{"id":"https://openalex.org/W4293518017","doi":"https://doi.org/10.1109/icme52920.2022.9859972","title":"CAT-MNER: Multimodal Named Entity Recognition with Knowledge-Refined Cross-Modal Attention","display_name":"CAT-MNER: Multimodal Named Entity Recognition with Knowledge-Refined Cross-Modal Attention","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518017","doi":"https://doi.org/10.1109/icme52920.2022.9859972"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859972","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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 IEEE International Conference on Multimedia and Expo (ICME)","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/A5068832926","display_name":"Xuwu Wang","orcid":"https://orcid.org/0000-0003-3363-570X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuwu Wang","raw_affiliation_strings":["School of Computer Science, Fudan University,China","School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091465907","display_name":"Jiabo Ye","orcid":"https://orcid.org/0009-0009-5451-8984"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabo Ye","raw_affiliation_strings":["School of Computer Science, East China Normal University,China","School of Computer Science, East China Normal University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, East China Normal University,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science, East China Normal University, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065529268","display_name":"Zhixu Li","orcid":"https://orcid.org/0000-0003-2355-288X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixu Li","raw_affiliation_strings":["School of Computer Science, Fudan University,China","School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006589025","display_name":"Junfeng Tian","orcid":"https://orcid.org/0000-0003-1759-3255"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Tian","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101656023","display_name":"Yong Jiang","orcid":"https://orcid.org/0000-0003-4482-1559"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Jiang","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079627710","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0002-5762-395X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329246","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0001-6949-3673"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090455375","display_name":"Yanghua Xiao","orcid":"https://orcid.org/0000-0001-8403-9591"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghua Xiao","raw_affiliation_strings":["School of Computer Science, Fudan University,China","School of Computer Science, Fudan University, China","Fudan-Aishu Cognitive Intelligence Joint Research Center, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan-Aishu Cognitive Intelligence Joint Research Center, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980999827384949,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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":0.8302464485168457},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6194968819618225},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6097944378852844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086299419403076},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5998818874359131},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5339540243148804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4788515567779541},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4581555128097534},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4416050612926483},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42227381467819214},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4215548634529114},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4163004159927368},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3940993845462799},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37349236011505127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3463786840438843},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.2374170422554016},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07540267705917358}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302464485168457},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6194968819618225},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6097944378852844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086299419403076},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5998818874359131},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5339540243148804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4788515567779541},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4581555128097534},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4416050612926483},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42227381467819214},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4215548634529114},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4163004159927368},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3940993845462799},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37349236011505127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3463786840438843},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2374170422554016},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07540267705917358},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"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:10.1109/icme52920.2022.9859972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859972","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3277427600","display_name":"\u5f00\u653e\u591a\u6a21\u6001\u73af\u5883\u4e0b\u52a8\u6001\u77e5\u8bc6\u56fe\u8c31\u8865\u5168\u4e0e\u66f4\u65b0\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":24,"referenced_works":["https://openalex.org/W1940872118","https://openalex.org/W2788647998","https://openalex.org/W2789065247","https://openalex.org/W2798298921","https://openalex.org/W2962902328","https://openalex.org/W2962982907","https://openalex.org/W3035448883","https://openalex.org/W3047144459","https://openalex.org/W3092692431","https://openalex.org/W3104415840","https://openalex.org/W3117216739","https://openalex.org/W3127151332","https://openalex.org/W3148395438","https://openalex.org/W3166170409","https://openalex.org/W3170032237","https://openalex.org/W3176858586","https://openalex.org/W3189857991","https://openalex.org/W3195893957","https://openalex.org/W3199057778","https://openalex.org/W4225757376","https://openalex.org/W6748181105","https://openalex.org/W6790153489","https://openalex.org/W6797632053","https://openalex.org/W6799517187"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W3000685722","https://openalex.org/W2520117834","https://openalex.org/W626980589","https://openalex.org/W4313162113","https://openalex.org/W1884363728","https://openalex.org/W3133906981"],"abstract_inverted_index":{"Multimodal":[0],"named":[1,10],"entity":[2,93],"recognition":[3],"(MNER)":[4],"aims":[5],"to":[6,47,54,67,87,124],"detect":[7],"and":[8,23,35,51,74,141],"classify":[9],"entities":[11],"in":[12,138],"multimodal":[13],"scenarios.":[14],"It":[15],"requires":[16],"bridging":[17],"the":[18,30,36,56,69,91,126],"gap":[19],"between":[20],"natural":[21],"language":[22],"visual":[24],"context,":[25],"which":[26,109],"presents":[27],"two-fold":[28],"challenges:":[29],"cross-modal":[31,37,70],"alignment":[32],"is":[33,39,84],"diversified,":[34],"interaction":[38],"sometimes":[40],"implicit.":[41],"Existing":[42],"MNER":[43,107],"methods":[44],"are":[45,52,122],"vulnerable":[46],"some":[48,76],"implicit":[49],"interactions":[50],"prone":[53],"overlook":[55],"involved":[57],"significant":[58,136],"features.":[59,78],"To":[60],"tackle":[61],"this":[62],"problem,":[63],"we":[64],"novelly":[65],"propose":[66,103],"refine":[68],"attention":[71],"by":[72],"identifying":[73],"highlighting":[75],"task-salient":[77],"The":[79],"saliency":[80],"of":[81,128],"each":[82],"feature":[83],"measured":[85],"according":[86],"its":[88],"correlation":[89],"with":[90],"expanded":[92],"label":[94],"words":[95],"derived":[96],"from":[97],"external":[98],"knowledge":[99],"bases.":[100],"We":[101],"further":[102],"an":[104],"end-to-end":[105],"Transformer-based":[106],"framework,":[108],"holds":[110],"neater":[111],"architecture":[112],"yet":[113],"achieves":[114],"better":[115],"performance":[116],"than":[117],"previous":[118],"methods.":[119],"Extensive":[120],"experiments":[121],"conducted":[123],"validate":[125],"merits":[127],"our":[129,132],"method.":[130],"Moreover,":[131],"method":[133],"reveals":[134],"a":[135],"advantage":[137],"data":[139],"efficiency":[140],"generalization":[142],"ability.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}