{"id":"https://openalex.org/W4403587458","doi":"https://doi.org/10.1016/j.knosys.2024.112641","title":"Cross-modal recipe retrieval based on unified text encoder with fine-grained contrastive learning","display_name":"Cross-modal recipe retrieval based on unified text encoder with fine-grained contrastive learning","publication_year":2024,"publication_date":"2024-10-21","ids":{"openalex":"https://openalex.org/W4403587458","doi":"https://doi.org/10.1016/j.knosys.2024.112641"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2024.112641","doi":"https://doi.org/10.1016/j.knosys.2024.112641","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2024.112641","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-b","fnege-4","jufo-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.knosys.2024.112641","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bolin Zhang","orcid":"https://orcid.org/0009-0006-1728-9682","observed_orcids":["https://orcid.org/0009-0006-1728-9682"]},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolin Zhang","raw_affiliation_strings":["Faculty of Electronic Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0006-1728-9682","affiliations":[{"raw_affiliation_string":"Faculty of Electronic Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064740974","display_name":"Haruya Kyutoku","orcid":"https://orcid.org/0000-0002-4042-2836","observed_orcids":["https://orcid.org/0000-0002-4042-2836"]},"institutions":[{"id":"https://openalex.org/I88019430","display_name":"Aichi University of Technology","ror":"https://ror.org/01wx88t91","country_code":"JP","type":"education","lineage":["https://openalex.org/I88019430"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruya Kyutoku","raw_affiliation_strings":["Faculty of Engineering, Aichi University of Technology, Gamagori, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Aichi University of Technology, Gamagori, Aichi, Japan","institution_ids":["https://openalex.org/I88019430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058196829","display_name":"Keisuke Doman","orcid":"https://orcid.org/0000-0001-6040-4988","observed_orcids":["https://orcid.org/0000-0001-6040-4988"]},"institutions":[{"id":"https://openalex.org/I98940699","display_name":"Chukyo University","ror":"https://ror.org/04ajrmg05","country_code":"JP","type":"education","lineage":["https://openalex.org/I98940699"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Doman","raw_affiliation_strings":["School of Engineering, Chukyo University, Toyota, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Chukyo University, Toyota, Aichi, Japan","institution_ids":["https://openalex.org/I98940699"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047823141","display_name":"Takahiro Komamizu","orcid":"https://orcid.org/0000-0002-3041-4330","observed_orcids":["https://orcid.org/0000-0002-3041-4330"]},"institutions":[{"id":"https://openalex.org/I4405286953","display_name":"Center for Artificial Intelligence, Mathematical and Data Science, Nagoya University","ror":"https://ror.org/03njf3f81","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4405286953","https://openalex.org/I60134161"]},{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Komamizu","raw_affiliation_strings":["Mathematical and Data Science Center, Nagoya University, Nagoya, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematical and Data Science Center, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I4405286953","https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034941095","display_name":"Ichiro Ide","orcid":"https://orcid.org/0000-0003-3942-9296","observed_orcids":["https://orcid.org/0000-0003-3942-9296"]},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ichiro Ide","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3942-9296","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004828717","display_name":"Jiangbo Qian","orcid":"https://orcid.org/0000-0003-4245-3246","observed_orcids":["https://orcid.org/0000-0003-4245-3246"]},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangbo Qian","raw_affiliation_strings":["Faculty of Electronic Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronic Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034941095"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":{"value":3250,"currency":"USD","value_usd":3250},"apc_paid":{"value":3250,"currency":"USD","value_usd":3250},"fwci":0.6511,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65053385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"305","issue":null,"first_page":"112641","last_page":"112641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9907000064849854,"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":0.9907000064849854,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.006099999882280827,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0006000000284984708,"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/image-text-alignment","display_name":"image-text alignment","score":0.49399998784065247},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.5329999923706055},{"id":"https://openalex.org/keywords/transformer-encoder","display_name":"Transformer encoder","score":0.49799999594688416}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.9486836194992065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123193740844727},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6026365160942078},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5578076839447021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4870951175689697},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4594273567199707},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40686658024787903},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11229011416435242},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.knosys.2024.112641","doi":"https://doi.org/10.1016/j.knosys.2024.112641","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2024.112641","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-b","fnege-4","jufo-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.knosys.2024.112641","doi":"https://doi.org/10.1016/j.knosys.2024.112641","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2024.112641","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-b","fnege-4","jufo-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8546563133","display_name":"New Technologies for Active Dietary Management Using Deep Learning","funder_award_id":"22H00548","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W2064675550","https://openalex.org/W2108384452","https://openalex.org/W2123649031","https://openalex.org/W2138621090","https://openalex.org/W2163605009","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2259472270","https://openalex.org/W2549139847","https://openalex.org/W2594259972","https://openalex.org/W2626778328","https://openalex.org/W2737041163","https://openalex.org/W2798991696","https://openalex.org/W2888676701","https://openalex.org/W2897152025","https://openalex.org/W2948037078","https://openalex.org/W2963055199","https://openalex.org/W2963997278","https://openalex.org/W2971155163","https://openalex.org/W2975357369","https://openalex.org/W2990135557","https://openalex.org/W2994536315","https://openalex.org/W2997298113","https://openalex.org/W2998388430","https://openalex.org/W3033103428","https://openalex.org/W3035032757","https://openalex.org/W3035524453","https://openalex.org/W3035635319","https://openalex.org/W3137684688","https://openalex.org/W3153694119","https://openalex.org/W3155721152","https://openalex.org/W3163303044","https://openalex.org/W3164325351","https://openalex.org/W3186223381","https://openalex.org/W3189092450","https://openalex.org/W3197950609","https://openalex.org/W3204119129","https://openalex.org/W3208601917","https://openalex.org/W3209420799","https://openalex.org/W4205111180","https://openalex.org/W4282913028","https://openalex.org/W4283070887","https://openalex.org/W4292787334","https://openalex.org/W4297808394","https://openalex.org/W4304080716","https://openalex.org/W4304083183","https://openalex.org/W4304142044","https://openalex.org/W4312325116","https://openalex.org/W4377023114","https://openalex.org/W4386711666","https://openalex.org/W4388185880","https://openalex.org/W4390523405","https://openalex.org/W4394659899","https://openalex.org/W4398192374","https://openalex.org/W4399206217","https://openalex.org/W4405863024","https://openalex.org/W6601630192","https://openalex.org/W6603663020"],"related_works":["https://openalex.org/W4407282394","https://openalex.org/W7161416548","https://openalex.org/W3128302566","https://openalex.org/W3137684688","https://openalex.org/W4404442832","https://openalex.org/W2990135557","https://openalex.org/W4407693133","https://openalex.org/W4390523405","https://openalex.org/W4393972806","https://openalex.org/W4403335218"],"abstract_inverted_index":{"Cross-modal":[0],"recipe":[1,24,38,70,80,199],"retrieval":[2],"is":[3],"vital":[4],"for":[5],"transforming":[6],"visual":[7],"food":[8],"cues":[9],"into":[10],"actionable":[11],"cooking":[12],"guidance,":[13],"making":[14],"culinary":[15],"creativity":[16],"more":[17],"accessible.":[18],"Existing":[19],"methods":[20,54],"separately":[21],"encode":[22],"the":[23,68,72,76,83,125,146,152,163,178,183,196,202,212,218],"Title,":[25,205],"Ingredient,":[26,206],"and":[27,40,71,82,127,162,181,201,207],"Instruction":[28,128,208],"using":[29],"different":[30],"text":[31],"encoders,":[32],"then":[33],"aggregate":[34],"them":[35],"to":[36,109,150,194,223],"obtain":[37,151],"feature,":[39],"finally":[41],"match":[42],"it":[43,139,156],"with":[44,101,145],"encoded":[45],"image":[46,73,203],"feature":[47,184],"in":[48,86,117],"a":[49,111,135,167],"joint":[50],"embedding":[51],"space.":[52],"These":[53],"perform":[55],"well":[56],"but":[57,74,113],"require":[58],"significant":[59],"computational":[60],"cost.":[61],"In":[62],"addition,":[63],"they":[64],"only":[65],"consider":[66],"matching":[67],"entire":[69],"ignore":[75],"fine-grained":[77,190],"correspondence":[78,197],"between":[79,198],"components":[81,200],"image,":[84],"resulting":[85],"insufficient":[87],"cross-modal":[88],"interaction.":[89],"To":[90],"this":[91],"end,":[92],"we":[93,188],"propose":[94,189],"U":[95],"nified":[96],"T":[97],"ext":[98],"E":[99],"ncoder":[100],"F":[102],"ine-grained":[103],"C":[104],"ontrastive":[105],"L":[106],"earning":[107],"(UTE-FCL)":[108],"achieve":[110],"simple":[112],"efficient":[114],"model.":[115],"Specifically,":[116],"each":[118,123],"recipe,":[119],"UTE-FCL":[120,221],"first":[121],"concatenates":[122],"of":[124,131,220],"Ingredient":[126],"texts":[129,144,161],"composed":[130],"multiple":[132],"sentences":[133],"as":[134],"single":[136],"text.":[137],"Then,":[138],"connects":[140],"these":[141,158],"two":[142],"concatenated":[143,153,160],"original":[147,164],"single-phrase":[148],"Title":[149,165],"recipe.":[154],"Finally,":[155],"encodes":[157],"three":[159],"by":[166,210],"Transformer-based":[168],"Unified":[169],"Text":[170],"Encoder":[171],"(UTE).":[172],"This":[173],"proposed":[174],"structure":[175],"greatly":[176],"reduces":[177],"memory":[179],"usage":[180],"improves":[182],"encoding":[185],"efficiency.":[186],"Further,":[187],"contrastive":[191],"learning":[192],"objectives":[193],"capture":[195],"at":[204],"levels":[209],"measuring":[211],"mutual":[213],"information.":[214],"Extensive":[215],"experiments":[216],"demonstrate":[217],"effectiveness":[219],"compared":[222],"existing":[224],"methods.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-10-21T00:00:00"}