{"id":"https://openalex.org/W4392909518","doi":"https://doi.org/10.1109/icassp48485.2024.10447455","title":"MTA: A Lightweight Multilingual Text Alignment Model for Cross-Language Visual Word Sense Disambiguation","display_name":"MTA: A Lightweight Multilingual Text Alignment Model for Cross-Language Visual Word Sense Disambiguation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909518","doi":"https://doi.org/10.1109/icassp48485.2024.10447455"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102666376","display_name":"Qihao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qihao Yang","raw_affiliation_strings":["South China Normal University,School of Computer Science,Guangzhou,China","School of Computer Science, South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]},{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639857","display_name":"Xuelin Wang","orcid":"https://orcid.org/0000-0001-5750-6035"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelin Wang","raw_affiliation_strings":["Jinan University,College of Chinese Language and Culture,Guangzhou,China","College of Chinese Language and Culture, Jinan University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Jinan University,College of Chinese Language and Culture,Guangzhou,China","institution_ids":["https://openalex.org/I159948400"]},{"raw_affiliation_string":"College of Chinese Language and Culture, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355406","display_name":"Yong Li","orcid":"https://orcid.org/0000-0002-6521-5921"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["South China Normal University,School of Computer Science,Guangzhou,China","School of Computer Science, South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]},{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060707834","display_name":"Lap\u2013Kei Lee","orcid":"https://orcid.org/0000-0001-9619-6041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lap-Kei Lee","raw_affiliation_strings":["Hong Kong Metropolitan University,School of Science and Technology,Hong Kong","School of Science and Technology, Hong Kong Metropolitan University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong Metropolitan University,School of Science and Technology,Hong Kong","institution_ids":[]},{"raw_affiliation_string":"School of Science and Technology, Hong Kong Metropolitan University, Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482402","display_name":"Fu Lee Wang","orcid":"https://orcid.org/0000-0002-3976-0053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu Lee Wang","raw_affiliation_strings":["Hong Kong Metropolitan University,School of Science and Technology,Hong Kong","School of Science and Technology, Hong Kong Metropolitan University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong Metropolitan University,School of Science and Technology,Hong Kong","institution_ids":[]},{"raw_affiliation_string":"School of Science and Technology, Hong Kong Metropolitan University, Hong Kong","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080646275","display_name":"Tianyong Hao","orcid":"https://orcid.org/0000-0002-9792-3949"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyong Hao","raw_affiliation_strings":["South China Normal University,School of Computer Science,Guangzhou,China","School of Computer Science, South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]},{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102666376"],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":0.5299,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61623547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"12166","last_page":"12170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9901999831199646,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9901999831199646,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9754999876022339,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9746999740600586,"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":0.8060809969902039},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6497127413749695},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.62428879737854},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5531423091888428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5157773494720459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32944145798683167},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2898922562599182},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.054413408041000366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060809969902039},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6497127413749695},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.62428879737854},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5531423091888428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157773494720459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32944145798683167},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2898922562599182},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.054413408041000366},{"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:10.1109/icassp48485.2024.10447455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2102381086","https://openalex.org/W2131540451","https://openalex.org/W2138621090","https://openalex.org/W2436001372","https://openalex.org/W2970641574","https://openalex.org/W3034782826","https://openalex.org/W3035524453","https://openalex.org/W3094502228","https://openalex.org/W3184735396","https://openalex.org/W3190186724","https://openalex.org/W3193147816","https://openalex.org/W4285537247","https://openalex.org/W4295168876","https://openalex.org/W4385570655","https://openalex.org/W4385572031","https://openalex.org/W6691470440","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6811013733"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2296205523","https://openalex.org/W2325435433","https://openalex.org/W2188275805","https://openalex.org/W2498383244","https://openalex.org/W2259621217","https://openalex.org/W2904069821","https://openalex.org/W2771050216","https://openalex.org/W2613956519","https://openalex.org/W3087778885"],"abstract_inverted_index":{"Visual":[0],"Word":[1],"Sense":[2],"Disambiguation":[3],"(Visual-WSD),":[4],"as":[5],"a":[6,13,57,87,105,113],"sub-task":[7],"of":[8,16],"fine-grained":[9,68,107],"image-text":[10,108],"retrieval,":[11],"requires":[12],"high":[14],"level":[15],"language-vision":[17],"understanding":[18],"to":[19,66,71,80,119],"capture":[20],"and":[21,28,75,89,112,142,149,161],"exploit":[22],"the":[23,32,42,98,121,126,138],"nuanced":[24],"relationships":[25],"between":[26],"text":[27,159],"visual":[29,99],"features.":[30,84],"However,":[31],"cross-linguistic":[33],"background":[34],"only":[35],"with":[36,64,156],"limited":[37],"contextual":[38],"information":[39],"is":[40,86,110,117],"considered":[41],"most":[43],"significant":[44],"challenges":[45],"for":[46,60],"this":[47,50],"task.":[48],"In":[49],"paper,":[51],"we":[52],"propose":[53],"MTA,":[54],"which":[55],"employs":[56],"new":[58],"approach":[59],"multilingual":[61],"contrastive":[62],"learning":[63],"self-distillation":[65],"align":[67,76],"textual":[69,78,82],"features":[70,74,79],"fixed":[72],"vision":[73],"non-English":[77],"English":[81],"momentum":[83],"It":[85],"lightweight":[88],"end-to-end":[90],"model":[91],"since":[92],"it":[93],"does":[94],"not":[95],"require":[96],"updating":[97],"encoder":[100],"or":[101],"translation":[102],"operations.":[103],"Furthermore,":[104],"trilingual":[106],"dataset":[109],"developed":[111],"ChatGPT":[114],"API":[115],"module":[116],"integrated":[118],"enrich":[120],"word":[122],"senses":[123],"effectively":[124],"during":[125],"testing":[127],"phase.":[128],"Extensive":[129],"experiments":[130],"show":[131],"that":[132],"MTA":[133],"achieves":[134],"state-of-the-art":[135],"results":[136],"on":[137],"benchmark":[139],"English,":[140],"Farsi,":[141],"Italian":[143],"datasets":[144],"in":[145,158],"SemEval-2023":[146],"Task":[147],"1":[148],"exhibits":[150],"impressive":[151],"generalization":[152],"abilities":[153],"when":[154],"dealing":[155],"variations":[157],"length":[160],"language.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}