{"id":"https://openalex.org/W4403780570","doi":"https://doi.org/10.1145/3664647.3681598","title":"Generative Multimodal Data Augmentation for Low-Resource Multimodal Named Entity Recognition","display_name":"Generative Multimodal Data Augmentation for Low-Resource Multimodal Named Entity Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780570","doi":"https://doi.org/10.1145/3664647.3681598"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681598","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5037132022","display_name":"Ziyan Li","orcid":"https://orcid.org/0009-0006-3034-7998"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-3034-7998","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084990301","display_name":"Jianfei Yu","orcid":"https://orcid.org/0000-0001-8380-0609"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfei Yu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8380-0609","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064179313","display_name":"Jia Yang","orcid":"https://orcid.org/0009-0008-2903-9589"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-2903-9589","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078565848","display_name":"Wenya Wang","orcid":"https://orcid.org/0000-0001-5612-7818"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenya Wang","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5612-7818","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022461927","display_name":"Li Yang","orcid":"https://orcid.org/0000-0001-7160-9620"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Li Yang","raw_affiliation_strings":["Wee Kim Wee School of Communication and Information, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7160-9620","affiliations":[{"raw_affiliation_string":"Wee Kim Wee School of Communication and Information, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035534911","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0002-0621-1058"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0621-1058","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1383,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89390546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7336","last_page":"7345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9977999925613403,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9797999858856201,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7757358551025391},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6206741333007812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5153777003288269},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.43777093291282654},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38416463136672974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37342900037765503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34828096628189087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757358551025391},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6206741333007812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5153777003288269},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43777093291282654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38416463136672974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37342900037765503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34828096628189087},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681598","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2788647998","https://openalex.org/W2798298921","https://openalex.org/W3035448883","https://openalex.org/W3092692431","https://openalex.org/W3148395438","https://openalex.org/W3176659256","https://openalex.org/W3176858586","https://openalex.org/W3207972321","https://openalex.org/W4212998232","https://openalex.org/W4229024390","https://openalex.org/W4283075937","https://openalex.org/W4293518017","https://openalex.org/W4304015092","https://openalex.org/W4304091743","https://openalex.org/W4312933868","https://openalex.org/W4385571080","https://openalex.org/W4386076522","https://openalex.org/W4387848810","https://openalex.org/W4387968507","https://openalex.org/W4387969106","https://openalex.org/W4387969285","https://openalex.org/W4389519297","https://openalex.org/W4389523688"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W4383031710","https://openalex.org/W3211753092","https://openalex.org/W2386000789"],"abstract_inverted_index":{"As":[0],"an":[1],"important":[2],"task":[3],"in":[4,24,33,173],"multimodal":[5],"information":[6],"extraction,":[7],"Multimodal":[8,72,83,87,107],"Named":[9],"Entity":[10],"Recognition":[11],"(MNER)":[12],"has":[13],"recently":[14],"attracted":[15],"considerable":[16],"attention.":[17],"One":[18],"key":[19],"challenge":[20],"of":[21,27,154,164,171],"MNER":[22,172],"lies":[23],"the":[25,46,114,135,152,155,162],"lack":[26],"sufficient":[28],"fine-grained":[29],"annotated":[30,95],"data,":[31],"especially":[32],"low-resource":[34,177,180],"scenarios.":[35],"Although":[36],"data":[37],"augmentation":[38],"is":[39,50],"a":[40,69,98,105,119,129],"widely":[41],"used":[42],"technique":[43],"to":[44,52,112,133,142],"tackle":[45],"above":[47],"issue,":[48],"it":[49],"challenging":[51],"simultaneously":[53],"generate":[54,113,134],"synthetic":[55,136],"text-image":[56],"pairs":[57],"and":[58,86,102,122,176,182],"their":[59],"corresponding":[60],"high-quality":[61],"entity":[62],"annotations.":[63],"In":[64],"this":[65],"work,":[66],"we":[67,91],"propose":[68],"novel":[70],"Generative":[71],"Data":[73],"Augmentation":[74],"(GMDA)":[75],"framework":[76],"for":[77,168],"MNER,":[78],"which":[79,159],"contains":[80],"two":[81,169],"stages:":[82],"Text":[84],"Generation":[85],"Image":[88],"Generation.":[89],"Specifically,":[90],"first":[92],"transform":[93],"each":[94],"sentence":[96],"into":[97],"linearized":[99],"labeled":[100,115],"sequence,":[101],"then":[103],"train":[104],"Label-aware":[106],"Large":[108],"Language":[109],"Model":[110],"(LMLLM)":[111],"sequence":[116],"based":[117],"on":[118,147],"label-aware":[120],"prompt":[121],"its":[123],"associated":[124],"image.":[125],"We":[126],"further":[127],"employ":[128],"Stable":[130],"Diffusion":[131],"model":[132],"images":[137],"that":[138],"are":[139,185],"semantically":[140],"related":[141],"these":[143],"sentences.":[144],"Experimental":[145],"results":[146],"three":[148],"benchmark":[149],"datasets":[150],"demonstrate":[151],"effectiveness":[153],"proposed":[156],"GMDA":[157],"framework,":[158],"consistently":[160],"boosts":[161],"performance":[163],"several":[165],"competitive":[166],"methods":[167],"subtasks":[170],"both":[174],"full-supervision":[175],"settings.":[178],"The":[179],"dataset":[181],"source":[183],"code":[184],"released":[186],"at":[187],"https://github.com/NUSTM/GMDA.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}