{"id":"https://openalex.org/W4408399657","doi":"https://doi.org/10.1109/mmul.2025.3550451","title":"MangaUB: A Manga Understanding Benchmark for Large Multimodal Models","display_name":"MangaUB: A Manga Understanding Benchmark for Large Multimodal Models","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408399657","doi":"https://doi.org/10.1109/mmul.2025.3550451"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2025.3550451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3550451","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-article"},"type":"article","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/A5087680844","display_name":"Hikaru Ikuta","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hikaru Ikuta","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0001-6372-2444","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008368006","display_name":"Leslie W\u00f6hler","orcid":"https://orcid.org/0000-0002-8771-916X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Leslie W\u00f6hler","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8771-916X","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069982192","display_name":"Kiyoharu Aizawa","orcid":"https://orcid.org/0000-0003-2146-6275"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyoharu Aizawa","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2146-6275","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":4.4706,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93417984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"32","issue":"2","first_page":"33","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9490000009536743,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9490000009536743,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9455999732017517,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9350000023841858,"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":0.8267254829406738},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6901959776878357},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4501117765903473},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42625513672828674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42217424511909485},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3904581665992737},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.343461275100708},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3272625207901001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267254829406738},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6901959776878357},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4501117765903473},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42625513672828674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42217424511909485},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3904581665992737},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.343461275100708},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3272625207901001},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2025.3550451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3550451","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2192954843","https://openalex.org/W2552837936","https://openalex.org/W2553305164","https://openalex.org/W2780254190","https://openalex.org/W2964280909","https://openalex.org/W3017083351","https://openalex.org/W3120043490","https://openalex.org/W4312817644","https://openalex.org/W4385819801","https://openalex.org/W4388823714","https://openalex.org/W4401024025","https://openalex.org/W4402423425","https://openalex.org/W4402727764","https://openalex.org/W4402727809","https://openalex.org/W4403081466","https://openalex.org/W4406844855"],"related_works":["https://openalex.org/W2035104213","https://openalex.org/W2240967841","https://openalex.org/W2791686160","https://openalex.org/W1513257435","https://openalex.org/W2289840258","https://openalex.org/W2503352526","https://openalex.org/W2968405290","https://openalex.org/W2960696728","https://openalex.org/W2114040463","https://openalex.org/W2053633997"],"abstract_inverted_index":{"Manga":[0],"is":[1,80,137],"a":[2,72,92,104,108],"popular":[3],"medium":[4],"that":[5],"combines":[6],"stylized":[7],"drawings":[8],"and":[9,61,69,86,131],"text":[10],"to":[11,25,82],"convey":[12],"stories.":[13],"As":[14],"manga":[15,58,74,114,146],"panels":[16,136],"differ":[17],"from":[18],"natural":[19],"images,":[20],"computational":[21],"systems":[22],"traditionally":[23],"had":[24],"be":[26],"designed":[27,81],"specifically":[28],"for":[29,43,57,64,77,103,113,145],"manga.":[30],"Recently,":[31],"the":[32,52,84,122,129],"adaptive":[33],"nature":[34],"of":[35,51,55,88,107,124],"modern":[36],"large":[37],"multimodal":[38],"models":[39],"(LMMs)":[40],"shows":[41],"possibilities":[42],"more":[44],"general":[45],"approaches.":[46],"To":[47],"provide":[48],"an":[49],"analysis":[50,106],"current":[53],"capability":[54],"LMMs":[56,144],"understanding":[59,75,87,128],"tasks":[60],"identifying":[62],"areas":[63],"their":[65],"improvement,":[66],"we":[67],"design":[68],"evaluate":[70],"MangaUB,":[71],"novel":[73],"benchmark":[76],"LMMs.":[78],"MangaUB":[79],"assess":[83],"recognition":[85,123],"content":[89],"shown":[90],"in":[91],"single":[93],"panel":[94],"as":[95,97],"well":[96],"conveyed":[98,133],"across":[99,134],"multiple":[100,135],"panels,":[101],"allowing":[102],"fine-grained":[105],"model\u2019s":[109],"various":[110],"capabilities":[111],"required":[112],"understanding.":[115,147],"Our":[116],"results":[117],"show":[118],"strong":[119],"performance":[120],"on":[121],"image":[125],"content,":[126],"while":[127],"emotion":[130],"information":[132],"still":[138],"challenging,":[139],"highlighting":[140],"future":[141],"work":[142],"toward":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}