{"id":"https://openalex.org/W4392902491","doi":"https://doi.org/10.1109/tmm.2024.3377540","title":"CookGALIP: Recipe Controllable Generative Adversarial CLIPs With Sequential Ingredient Prompts for Food Image Generation","display_name":"CookGALIP: Recipe Controllable Generative Adversarial CLIPs With Sequential Ingredient Prompts for Food Image Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902491","doi":"https://doi.org/10.1109/tmm.2024.3377540"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3377540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3377540","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","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/A5076639787","display_name":"Mengling Xu","orcid":"https://orcid.org/0009-0002-4809-9129"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengling Xu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440133","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-8662-9488"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776884","display_name":"Ming Tao","orcid":"https://orcid.org/0000-0002-4662-7170"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Peng Cheng Laboratory, Shenzhen, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076639787"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":2.9914,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92138803,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"2772","last_page":"2782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.883899986743927,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.883899986743927,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.8119000196456909,"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/clips","display_name":"CLIPS","score":0.9074918031692505},{"id":"https://openalex.org/keywords/recipe","display_name":"Recipe","score":0.8529938459396362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.798349142074585},{"id":"https://openalex.org/keywords/ingredient","display_name":"Ingredient","score":0.7633116841316223},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7437427639961243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5780985951423645},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5559845566749573},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5250748991966248},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4813981056213379},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3729217052459717}],"concepts":[{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.9074918031692505},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.8529938459396362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798349142074585},{"id":"https://openalex.org/C2780589914","wikidata":"https://www.wikidata.org/wiki/Q10675206","display_name":"Ingredient","level":2,"score":0.7633116841316223},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7437427639961243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5780985951423645},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5559845566749573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5250748991966248},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4813981056213379},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3729217052459717},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3377540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3377540","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2183341477","https://openalex.org/W2526198870","https://openalex.org/W2896457183","https://openalex.org/W2948037078","https://openalex.org/W2960416371","https://openalex.org/W2962762068","https://openalex.org/W2963163163","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2966792645","https://openalex.org/W2981631843","https://openalex.org/W3009381623","https://openalex.org/W3034667500","https://openalex.org/W3035574324","https://openalex.org/W3093100367","https://openalex.org/W3115266926","https://openalex.org/W3173777717","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3207865986","https://openalex.org/W3215495615","https://openalex.org/W4291433229","https://openalex.org/W4312438583","https://openalex.org/W4312977351","https://openalex.org/W4319996536","https://openalex.org/W4377715513","https://openalex.org/W4386065752","https://openalex.org/W4386076458","https://openalex.org/W4386790226","https://openalex.org/W6638319203","https://openalex.org/W6678815747","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6729482032","https://openalex.org/W6765779288","https://openalex.org/W6791353385","https://openalex.org/W6845764769"],"related_works":["https://openalex.org/W2909050333","https://openalex.org/W2611971073","https://openalex.org/W2011684307","https://openalex.org/W2512497230","https://openalex.org/W2950291079","https://openalex.org/W4288389006","https://openalex.org/W2124095343","https://openalex.org/W3168874191","https://openalex.org/W2065710407","https://openalex.org/W2765707332"],"abstract_inverted_index":{"Generating":[0],"food":[1,10,23,54,83,105,120,144,180],"images":[2,55],"from":[3],"recipes":[4,13,80,177],"is":[5,87],"a":[6,150],"challenging":[7],"task":[8],"in":[9,22,70,104],"analysis,":[11],"as":[12,163],"contain":[14],"lengthy":[15],"texts":[16],"far":[17],"beyond":[18],"the":[19,30,39,49,66,100,125,139,143,157,166,173,187,193,209,223,227],"semantic":[20,77,115,167,174],"information":[21,68],"images,":[24],"making":[25],"it":[26,86],"difficult":[27,89],"to":[28,52,76,93,155,164,198],"align":[29],"features":[31,103],"of":[32,41,159,176],"two":[33,131],"modalities.":[34],"Existing":[35],"studies":[36],"usually":[37],"concatenate":[38],"representations":[40,51],"ingredients":[42],"and":[43,47,81,95,117,171,178,185,217],"cooking":[44,160],"instructions":[45],"directly,":[46],"use":[48],"concatenated":[50],"generate":[53,199],"through":[56],"generative":[57],"adversarial":[58],"networks":[59],"(GANs).":[60],"However,":[61],"previous":[62],"models":[63,92],"generally":[64],"ignore":[65],"sequential":[67,140,200],"contained":[69],"complicated":[71],"procedural":[72],"instructions,":[73,161],"which":[74,113,203],"leads":[75],"inconsistency":[78],"between":[79,169],"generated":[82,179],"images.":[84,106,181],"Furthermore,":[85],"still":[88],"for":[90,119],"current":[91],"distinguish":[94,184],"control":[96,186,207],"fine-grained":[97,188],"features,":[98,190],"causing":[99],"entangled":[101],"ingredient":[102,189,201],"To":[107,137,183],"this":[108],"end,":[109],"we":[110,148,191],"propose":[111,149],"CookGALIP,":[112],"strengthens":[114],"consistency":[116,175],"controllability":[118],"image":[121,145],"generation.":[122],"Based":[123],"on":[124,215],"recently":[126],"proposed":[127,224],"text-to-image":[128],"framework":[129],"GALIP,":[130],"modules":[132],"are":[133],"specially":[134],"designed:":[135],"1)":[136],"incorporate":[138],"relationships":[141],"into":[142],"generation":[146],"process,":[147],"Recipe":[151],"Fusion":[152],"Module":[153,196],"(RFM)":[154],"fuse":[156],"semantics":[158],"so":[162],"balance":[165],"complexity":[168],"modalities":[170],"improve":[172],"2)":[182],"introduce":[192],"Ingredient":[194],"Control":[195],"(ICM)":[197],"prompts,":[202],"enables":[204],"more":[205],"refined":[206],"over":[208],"recipe-to-food":[210],"synthesis":[211],"process.":[212],"Experimental":[213],"results":[214],"Recipe1M":[216],"Vireo":[218],"Food-172":[219],"datasets":[220],"show":[221],"that":[222],"model":[225],"outperforms":[226],"state-of-the-art":[228],"methods.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}