{"id":"https://openalex.org/W4413182128","doi":"https://doi.org/10.1142/s0218001425500272","title":"Multimodal Item Retrieval and Matching Algorithm Based on Visual-Semantic Joint Embedding","display_name":"Multimodal Item Retrieval and Matching Algorithm Based on Visual-Semantic Joint Embedding","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W4413182128","doi":"https://doi.org/10.1142/s0218001425500272"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001425500272","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425500272","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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/A5108092771","display_name":"Xu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Xu","raw_affiliation_strings":["Business School, Suzhou University, Suzhou 234000, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Business School, Suzhou University, Suzhou 234000, Anhui, China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078654104","display_name":"Jiaojiao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaojiao Sun","raw_affiliation_strings":["Business School, Suzhou University, Suzhou 234000, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Business School, Suzhou University, Suzhou 234000, Anhui, China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28527152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"15","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.8888999819755554,"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"}},"topics":[{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.8888999819755554,"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/computer-science","display_name":"Computer science","score":0.7338900566101074},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6781768798828125},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6301525235176086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6258193850517273},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5399759411811829},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5148683786392212},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3523339033126831},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.348850280046463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3373766541481018},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16368749737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7338900566101074},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6781768798828125},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6301525235176086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258193850517273},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5399759411811829},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5148683786392212},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3523339033126831},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.348850280046463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3373766541481018},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16368749737739563},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001425500272","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425500272","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2943107462","https://openalex.org/W2946485437","https://openalex.org/W2950864153","https://openalex.org/W2952985824","https://openalex.org/W2954672622","https://openalex.org/W2971765950","https://openalex.org/W2991118492","https://openalex.org/W3023371261","https://openalex.org/W3034202663","https://openalex.org/W3094286186","https://openalex.org/W3109684201","https://openalex.org/W3163140850","https://openalex.org/W3175888430","https://openalex.org/W3206001941","https://openalex.org/W3213100861"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,12,21,26,31,45,53,173],"multimodal":[4],"item":[5],"retrieval":[6,81,181],"and":[7,30,62,69,75,91,96,99,110,118,124,139,155,164,176,193],"matching":[8],"framework":[9],"based":[10],"on":[11,73,94,102],"visual-semantic":[13],"joint":[14],"embedding":[15,47],"architecture.":[16],"The":[17,112],"proposed":[18,170],"model":[19,113],"leverages":[20],"dual-encoder":[22],"structure":[23],"\u2014":[24,35],"comprising":[25],"ResNet-50":[27],"visual":[28],"encoder":[29,34],"DistilBERT":[32],"text":[33],"followed":[36],"by":[37,52],"modality-specific":[38],"projection":[39,137],"heads":[40],"to":[41],"map":[42],"features":[43],"into":[44],"shared":[46],"space.":[48],"Training":[49,153],"is":[50],"driven":[51],"symmetric":[54],"contrastive":[55,135],"loss":[56,154],"enhanced":[57],"with":[58,183],"hard":[59],"negative":[60],"mining":[61],"semantic":[63,140],"regularization,":[64,141],"fostering":[65],"strong":[66,184],"intra-class":[67],"cohesion":[68],"inter-class":[70],"separability.":[71],"Evaluations":[72],"MS-COCO":[74],"Flickr30K":[76],"demonstrate":[77],"the":[78,132,161,169],"model\u2019s":[79,162],"superior":[80],"performance.":[82],"Specifically,":[83],"it":[84],"achieves":[85],"Recall@1":[86],"scores":[87],"of":[88,134],"80.5":[89],"(I2T)":[90,98],"68.4":[92],"(T2I)":[93,101],"MS-COCO,":[95],"69.8":[97],"55.7":[100],"Flickr30K,":[103],"outperforming":[104],"baselines":[105],"such":[106],"as":[107],"UNITER,":[108],"CLIP,":[109],"SCAN.":[111],"also":[114],"shows":[115],"high":[116],"stability":[117],"efficiency,":[119],"converging":[120],"faster":[121],"than":[122],"alternatives":[123],"requiring":[125],"less":[126],"training":[127],"time.":[128],"Ablation":[129],"studies":[130],"confirm":[131],"effectiveness":[133],"loss,":[136],"heads,":[138],"while":[142],"sensitivity":[143],"analysis":[144],"identifies":[145],"an":[146],"optimal":[147],"temperature":[148],"parameter":[149],"([Formula:":[150],"see":[151],"text]).":[152],"ranking":[156],"distribution":[157],"analyses":[158],"further":[159],"validate":[160],"robustness":[163],"fine-grained":[165,192],"alignment":[166],"capabilities.":[167],"Overall,":[168],"method":[171],"offers":[172],"scalable,":[174],"interpretable,":[175],"efficient":[177],"solution":[178],"for":[179,186],"cross-modal":[180],"tasks,":[182],"potential":[185],"deployment":[187],"in":[188],"real-world":[189],"applications":[190],"involving":[191],"domain-specific":[194],"queries.":[195]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}