{"id":"https://openalex.org/W4312874665","doi":"https://doi.org/10.1109/icpr56361.2022.9956155","title":"Writer Retrieval using Compact Convolutional Transformers and NetMVLAD","display_name":"Writer Retrieval using Compact Convolutional Transformers and NetMVLAD","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312874665","doi":"https://doi.org/10.1109/icpr56361.2022.9956155"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956155","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026297998","display_name":"Marco Peer","orcid":"https://orcid.org/0000-0001-6843-0830"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marco Peer","raw_affiliation_strings":["TU Wien,Computer Vision Lab,Institute of Visual Computing & Human-Centered Technology,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Computer Vision Lab,Institute of Visual Computing & Human-Centered Technology,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083550889","display_name":"Florian Kleber","orcid":"https://orcid.org/0000-0001-8351-5066"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Florian Kleber","raw_affiliation_strings":["TU Wien,Computer Vision Lab,Institute of Visual Computing & Human-Centered Technology,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Computer Vision Lab,Institute of Visual Computing & Human-Centered Technology,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019162549","display_name":"Robert Sablatnig","orcid":"https://orcid.org/0000-0003-4195-1593"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Robert Sablatnig","raw_affiliation_strings":["TU Wien,Computer Vision Lab,Institute of Visual Computing & Human-Centered Technology,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Computer Vision Lab,Institute of Visual Computing & Human-Centered Technology,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1571","last_page":"1578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9993000030517578,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613181471824646},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7320027351379395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.66053706407547},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6408812999725342},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6324557662010193},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6045461893081665},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5321188569068909},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5025084018707275},{"id":"https://openalex.org/keywords/scale-invariant-feature-transform","display_name":"Scale-invariant feature transform","score":0.4190753102302551},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3334549069404602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613181471824646},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7320027351379395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.66053706407547},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6408812999725342},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6324557662010193},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6045461893081665},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5321188569068909},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5025084018707275},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.4190753102302551},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3334549069404602},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956155","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1928278792","https://openalex.org/W1982067089","https://openalex.org/W1984309565","https://openalex.org/W2048171373","https://openalex.org/W2050995497","https://openalex.org/W2133059825","https://openalex.org/W2151103935","https://openalex.org/W2179042386","https://openalex.org/W2190740400","https://openalex.org/W2194775991","https://openalex.org/W2328077678","https://openalex.org/W2331143823","https://openalex.org/W2529897829","https://openalex.org/W2605102252","https://openalex.org/W2612112834","https://openalex.org/W2620629206","https://openalex.org/W2906540649","https://openalex.org/W2908510526","https://openalex.org/W2962708362","https://openalex.org/W2963272834","https://openalex.org/W2963446712","https://openalex.org/W2963775347","https://openalex.org/W2963988212","https://openalex.org/W3081288214","https://openalex.org/W3094502228","https://openalex.org/W3109684201","https://openalex.org/W3121523901","https://openalex.org/W3128099838","https://openalex.org/W3137278571","https://openalex.org/W3159778524","https://openalex.org/W3160331490","https://openalex.org/W3168356478","https://openalex.org/W3172942063","https://openalex.org/W3203778378","https://openalex.org/W4297849929","https://openalex.org/W4312950730","https://openalex.org/W4385245566","https://openalex.org/W6675402254","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6784333009","https://openalex.org/W6795062860","https://openalex.org/W6796534762","https://openalex.org/W6798046796"],"related_works":["https://openalex.org/W3034955165","https://openalex.org/W2094920358","https://openalex.org/W2041448692","https://openalex.org/W2953234277","https://openalex.org/W2247121321","https://openalex.org/W2391926582","https://openalex.org/W2626256601","https://openalex.org/W2468279273","https://openalex.org/W1966831329","https://openalex.org/W1995688991"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,20,25,34],"method":[4],"for":[5,53,70],"writer":[6,54,71],"retrieval":[7,55],"where":[8],"embeddings":[9],"of":[10,51,83,86,94,112,115,136],"patches":[11],"extracted":[12],"at":[13,76],"SIFT":[14],"keypoint":[15],"locations":[16],"are":[17],"learned":[18],"by":[19,33],"Compact":[21],"Convolutional":[22,61],"Transformer":[23],"(CCT),":[24],"modified":[26],"attention-based":[27],"transformer":[28],"architecture":[29],"including":[30],"convolutions,":[31],"followed":[32],"NetMVLAD":[35,152],"layer":[36,143],"and":[37,56,131,163],"Generalized":[38],"Max":[39],"Pooling":[40],"(GMP)":[41],"to":[42,99,118],"obtain":[43],"global":[44],"page":[45],"descriptors.":[46],"We":[47],"introduce":[48],"the":[49,77,84,107,113,123,141,160,166],"application":[50],"CCTs":[52,116],"show":[57],"that":[58],"they":[59],"outperform":[60],"Neural":[62],"Networks":[63],"(CNNs)":[64],"used":[65],"in":[66],"current":[67],"State-of-the-Art":[68],"methods":[69],"retrieval,":[72],"namely":[73],"ResNet18,":[74],"while":[75],"same":[78],"time":[79],"only":[80],"have":[81],"one-third":[82],"number":[85],"parameters.":[87],"Additionally,":[88],"we":[89],"propose":[90],"Net-MVLAD,":[91],"an":[92],"extension":[93],"NetVLAD":[95,142],"with":[96,102,151],"multiple":[97,137],"vocabularies,":[98],"encode":[100],"information":[101],"different":[103],"vocabulary":[104],"sizes":[105],"improving":[106],"original":[108],"NetVLAD.":[109],"An":[110],"evaluation":[111],"performance":[114],"compared":[117],"ResNet18":[119],"is":[120,144],"provided":[121],"on":[122,126,148,159,165],"ICDAR2013":[124,161],"Competition":[125],"Writer":[127],"Identification":[128],"dataset":[129,162],"(ICDAR2013)":[130],"CVL":[132,167],"dataset.":[133,168],"The":[134],"effect":[135],"vocabularies":[138],"applied":[139],"within":[140],"shown.":[145],"CCT7":[146],"pretrained":[147],"CIFAR-100":[149],"combined":[150],"achieves":[153],"89.3%":[154],"Mean":[155],"Average":[156],"Precision":[157],"(mAP)":[158],"96.5%":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}