{"id":"https://openalex.org/W4409295523","doi":"https://doi.org/10.32604/cmc.2025.061902","title":"Multi-Modal Named Entity Recognition with Auxiliary Visual Knowledge and Word-Level Fusion","display_name":"Multi-Modal Named Entity Recognition with Auxiliary Visual Knowledge and Word-Level Fusion","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409295523","doi":"https://doi.org/10.32604/cmc.2025.061902"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.061902","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.061902","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.061902","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072416074","display_name":"Huansha Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Huansha Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050386496","display_name":"Ruiyang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiyang Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041609414","display_name":"Qinrang Liu","orcid":"https://orcid.org/0000-0002-9553-2282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinrang Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008174737","display_name":"Xinghao Wang","orcid":"https://orcid.org/0000-0001-5751-7383"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinghao Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072416074"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03456535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"83","issue":"3","first_page":"5747","last_page":"5760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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":0.9894999861717224,"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/natural-language-processing","display_name":"Natural language processing","score":0.6489322781562805},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6390372514724731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6354389190673828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5744243860244751},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.44293251633644104},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4310365915298462},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35819411277770996},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3519400954246521}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6489322781562805},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6390372514724731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6354389190673828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5744243860244751},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.44293251633644104},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4310365915298462},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35819411277770996},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3519400954246521},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.061902","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.061902","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.061902","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.061902","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4307855645","https://openalex.org/W4391691787"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W1569283511","https://openalex.org/W2099421762","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2530546662","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Multi-modal":[0,91],"Named":[1],"Entity":[2],"Recognition":[3],"(MNER)":[4],"aims":[5,87],"to":[6,88,127,135,166],"better":[7],"identify":[8],"meaningful":[9],"textual":[10,54],"entities":[11],"by":[12,139,151],"integrating":[13],"information":[14],"from":[15,35,107,133,176],"images.":[16],"Previous":[17],"work":[18],"has":[19],"focused":[20],"on":[21,192],"extracting":[22],"visual":[23,52,81],"semantics":[24],"at":[25],"a":[26,73,161],"fine-grained":[27],"level,":[28],"or":[29,38,187],"obtaining":[30],"entity":[31,76,137],"related":[32],"external":[33,129,170],"knowledge":[34,36,82,99,106,121,130,171],"bases":[37],"Large":[39,92],"Language":[40,93],"Models":[41],"(LLMs).":[42],"However,":[43],"these":[44],"approaches":[45],"ignore":[46],"the":[47,90,108,125,152,168,177,189,193,200],"poor":[48],"semantic":[49],"correlation":[50],"between":[51],"and":[53,59,83,113,147],"modalities":[55],"in":[56],"MNER":[57,196],"datasets":[58],"do":[60],"not":[61],"explore":[62],"different":[63],"multi-modal":[64,74,163],"fusion":[65,164],"approaches.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,117,159],"present":[71],"MMAVK,":[72],"named":[75],"recognition":[77,138,146],"model":[78],"with":[79,172],"auxiliary":[80,105,120],"word-level":[84,162],"fusion,":[85],"which":[86,123],"leverage":[89],"Model":[94],"(MLLM)":[95],"as":[96],"an":[97],"implicit":[98],"base.":[100],"It":[101],"also":[102],"extracts":[103],"vision-based":[104,119],"image":[109],"for":[110],"more":[111],"accurate":[112],"effective":[114],"recognition.":[115],"Specifically,":[116],"propose":[118],"generation,":[122],"guides":[124],"MLLM":[126],"extract":[128],"exclusively":[131],"derived":[132],"images":[134],"aid":[136],"designing":[140],"target-specific":[141],"prompts,":[142],"thus":[143],"avoiding":[144],"redundant":[145],"cognitive":[148],"confusion":[149],"caused":[150],"simultaneous":[153],"processing":[154],"of":[155],"image-text":[156],"pairs.":[157],"Furthermore,":[158],"employ":[160],"mechanism":[165],"fuse":[167],"extracted":[169],"each":[173],"word-embedding":[174],"embedded":[175],"transformer-based":[178],"encoder.":[179],"Extensive":[180],"experimental":[181],"results":[182],"demonstrate":[183],"that":[184],"MMAVK":[185],"outperforms":[186],"equals":[188],"state-of-the-art":[190],"methods":[191],"two":[194],"classical":[195],"datasets,":[197],"even":[198],"when":[199],"large":[201],"models":[202],"employed":[203],"have":[204],"significantly":[205],"fewer":[206],"parameters":[207],"than":[208],"other":[209],"baselines.":[210]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}