{"id":"https://openalex.org/W4387161251","doi":"https://doi.org/10.1145/3617233.3617239","title":"Noisy and Unbalanced Multimodal Document Classification: Textbook Exercises as a Use Case","display_name":"Noisy and Unbalanced Multimodal Document Classification: Textbook Exercises as a Use Case","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4387161251","doi":"https://doi.org/10.1145/3617233.3617239"},"language":"en","primary_location":{"id":"doi:10.1145/3617233.3617239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3617233.3617239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04221023/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092391925","display_name":"\u00c9lise Lincker","orcid":"https://orcid.org/0009-0005-1104-1785"},"institutions":[{"id":"https://openalex.org/I4210145724","display_name":"Centre d'Etudes et De Recherche en Informatique et Communications","ror":"https://ror.org/044j5mm75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210145724"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Elise Lincker","raw_affiliation_strings":["Cedric, CNAM, FR"],"raw_orcid":"https://orcid.org/0009-0005-1104-1785","affiliations":[{"raw_affiliation_string":"Cedric, CNAM, FR","institution_ids":["https://openalex.org/I4210145724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037286036","display_name":"Camille Guinaudeau","orcid":"https://orcid.org/0000-0001-7249-8715"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I176979517","display_name":"International Research Center for Japanese Studies","ror":"https://ror.org/04861vz74","country_code":"JP","type":"education","lineage":["https://openalex.org/I1319490839","https://openalex.org/I176979517","https://openalex.org/I4210148627"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152154","display_name":"Japanese-French Laboratory for Informatics","ror":"https://ror.org/007xn7v02","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I203951103","https://openalex.org/I39804081","https://openalex.org/I4387152154","https://openalex.org/I74801974"]}],"countries":["FR","JP"],"is_corresponding":false,"raw_author_name":"Camille Guinaudeau","raw_affiliation_strings":["JFLI, NII, CNRS, JP and Universit\u00e9 Paris-Saclay, France","STL - Sciences et Technologies des Langues - LISN (France)","JFLI - Japanese French Laboratory for Informatics (Japan)"],"raw_orcid":"https://orcid.org/0000-0001-7249-8715","affiliations":[{"raw_affiliation_string":"JFLI, NII, CNRS, JP and Universit\u00e9 Paris-Saclay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"STL - Sciences et Technologies des Langues - LISN (France)","institution_ids":[]},{"raw_affiliation_string":"JFLI - Japanese French Laboratory for Informatics (Japan)","institution_ids":["https://openalex.org/I176979517","https://openalex.org/I4387152154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020294470","display_name":"Olivier Pons","orcid":"https://orcid.org/0000-0001-6423-8630"},"institutions":[{"id":"https://openalex.org/I4210145724","display_name":"Centre d'Etudes et De Recherche en Informatique et Communications","ror":"https://ror.org/044j5mm75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210145724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Pons","raw_affiliation_strings":["Cedric, CNAM, FR"],"raw_orcid":"https://orcid.org/0000-0001-6423-8630","affiliations":[{"raw_affiliation_string":"Cedric, CNAM, FR","institution_ids":["https://openalex.org/I4210145724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038200112","display_name":"J\u00e9r\u00f4me Dupire","orcid":"https://orcid.org/0000-0001-6171-8989"},"institutions":[{"id":"https://openalex.org/I4210145724","display_name":"Centre d'Etudes et De Recherche en Informatique et Communications","ror":"https://ror.org/044j5mm75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210145724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J\u00e9r\u00f4me Dupire","raw_affiliation_strings":["Cedric, CNAM, FR"],"raw_orcid":"https://orcid.org/0000-0001-6171-8989","affiliations":[{"raw_affiliation_string":"Cedric, CNAM, FR","institution_ids":["https://openalex.org/I4210145724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070164335","display_name":"C\u00e9line Hudelot","orcid":"https://orcid.org/0000-0003-3849-4133"},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C\u00e9line Hudelot","raw_affiliation_strings":["MICS, CentraleSup\u00e9lec, FR"],"raw_orcid":"https://orcid.org/0000-0003-3849-4133","affiliations":[{"raw_affiliation_string":"MICS, CentraleSup\u00e9lec, FR","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107443232","display_name":"Vincent Mousseau","orcid":"https://orcid.org/0000-0001-8574-3337"},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Mousseau","raw_affiliation_strings":["MICS, CentraleSup\u00e9lec, FR"],"raw_orcid":"https://orcid.org/0000-0001-8574-3337","affiliations":[{"raw_affiliation_string":"MICS, CentraleSup\u00e9lec, FR","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040528236","display_name":"Isabelle Barbet","orcid":"https://orcid.org/0000-0003-4299-5061"},"institutions":[{"id":"https://openalex.org/I4210145724","display_name":"Centre d'Etudes et De Recherche en Informatique et Communications","ror":"https://ror.org/044j5mm75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210145724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Isabelle Barbet","raw_affiliation_strings":["Cedric, CNAM, FR"],"raw_orcid":"https://orcid.org/0000-0003-4299-5061","affiliations":[{"raw_affiliation_string":"Cedric, CNAM, FR","institution_ids":["https://openalex.org/I4210145724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001460464","display_name":"Caroline Huron","orcid":"https://orcid.org/0000-0002-3890-6110"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Caroline Huron","raw_affiliation_strings":["SEED, INSERM, Universit\u00e9 Paris Cit\u00e9, FR and Learning Planet Institute, France","LPI - Learning Planet Institute [Paris] (8, Rue Charles V, 75004 Paris - France)"],"raw_orcid":"https://orcid.org/0000-0002-3890-6110","affiliations":[{"raw_affiliation_string":"SEED, INSERM, Universit\u00e9 Paris Cit\u00e9, FR and Learning Planet Institute, France","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I4210091437"]},{"raw_affiliation_string":"LPI - Learning Planet Institute [Paris] (8, Rue Charles V, 75004 Paris - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5092391925"],"corresponding_institution_ids":["https://openalex.org/I4210145724"],"apc_list":null,"apc_paid":null,"fwci":0.3363,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65975722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9240999817848206,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9240999817848206,"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":0.7991816401481628},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6944079399108887},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6597334146499634},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.618070662021637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.536992073059082},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5283749103546143},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5181980729103088},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4986274242401123},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4916730523109436},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.44959062337875366},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4114103615283966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991816401481628},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6944079399108887},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6597334146499634},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.618070662021637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536992073059082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5283749103546143},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5181980729103088},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4986274242401123},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4916730523109436},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.44959062337875366},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4114103615283966},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3617233.3617239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3617233.3617239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04221023v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04221023","pdf_url":"https://hal.science/hal-04221023/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"20th International Conference on Content-based Multimedia Indexing (CBMI 2023), Sep 2023, Orl\u00e9ans, France. pp.71 - 78, ⟨10.1145/3617233.3617239⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04221023v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04221023","pdf_url":"https://hal.science/hal-04221023/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"20th International Conference on Content-based Multimedia Indexing (CBMI 2023), Sep 2023, Orl\u00e9ans, France. pp.71 - 78, ⟨10.1145/3617233.3617239⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2657122692","display_name":"Inclusive textbooks","funder_award_id":"ANR-21-CE38-0014","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387161251.pdf","grobid_xml":"https://content.openalex.org/works/W4387161251.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1966382373","https://openalex.org/W2750779823","https://openalex.org/W2962739339","https://openalex.org/W2962772269","https://openalex.org/W2963026768","https://openalex.org/W2963351448","https://openalex.org/W2986154550","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3015267417","https://openalex.org/W3103187652","https://openalex.org/W3104953317","https://openalex.org/W3176664887","https://openalex.org/W3176851559","https://openalex.org/W3200439183","https://openalex.org/W3202536355","https://openalex.org/W3202839357","https://openalex.org/W4226020328","https://openalex.org/W4287378708","https://openalex.org/W4304013646","https://openalex.org/W4313063630","https://openalex.org/W4365799947"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2185469136","https://openalex.org/W2043093291"],"abstract_inverted_index":{"In":[0,25],"order":[1],"to":[2,12,16,32,36,78,111],"foster":[3],"inclusive":[4],"education,":[5],"automatic":[6],"systems":[7],"that":[8],"can":[9],"adapt":[10],"textbooks":[11],"make":[13],"them":[14],"accessible":[15],"children":[17],"with":[18,51],"Developmental":[19],"Coordination":[20],"Disorder":[21],"(DCD)":[22],"are":[23],"necessary.":[24],"this":[26],"context,":[27],"we":[28,67],"propose":[29],"a":[30,43,62],"task":[31],"classify":[33],"exercises":[34],"according":[35],"their":[37],"DCD":[38],"adaptation":[39],"type.":[40],"We":[41],"introduce":[42],"challenging":[44],"exercise":[45],"dataset":[46],"extracted":[47],"from":[48],"French":[49],"textbooks,":[50],"two":[52],"major":[53],"difficulties:":[54],"limited":[55],"and":[56,74,83],"unbalanced,":[57],"noisy":[58],"data.":[59],"To":[60],"set":[61],"baseline":[63],"on":[64],"the":[65,95,98,101,108],"dataset,":[66],"use":[68],"state-of-the-art":[69],"models":[70],"combined":[71],"through":[72],"early":[73],"late":[75],"fusion":[76],"techniques":[77],"take":[79],"advantage":[80],"of":[81,92,100],"text":[82],"vision/layout":[84],"modalities.":[85],"Our":[86],"approach":[87],"achieves":[88],"an":[89],"overall":[90],"accuracy":[91,109],"0.802.":[93],"However,":[94],"experiments":[96],"show":[97],"difficulty":[99],"task,":[102],"especially":[103],"for":[104],"minority":[105],"classes,":[106],"where":[107],"drops":[110],"0.583.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}