{"id":"https://openalex.org/W4415539406","doi":"https://doi.org/10.1145/3746027.3758203","title":"RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation","display_name":"RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539406","doi":"https://doi.org/10.1145/3746027.3758203"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758203","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5111102145","display_name":"Ruoxuan Zhang","orcid":"https://orcid.org/0009-0002-0829-6267"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruoxuan Zhang","raw_affiliation_strings":["Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0009-0002-0829-6267","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jidong Gao","orcid":"https://orcid.org/0009-0006-3310-748X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Gao","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-3310-748X","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001013820","display_name":"Bin Wen","orcid":"https://orcid.org/0009-0000-4665-6978"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wen","raw_affiliation_strings":["Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0009-0000-4665-6978","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013026466","display_name":"Hongxia Xie","orcid":"https://orcid.org/0000-0002-5652-4327"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxia Xie","raw_affiliation_strings":["Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0002-5652-4327","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenming Zhang","orcid":"https://orcid.org/0009-0009-2987-0126"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenming Zhang","raw_affiliation_strings":["Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0009-0009-2987-0126","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040050806","display_name":"Hong-Han Shuai","orcid":"https://orcid.org/0000-0003-2216-077X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Han Shuai","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-2216-077X","affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000780442","display_name":"Wen-Huang Cheng","orcid":"https://orcid.org/0000-0002-4662-7875"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Huang Cheng","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-4662-7875","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5111102145"],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15609834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12659","last_page":"12665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9980000257492065,"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/T11197","display_name":"Digital Games and Media","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.994700014591217,"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":0.9904999732971191},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8482000231742859},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5299999713897705},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5217999815940857},{"id":"https://openalex.org/keywords/ingredient","display_name":"Ingredient","score":0.41530001163482666}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.9904999732971191},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8482000231742859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666700005531311},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46380001306533813},{"id":"https://openalex.org/C2780589914","wikidata":"https://www.wikidata.org/wiki/Q10675206","display_name":"Ingredient","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758203","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1635450702","display_name":null,"funder_award_id":"62406126","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2526198870","https://openalex.org/W2810262433","https://openalex.org/W2952132648","https://openalex.org/W2960416371","https://openalex.org/W2966316879","https://openalex.org/W2972610293","https://openalex.org/W2995924296","https://openalex.org/W3009381623","https://openalex.org/W3093100367","https://openalex.org/W3111340645","https://openalex.org/W3116194881","https://openalex.org/W3159481202","https://openalex.org/W4291433229","https://openalex.org/W4312933868","https://openalex.org/W4319996536","https://openalex.org/W4378619666","https://openalex.org/W4393200103","https://openalex.org/W4394596514"],"related_works":[],"abstract_inverted_index":{"Creating":[0],"recipe":[1,17,26,94],"images":[2],"is":[3,99],"a":[4],"key":[5],"challenge":[6],"in":[7,12],"food":[8],"computing,":[9],"with":[10],"applications":[11],"culinary":[13],"education":[14],"and":[15,30,47,57,66,79,86,89],"multimodal":[16],"assistants.":[18],"However,":[19],"existing":[20],"datasets":[21],"lack":[22],"fine-grained":[23],"alignment":[24],"between":[25],"goals,":[27],"step-wise":[28],"instructions,":[29],"visual":[31],"content.":[32],"We":[33,69],"present":[34],"RecipeGen,":[35],"the":[36],"first":[37],"large-scale,":[38],"real-world":[39],"benchmark":[40,82],"for":[41,92],"recipe-based":[42],"Text-to-Image":[43],"(T2I),":[44],"Image-to-Video":[45],"(I2V),":[46],"Text-to-Video":[48],"(T2V)":[49],"generation.":[50],"RecipeGen":[51],"contains":[52],"26,435":[53],"recipes,":[54],"196,724":[55],"images,":[56],"4,491":[58],"videos,":[59],"covering":[60],"diverse":[61],"ingredients,":[62],"cooking":[63],"procedures,":[64],"styles,":[65],"dish":[67],"types.":[68],"further":[70],"propose":[71],"domain-specific":[72],"evaluation":[73],"metrics":[74],"to":[75],"assess":[76],"ingredient":[77],"fidelity":[78],"interaction":[80],"modeling,":[81],"representative":[83],"T2I,":[84],"I2V,":[85],"T2V":[87],"models,":[88],"provide":[90],"insights":[91],"future":[93],"generation":[95],"models.":[96],"Project":[97],"page":[98],"available":[100],"at":[101],"https://wenbin08.github.io/RecipeGen.":[102]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}