{"id":"https://openalex.org/W4377104115","doi":"https://doi.org/10.3390/a16050259","title":"Using Deep-Learned Vector Representations for Page Stream Segmentation by Agglomerative Clustering","display_name":"Using Deep-Learned Vector Representations for Page Stream Segmentation by Agglomerative Clustering","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4377104115","doi":"https://doi.org/10.3390/a16050259"},"language":"en","primary_location":{"id":"doi:10.3390/a16050259","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16050259","pdf_url":"https://www.mdpi.com/1999-4893/16/5/259/pdf?version=1684407683","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/16/5/259/pdf?version=1684407683","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080058484","display_name":"L.S. Busch","orcid":"https://orcid.org/0000-0002-8184-4939"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lukas Busch","raw_affiliation_strings":["Information Retrieval Lab, Informatics Institute, University of Amsterdam, 1012 WX Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Information Retrieval Lab, Informatics Institute, University of Amsterdam, 1012 WX Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033059967","display_name":"Ruben van Heusden","orcid":"https://orcid.org/0000-0001-9204-9220"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Ruben van Heusden","raw_affiliation_strings":["Information Retrieval Lab, Informatics Institute, University of Amsterdam, 1012 WX Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Information Retrieval Lab, Informatics Institute, University of Amsterdam, 1012 WX Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049970479","display_name":"M. Marx","orcid":"https://orcid.org/0000-0003-3255-3729"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Maarten Marx","raw_affiliation_strings":["Information Retrieval Lab, Informatics Institute, University of Amsterdam, 1012 WX Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Information Retrieval Lab, Informatics Institute, University of Amsterdam, 1012 WX Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033059967","https://openalex.org/A5049970479"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.2388,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49750731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"16","issue":"5","first_page":"259","last_page":"259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9034733772277832},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7647337913513184},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6254912614822388},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.5297675728797913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5122867822647095},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49848246574401855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4501131772994995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39621442556381226},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15510493516921997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9034733772277832},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7647337913513184},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6254912614822388},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.5297675728797913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5122867822647095},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49848246574401855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4501131772994995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39621442556381226},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15510493516921997},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/a16050259","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16050259","pdf_url":"https://www.mdpi.com/1999-4893/16/5/259/pdf?version=1684407683","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/bdf6cfd6-fc27-49f8-baac-152b723b9c70","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/using-deeplearned-vector-representations-for-page-stream-segmentation-by-agglomerative-clustering(bdf6cfd6-fc27-49f8-baac-152b723b9c70).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Busch, L, van Heusden, R & Marx, M 2023, 'Using Deep-Learned Vector Representations for Page Stream Segmentation by Agglomerative Clustering', Algorithms, vol. 16, no. 5, 259. https://doi.org/10.3390/a16050259","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/bdf6cfd6-fc27-49f8-baac-152b723b9c70","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/bdf6cfd6-fc27-49f8-baac-152b723b9c70","pdf_url":"https://pure.uva.nl/ws/files/178794618/algorithms-16-00259-with-cover.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Busch, L, van Heusden, R & Marx, M 2023, 'Using Deep-Learned Vector Representations for Page Stream Segmentation by Agglomerative Clustering', Algorithms, vol. 16, no. 5, 259. https://doi.org/10.3390/a16050259","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:cf01ef750231449994af2e0c025d0dbd","is_oa":true,"landing_page_url":"https://doaj.org/article/cf01ef750231449994af2e0c025d0dbd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 16, Iss 5, p 259 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a16050259","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16050259","pdf_url":"https://www.mdpi.com/1999-4893/16/5/259/pdf?version=1684407683","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4723783796","display_name":null,"funder_award_id":"CISC.CC.016","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320313716","display_name":"Canadian Institute of Steel Construction","ror":"https://ror.org/04w9bz196"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377104115.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1557074680","https://openalex.org/W1928124889","https://openalex.org/W1977813952","https://openalex.org/W2016381774","https://openalex.org/W2025620159","https://openalex.org/W2044899606","https://openalex.org/W2085859579","https://openalex.org/W2101234009","https://openalex.org/W2108598243","https://openalex.org/W2159083595","https://openalex.org/W2493916176","https://openalex.org/W2594363710","https://openalex.org/W2962858109","https://openalex.org/W2976911383","https://openalex.org/W2999219213","https://openalex.org/W3080232144","https://openalex.org/W3191530498","https://openalex.org/W4205729528","https://openalex.org/W4288954271","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4308177873","https://openalex.org/W3202479762","https://openalex.org/W2480493049","https://openalex.org/W4322582183","https://openalex.org/W2592115649","https://openalex.org/W1937392525","https://openalex.org/W2347632764"],"abstract_inverted_index":{"Page":[0],"stream":[1,18],"segmentation":[2,139],"(PSS)":[3],"is":[4,67,128,238,305],"the":[5,9,38,77,99,133,138,173,177,184,189,194,206,243,253,261,285,298],"task":[6,28,100,106],"of":[7,19,37,41,70,76,81,101,141,191,193,224,255,260],"retrieving":[8],"boundaries":[10],"that":[11,109,127,304],"separate":[12],"source":[13],"documents":[14,20,53,256],"given":[15],"a":[16,35,104,147,155,198,267,271,294,302],"consecutive":[17],"(for":[21],"example,":[22],"sequentially":[23],"scanned":[24],"PDF":[25],"files).":[26],"The":[27,63],"has":[29,270],"recently":[30],"gained":[31],"more":[32,240],"interest":[33],"as":[34,46,86,103,170,258,293,310],"result":[36],"digitization":[39],"efforts":[40],"various":[42],"companies":[43],"and":[44,59,91,119,160,201],"organizations,":[45],"they":[47],"move":[48],"towards":[49],"having":[50,197,252],"all":[51],"their":[52],"available":[54,158],"online":[55],"for":[56,61,228],"improved":[57],"searchability":[58],"accessibility":[60],"users.":[62],"current":[64,134],"state-of-the-art":[65],"approach":[66],"neural":[68],"start":[69,223],"document":[71,113,225,317],"page":[72,226],"classification":[73,149,227],"on":[74,152,154],"representations":[75,237],"text":[78],"and/or":[79],"images":[80,153],"pages":[82,110,122,192],"using":[83,163,208],"models":[84],"such":[85],"Visual":[87],"Geometry":[88],"Group-16":[89],"(VGG-16)":[90],"BERT":[92],"to":[93,116,121,130,172,180,187,278,308,315],"classify":[94],"individual":[95],"pages.":[96],"We":[97,136],"view":[98],"PSS":[102,283,309],"clustering":[105,144,178,213,218,231],"instead,":[107],"hypothesizing":[108],"from":[111],"one":[112],"are":[114],"similar":[115],"each":[117],"other":[118,124],"different":[120],"in":[123,132,205,263,297],"documents,":[125],"something":[126],"difficult":[129],"incorporate":[131],"approaches.":[135],"compare":[137],"performance":[140],"an":[142,203],"agglomerative":[143],"method":[145,179,186],"with":[146,162,214,219,232,245,284],"binary":[148],"model":[150],"based":[151],"new":[156],"publicly":[157],"dataset":[159],"experiment":[161],"either":[164,233],"pretrained":[165,215,234,249],"or":[166,235],"finetuned":[167,220,236,246],"image":[168],"vectors":[169],"inputs":[171],"model.":[174],"To":[175],"adapt":[176],"PSS,":[181],"we":[182,281],"propose":[183],"switch":[185],"alleviate":[188],"effects":[190],"same":[195],"class":[196],"high":[199],"similarity,":[200],"report":[202],"improvement":[204],"scores":[207],"this":[209],"method.":[210],"Unfortunately,":[211],"neither":[212],"embeddings":[216,221,247],"nor":[217],"outperformed":[222],"PSS.":[229],"However,":[230],"substantially":[239],"effective":[241],"than":[242],"baseline,":[244],"outperforming":[248],"embeddings.":[250],"Finally,":[251],"number":[254],"K":[257],"part":[259],"input,":[262],"our":[264],"use":[265],"case":[266],"realistic":[268],"assumption,":[269],"surprisingly":[272],"significant":[273],"positive":[274],"effect.":[275],"In":[276],"contrast":[277],"earlier":[279],"papers,":[280],"evaluate":[282],"overlap":[286],"weighted":[287],"partial":[288],"match":[289],"F1":[290],"score,":[291],"developed":[292],"Panoptic":[295],"Quality":[296],"computer":[299],"vision":[300],"domain,":[301],"metric":[303],"particularly":[306],"well-suited":[307],"it":[311],"can":[312],"be":[313],"used":[314],"measure":[316],"segmentation.":[318]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}