{"id":"https://openalex.org/W3207562294","doi":"https://doi.org/10.1145/3474085.3475422","title":"Cross-Modal Recipe Embeddings by Disentangling Recipe Contents and Dish Styles","display_name":"Cross-Modal Recipe Embeddings by Disentangling Recipe Contents and Dish Styles","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207562294","doi":"https://doi.org/10.1145/3474085.3475422","mag":"3207562294"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5109619034","display_name":"Yu Sugiyama","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yu Sugiyama","raw_affiliation_strings":["The University of Electro-Communications, Chofu-shi, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Chofu-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054600485","display_name":"\u202aKeiji Yanai\u202c","orcid":"https://orcid.org/0000-0002-0431-183X"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiji Yanai","raw_affiliation_strings":["The University of Electro-Communications, Chofu-shi, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Chofu-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109619034"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":1.345,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83232026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2501","last_page":"2509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9932000041007996,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9932000041007996,"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":0.9926000237464905,"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":0.9747999906539917,"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/recipe","display_name":"Recipe","score":0.998385488986969},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7427813410758972},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6338450908660889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5402185320854187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5349510908126831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4505213499069214},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4489178955554962},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41100767254829407},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3965356945991516},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37010446190834045},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3207510709762573},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13300392031669617},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09878712892532349}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.998385488986969},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7427813410758972},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6338450908660889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5402185320854187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5349510908126831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4505213499069214},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4489178955554962},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41100767254829407},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3965356945991516},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37010446190834045},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3207510709762573},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13300392031669617},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09878712892532349},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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":31,"referenced_works":["https://openalex.org/W1975517671","https://openalex.org/W2096733369","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2194775991","https://openalex.org/W2564591810","https://openalex.org/W2593414223","https://openalex.org/W2605135824","https://openalex.org/W2737041163","https://openalex.org/W2765440071","https://openalex.org/W2766910785","https://openalex.org/W2797650215","https://openalex.org/W2798397499","https://openalex.org/W2858926098","https://openalex.org/W2948037078","https://openalex.org/W2950096404","https://openalex.org/W2951697117","https://openalex.org/W2960416371","https://openalex.org/W2962770929","https://openalex.org/W2963055199","https://openalex.org/W2963836885","https://openalex.org/W2963981733","https://openalex.org/W2963997278","https://openalex.org/W2980407281","https://openalex.org/W3008552039","https://openalex.org/W3033103428","https://openalex.org/W3034667500","https://openalex.org/W3035032757","https://openalex.org/W3093100367","https://openalex.org/W3099206234","https://openalex.org/W3159890710"],"related_works":["https://openalex.org/W258429745","https://openalex.org/W3161239248","https://openalex.org/W1584543623","https://openalex.org/W2561508161","https://openalex.org/W3195543079","https://openalex.org/W2098178683","https://openalex.org/W2740680361","https://openalex.org/W3207562294","https://openalex.org/W3187068967","https://openalex.org/W2312145515"],"abstract_inverted_index":{"Nowadays,":[0],"cooking":[1,21,46,161],"recipe":[2,28,31,48,71,121,140,175,185],"sharing":[3],"sites":[4],"on":[5,173],"the":[6,53,63,78,100,139,147,163,170,191],"Web":[7],"are":[8,50,158],"widely":[9],"used,":[10],"and":[11,27,45,73,93,124,142,154],"play":[12],"a":[13,66,70,74,108,120,125,133,143],"major":[14],"role":[15],"in":[16,57,60,77],"everyday":[17],"home":[18],"cooking.":[19],"Since":[20,146],"recipes":[22],"consist":[23],"of":[24,62,87,193],"dish":[25,75],"photos":[26,88],"texts,":[29],"cross-modal":[30,39,174],"search":[32],"is":[33,81,150],"being":[34],"actively":[35],"explored.":[36],"To":[37],"enable":[38],"search,":[40],"both":[41,138],"food":[42,116,134,194],"image":[43,76,117,122,135,195],"features":[44,49],"text":[47,72],"embedded":[51],"into":[52,119],"same":[54,101],"shared":[55],"space":[56,80],"general.":[58],"However,":[59],"most":[61],"existing":[64,171],"studies,":[65],"one-to-one":[67],"correspondence":[68],"between":[69],"embedding":[79,141,149],"assumed,":[82],"although":[83],"an":[84],"unlimited":[85],"number":[86],"with":[89,99],"different":[90,94],"serving":[91,153],"styles":[92,156],"plates":[95],"can":[96,187],"be":[97,188],"associated":[98],"recipe.":[102],"In":[103,129],"this":[104],"paper,":[105],"we":[106,131],"propose":[107],"RDE-GAN":[109],"(Recipe":[110],"Disentangled":[111],"Embedding":[112],"GAN)":[113],"which":[114,157],"separates":[115],"information":[118],"feature":[123],"non-recipe":[126],"shape":[127,144,183],"feature.":[128,145],"addition,":[130],"generate":[132],"by":[136],"integrating":[137],"proposed":[148],"free":[151],"from":[152],"plate":[155],"unrelated":[159],"to":[160],"recipes,":[162],"experimental":[164],"results":[165],"showed":[166],"that":[167,180],"it":[168],"outperformed":[169],"methods":[172],"search.":[176],"We":[177],"also":[178],"confirmed":[179],"only":[181],"either":[182],"or":[184],"elements":[186],"changed":[189],"at":[190],"time":[192],"generation.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}