/10.1117\/1.JEI.26.1.011010","journal-title":"J. Electron. Imaging"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez-Mota, D., Almaz\u00e1n, J., Cirera, N., Forn\u00e9s, A., Llad\u00f3s, J.: BH2M: the Barcelona historical, handwritten marriages database. In: 2014 22nd International Conference on Pattern Recognition, pp. 256\u2013261. IEEE (2014)","DOI":"10.1109\/ICPR.2014.53"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Fiel, S., Kleber, F., Diem, M., et\u00a0al.: ICDAR2017 competition on historical document writer identification (historical-wi). In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 1377\u20131382 (2017)","DOI":"10.1109\/ICDAR.2017.225"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Fischer, A., Frinken, V., Forn\u00e9s, A., Bunke, H.: Transcription alignment of latin manuscripts using hidden Markov models. In: Proceedings of the 2011 Workshop on Historical Document Imaging and Processing, pp. 29\u201336 (2011)","DOI":"10.1145\/2037342.2037348"},{"issue":"7","key":"21_CR13","doi-asserted-by":"publisher","first-page":"934","DOI":"10.1016\/j.patrec.2011.09.009","volume":"33","author":"A Fischer","year":"2012","unstructured":"Fischer, A., Keller, A., Frinken, V., Bunke, H.: Lexicon-free handwritten word spotting using character HMMs. Pattern Recogn. Lett. 33(7), 934\u2013942 (2012)","journal-title":"Pattern Recogn. Lett."},{"key":"21_CR14","doi-asserted-by":"publisher","unstructured":"Gatos, B., et al.: GRPOLY-DB: an old Greek polytonic document image database. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 646\u2013650 (2015). https:\/\/doi.org\/10.1109\/ICDAR.2015.7333841","DOI":"10.1109\/ICDAR.2015.7333841"},{"issue":"2","key":"21_CR15","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1017\/S1351324922000110","volume":"29","author":"A Hamdi","year":"2023","unstructured":"Hamdi, A., Pontes, E.L., Sidere, N., Coustaty, M., Doucet, A.: In-depth analysis of the impact of OCR errors on named entity recognition and linking. Nat. Lang. Eng. 29(2), 425\u2013448 (2023)","journal-title":"Nat. Lang. Eng."},{"key":"21_CR16","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: R-CNN Mask . In: Proceedings of the IEEE International Conference on Computer Vision (2017)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW). IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Kassis, M., Abdalhaleem, A., Droby, A., et\u00a0al.: VML-HD: the historical Arabic documents dataset for recognition systems. In: 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR), pp. 11\u201314 (2017)","DOI":"10.1109\/ASAR.2017.8067751"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Kesiman, M., Burie, J., Wibawantara, G., et\u00a0al.: AMADI_LontarSet: the first handwritten balinese palm leaf manuscripts dataset. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 168\u2013173 (2016)","DOI":"10.1109\/ICFHR.2016.0042"},{"key":"21_CR20","unstructured":"Krishnan, P., Jawahar, C.: HWNet v2: an efficient word image representation for handwritten documents. Int. J. Doc. Anal. Recogn. (IJDAR)"},{"issue":"1\u20132","key":"21_CR21","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"21_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/978-3-319-56608-5_57","volume-title":"Advances in Information Retrieval","author":"E M\u00fcller","year":"2017","unstructured":"M\u00fcller, E., Springstein, M., Ewerth, R.: \u201cWhen was this picture taken?\u2019\u2019 \u2013 image date estimation in the wild. In: Jose, J.M., Hauff, C., Alt\u0131ngovde, I.S., Song, D., Albakour, D., Watt, S., Tait, J. (eds.) ECIR 2017. LNCS, vol. 10193, pp. 619\u2013625. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-56608-5_57"},{"key":"21_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/978-3-030-58595-2_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Musgrave","year":"2020","unstructured":"Musgrave, K., Belongie, S., Lim, S.-N.: A metric learning reality check. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XXV. LNCS, vol. 12370, pp. 681\u2013699. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_41"},{"key":"21_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/978-3-031-56063-7_9","volume-title":"Advances in Information Retrieval","author":"F Net","year":"2024","unstructured":"Net, F., Hern\u00e1ndez, N., Molina, A., G\u00f3mez, L.: A transformer-based object-centric approach for date estimation of historical photographs. In: Goharian, N., et al. (eds.) ECIR 2024. LNCS, vol. 14610, pp. 137\u2013150. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-56063-7_9"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Nikolaidou, K., Seuret, M., Mokayed, H., Liwicki, M.: A survey of historical document image datasets (2022)","DOI":"10.1007\/s10032-022-00405-8"},{"key":"21_CR26","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding (2018)"},{"key":"21_CR27","doi-asserted-by":"publisher","unstructured":"Pantke, W., Dennhardt, M., Fecker, D., M\u00e4rgner, V., Fingscheidt, T.: An historical handwritten Arabic dataset for segmentation-free word spotting - HADARA80P. In: 2014 14th International Conference on Frontiers in Handwriting Recognition, pp. 15\u201320 (2014). https:\/\/doi.org\/10.1109\/ICFHR.2014.11","DOI":"10.1109\/ICFHR.2014.11"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"P\u00e9rez, D., Taraz\u00f3n, L., Serrano, N., et\u00a0al.: The GERMANA database. In: 2009 10th International Conference on Document Analysis and Recognition, pp. 301\u2013305 (2009)","DOI":"10.1109\/ICDAR.2009.10"},{"key":"21_CR29","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR (2021)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks (2019)","DOI":"10.18653\/v1\/D19-1410"},{"issue":"6","key":"21_CR31","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1016\/j.patcog.2012.11.024","volume":"46","author":"V Romero","year":"2013","unstructured":"Romero, V., et al.: The esposalles database: an ancient marriage license corpus for off-line handwriting recognition. Pattern Recogn. 46(6), 1658\u20131669 (2013)","journal-title":"Pattern Recogn."},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"21_CR33","unstructured":"Serrano, N., Castro, F., Juan, A.: The RODRIGO database. In: Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC 2010). European Language Resources Association (ELRA), Valletta, Malta (2010)"},{"key":"21_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1007\/978-3-030-86337-1_41","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"M Seuret","year":"2021","unstructured":"Seuret, M., et al.: ICDAR 2021 competition on historical document classification. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 618\u2013634. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_41"},{"key":"21_CR35","unstructured":"Shazeer, N.: GLU variants improve transformer. arXiv preprint arXiv:2002.05202 (2020)"},{"key":"21_CR36","unstructured":"Stacchio, L., Angeli, A., Lisanti, G., Calanca, D., Marfia, G.: IMAGO: a family photo album dataset for a socio-historical analysis of the twentieth century. arXiv preprint arXiv:2012.01955 (2020)"},{"key":"21_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2018)"},{"key":"21_CR38","unstructured":"Xiong, R., et al.: On layer normalization in the transformer architecture. In: International Conference on Machine Learning, pp. 10524\u201310533. PMLR (2020)"},{"key":"21_CR39","unstructured":"Zhang, B., Sennrich, R.: Root mean square layer normalization. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70442-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:17:09Z","timestamp":1725956229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70442-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031704413","9783031704420"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70442-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Document Analysis Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"das2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/das2024.seecs.edu.pk\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}