{"id":"https://openalex.org/W4402803792","doi":"https://doi.org/10.1109/lsp.2024.3466992","title":"Improving Image-Text Matching by Integrating Word Sense Disambiguation","display_name":"Improving Image-Text Matching by Integrating Word Sense Disambiguation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402803792","doi":"https://doi.org/10.1109/lsp.2024.3466992"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3466992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3466992","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5104546388","display_name":"Xiao Pu","orcid":"https://orcid.org/0009-0005-4173-4996"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Pu","raw_affiliation_strings":["Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","School of Cyber Security and Information Law, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Cyber Security and Information Law, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100727442","display_name":"Ping Yang","orcid":"https://orcid.org/0000-0002-9520-3884"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Yang","raw_affiliation_strings":["Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486583","display_name":"Lin Yuan","orcid":"https://orcid.org/0000-0002-8148-9770"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Yuan","raw_affiliation_strings":["Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","School of Cyber Security and Information Law, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Cyber Security and Information Law, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101785348","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0003-1443-0776"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104546388"],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66089534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"2695","last_page":"2699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9915000200271606,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9915000200271606,"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":0.9832000136375427,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9815000295639038,"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":0.7025706768035889},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.682602047920227},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6538598537445068},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6189165115356445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5985794067382812},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5657596588134766},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48561254143714905},{"id":"https://openalex.org/keywords/semeval","display_name":"SemEval","score":0.4146282374858856},{"id":"https://openalex.org/keywords/image-matching","display_name":"Image matching","score":0.4133617579936981},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35790735483169556},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3519524931907654},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32488077878952026},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2447381317615509},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18453285098075867},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12752562761306763},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.12086296081542969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025706768035889},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.682602047920227},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6538598537445068},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6189165115356445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985794067382812},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5657596588134766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48561254143714905},{"id":"https://openalex.org/C44572571","wikidata":"https://www.wikidata.org/wiki/Q7448970","display_name":"SemEval","level":3,"score":0.4146282374858856},{"id":"https://openalex.org/C2986492983","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image matching","level":3,"score":0.4133617579936981},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35790735483169556},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3519524931907654},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32488077878952026},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2447381317615509},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18453285098075867},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12752562761306763},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.12086296081542969},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3466992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3466992","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3497477163","display_name":null,"funder_award_id":"62201107","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4297946667","display_name":null,"funder_award_id":"U22A2096","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":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2187089797","https://openalex.org/W2737175496","https://openalex.org/W2894627709","https://openalex.org/W2962946486","https://openalex.org/W2988823324","https://openalex.org/W3005971801","https://openalex.org/W3010277541","https://openalex.org/W3035454331","https://openalex.org/W3035521632","https://openalex.org/W3035605030","https://openalex.org/W3101094968","https://openalex.org/W3105858864","https://openalex.org/W3118694826","https://openalex.org/W3155230099","https://openalex.org/W3173220653","https://openalex.org/W3201645700","https://openalex.org/W4206546481","https://openalex.org/W4283812943","https://openalex.org/W4285138127","https://openalex.org/W4304014355","https://openalex.org/W4312761738","https://openalex.org/W4315643106","https://openalex.org/W4321488152","https://openalex.org/W4391744111"],"related_works":["https://openalex.org/W2101293500","https://openalex.org/W2384058382","https://openalex.org/W2000205775","https://openalex.org/W2251529656","https://openalex.org/W2324822715","https://openalex.org/W2330879361","https://openalex.org/W2140343536","https://openalex.org/W2188275805","https://openalex.org/W3184106707","https://openalex.org/W2062413478"],"abstract_inverted_index":{"This":[0],"letter":[1],"presents":[2],"a":[3,40,48,80],"novel":[4],"approach":[5],"to":[6],"enhance":[7],"image-text":[8,44,121],"matching":[9,54,122,133],"by":[10,46],"incorporating":[11],"word":[12,66,97],"sense":[13,100],"disambiguation":[14],"(WSD)":[15],"within":[16],"the":[17,24,31,53,69,92,136],"text":[18],"encoder.":[19],"Our":[20,60,89],"method":[21,111],"explicitly":[22],"models":[23],"senses":[25],"of":[26,71,94,138],"potentially":[27],"ambiguous":[28],"words,":[29],"refining":[30],"semantic":[32],"understanding":[33],"between":[34],"images":[35],"and":[36,76,115,125],"text.":[37],"We":[38,107],"introduce":[39],"sense-aware":[41],"mechanism":[42],"for":[43],"alignment":[45],"integrating":[47],"lightweight":[49],"WSD":[50,61,84,105],"component":[51],"into":[52],"framework,":[55],"optimizing":[56],"both":[57],"tasks":[58],"simultaneously.":[59],"module":[62],"operates":[63],"on":[64,118],"extensive":[65],"contexts,":[67],"leveraging":[68],"power":[70],"graph":[72],"attention":[73],"networks":[74],"(GAT),":[75],"distills":[77],"knowledge":[78],"from":[79,103],"substantially":[81],"larger":[82],"pre-trained":[83],"model":[85],"through":[86],"multi-task":[87],"learning.":[88],"experiments":[90],"demonstrate":[91],"effectiveness":[93],"augmenting":[95],"original":[96],"embeddings":[98],"with":[99],"representations":[101],"derived":[102],"our":[104,110,139],"approach.":[106,141],"systematically":[108],"evaluate":[109],"against":[112],"several":[113],"baselines":[114],"state-of-the-art":[116],"approaches":[117],"two":[119],"widely-used":[120],"benchmarks:":[123],"MS-COCO":[124],"Flickr30K.":[126],"The":[127],"results":[128],"illustrate":[129],"significant":[130],"improvements":[131],"in":[132],"accuracy,":[134],"highlighting":[135],"efficacy":[137],"proposed":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}