{"id":"https://openalex.org/W4407466176","doi":"https://doi.org/10.1109/iccvit63928.2024.10872544","title":"Enhancing Multimodal Named Entity Recognition via Entity Span Detection and Graph Networks","display_name":"Enhancing Multimodal Named Entity Recognition via Entity Span Detection and Graph Networks","publication_year":2024,"publication_date":"2024-11-24","ids":{"openalex":"https://openalex.org/W4407466176","doi":"https://doi.org/10.1109/iccvit63928.2024.10872544"},"language":"en","primary_location":{"id":"doi:10.1109/iccvit63928.2024.10872544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvit63928.2024.10872544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Computer, Vision and Intelligent Technology (ICCVIT)","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/A5104955672","display_name":"Yupeng Ma","orcid":"https://orcid.org/0009-0005-7010-4272"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yupeng Ma","raw_affiliation_strings":["Wuhan Institute of Technology,School of Computer Science and Engineering,Wuhan,China,430205"],"affiliations":[{"raw_affiliation_string":"Wuhan Institute of Technology,School of Computer Science and Engineering,Wuhan,China,430205","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025505902","display_name":"Ming Zhang","orcid":"https://orcid.org/0000-0003-4145-5389"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhang","raw_affiliation_strings":["Wuhan Institute of Technology,School of Computer Science and Engineering,Wuhan,China,430205"],"affiliations":[{"raw_affiliation_string":"Wuhan Institute of Technology,School of Computer Science and Engineering,Wuhan,China,430205","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114888785","display_name":"Zhiqiang Li","orcid":"https://orcid.org/0000-0001-6007-873X"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Li","raw_affiliation_strings":["Wuhan Institute of Technology,School of Computer Science and Engineering,Wuhan,China,430205"],"affiliations":[{"raw_affiliation_string":"Wuhan Institute of Technology,School of Computer Science and Engineering,Wuhan,China,430205","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103851145","display_name":"Shihong Wu","orcid":"https://orcid.org/0000-0002-8684-8330"},"institutions":[{"id":"https://openalex.org/I4210093776","display_name":"DHC Software (China)","ror":"https://ror.org/00kn8e190","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093776"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihong Wu","raw_affiliation_strings":["Yuanguang Software Co., Ltd,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Yuanguang Software Co., Ltd,Wuhan,China","institution_ids":["https://openalex.org/I4210093776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104955672"],"corresponding_institution_ids":["https://openalex.org/I91125648"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25058867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9919000267982483,"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/T11719","display_name":"Data Quality and Management","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7858242392539978},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6772703528404236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4465555250644684},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35978516936302185},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.11007413268089294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08993753790855408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858242392539978},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6772703528404236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4465555250644684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35978516936302185},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.11007413268089294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08993753790855408},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvit63928.2024.10872544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvit63928.2024.10872544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Computer, Vision and Intelligent Technology (ICCVIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2144578941","https://openalex.org/W2962902328","https://openalex.org/W3035448883","https://openalex.org/W3096266342","https://openalex.org/W3176858586","https://openalex.org/W4212998232","https://openalex.org/W4311167584","https://openalex.org/W4378981728"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3017222382","https://openalex.org/W3128216712","https://openalex.org/W3204019825","https://openalex.org/W3136915866","https://openalex.org/W4390279576","https://openalex.org/W2886890203","https://openalex.org/W4313535650","https://openalex.org/W2287770975"],"abstract_inverted_index":{"Multimodal":[0],"Named":[1],"Entity":[2],"Recognition":[3],"(MNER)":[4],"focuses":[5],"on":[6,54,138],"utilizing":[7],"multiple":[8],"modalities,":[9,43],"including":[10],"text":[11,108],"and":[12,40,44,63,86,94,109,119,144],"images,":[13,110],"to":[14,33,47,68,97,106,129],"recognize":[15],"specific":[16],"types":[17],"of":[18,149],"entities":[19],"within":[20],"text.":[21],"Despite":[22],"recent":[23],"advancements,":[24],"existing":[25],"methods":[26],"still":[27],"face":[28],"several":[29],"challenges:":[30],"(1)":[31],"How":[32],"create":[34],"a":[35,74,103,112,125],"unified":[36,56],"representation":[37,57],"that":[38],"connects":[39],"integrates":[41],"different":[42,51],"(2)":[45],"how":[46],"better":[48],"interact":[49],"between":[50],"modalities":[52],"based":[53],"the":[55,131,139,147],"while":[58],"fully":[59],"capturing":[60],"both":[61],"intra-modal":[62],"inter-modal":[64],"information.":[65],"In":[66],"order":[67],"address":[69],"these":[70],"challenges,":[71],"we":[72,101],"design":[73],"new":[75],"model,":[76],"enhancing":[77],"multimodal":[78,117],"named":[79],"entity":[80,83,92,121],"recognition":[81,93],"via":[82],"span":[84,122],"detection":[85,123],"graph":[87,95,113,126],"networks":[88,96],"(GENT-Net),":[89],"which":[90],"leverages":[91],"enhance":[98],"MNER.":[99],"Specifically,":[100],"employ":[102],"graph-based":[104],"structure":[105],"model":[107],"use":[111],"attention":[114],"network":[115,128],"for":[116],"fusion,":[118],"introduce":[120],"using":[124],"convolutional":[127],"assist":[130],"MNER":[132],"task.":[133],"We":[134],"perform":[135],"comprehensive":[136],"experiments":[137],"publicly":[140],"available":[141],"datasets,":[142],"Twitter2015":[143],"Twitter2017,":[145],"showcasing":[146],"effectiveness":[148],"our":[150],"proposed":[151],"approach.":[152]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}