{"id":"https://openalex.org/W4392903659","doi":"https://doi.org/10.1109/icassp48485.2024.10447148","title":"Cooking-Clip: Context-Aware Language-Image Pretraining for Zero-Shot Recipe Generation","display_name":"Cooking-Clip: Context-Aware Language-Image Pretraining for Zero-Shot Recipe Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903659","doi":"https://doi.org/10.1109/icassp48485.2024.10447148"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447148","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100403214","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0002-9944-5151"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067909002","display_name":"Haithm M. Al-Gunid","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haithm M. Al-Gunid","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089032960","display_name":"Ammar Hawbani","orcid":"https://orcid.org/0000-0002-1069-3993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ammar Hawbani","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100735350","display_name":"Yan Xiong","orcid":"https://orcid.org/0000-0001-6347-8747"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Xiong","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03146517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11446","last_page":"11450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9914000034332275,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7497689723968506},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6856385469436646},{"id":"https://openalex.org/keywords/recipe","display_name":"Recipe","score":0.6808326244354248},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.589928388595581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5217448472976685},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5168081521987915},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4751056134700775},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.46697187423706055},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40926969051361084},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14994624257087708},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09126174449920654},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08389595150947571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497689723968506},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6856385469436646},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.6808326244354248},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.589928388595581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217448472976685},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5168081521987915},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4751056134700775},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.46697187423706055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40926969051361084},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14994624257087708},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09126174449920654},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08389595150947571},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/icassp48485.2024.10447148","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2737041163","https://openalex.org/W2890399523","https://openalex.org/W2952132648","https://openalex.org/W2957775769","https://openalex.org/W2963351113","https://openalex.org/W2982335217","https://openalex.org/W3153469116","https://openalex.org/W3185341429","https://openalex.org/W3208474254","https://openalex.org/W4214663214","https://openalex.org/W4327852044","https://openalex.org/W4377300483","https://openalex.org/W4378942464","https://openalex.org/W4390872424","https://openalex.org/W4404792832","https://openalex.org/W6682631176","https://openalex.org/W6761205521","https://openalex.org/W6851149231","https://openalex.org/W6852217271","https://openalex.org/W6852586215","https://openalex.org/W6853320480"],"related_works":["https://openalex.org/W3161239248","https://openalex.org/W258429745","https://openalex.org/W2740181000","https://openalex.org/W1584543623","https://openalex.org/W2561508161","https://openalex.org/W2013985456","https://openalex.org/W2951564084","https://openalex.org/W4302984940","https://openalex.org/W2776807270","https://openalex.org/W2392685819"],"abstract_inverted_index":{"Cooking":[0],"is":[1],"one":[2,22],"of":[3,23,94,164],"the":[4,7,24,50,71,75,92],"oldest":[5],"and":[6,53,146],"most":[8,25],"common":[9,26],"human":[10],"activities":[11],"in":[12,162],"everyone\u2019s":[13],"daily":[14],"life.":[15],"Instructional":[16],"cooking":[17,39,141],"videos":[18],"have":[19,44,65],"also":[20,64,111,149],"become":[21],"data":[27,143],"sources":[28],"for":[29,83],"multimodal":[30,38,101],"visual":[31,56],"understanding":[32],"researches.":[33],"Compared":[34],"to":[35,117,123],"other":[36],"domains,":[37],"videos:":[40],"1.":[41],"not":[42],"only":[43,158],"significantly":[45,66],"stronger":[46,67],"cross-modal":[47],"dependencies":[48,69],"between":[49],"speech":[51],"transcriptions":[52],"their":[54],"semantically-aligned":[55],"frames":[57],"at":[58],"static":[59],"time":[60],"stamps;":[61],"2.":[62],"but":[63],"cross-context":[68],"among":[70],"sequential":[72],"steps":[73],"along":[74],"temporal":[76],"dimension,":[77],"resulting":[78],"as":[79],"an":[80],"ideal":[81],"domain":[82],"contextualized":[84],"semantic":[85],"understanding.":[86],"We":[87,110,148],"propose":[88,112],"Cooking-CLIP,":[89],"which":[90],"introduces":[91],"concept":[93],"language-image":[95],"pretraining":[96,115],"(CLIP)":[97],"from":[98],"a":[99,105,113,119,134,154,159],"general-purpose":[100],"embedding":[102],"problem":[103],"into":[104],"customized":[106],"recipe":[107],"generation":[108,131],"application.":[109],"context-aware":[114],"approach,":[116,156],"facilitate":[118],"better":[120],"CLIP":[121],"customization":[122],"cooking-related":[124],"applications.":[125],"Our":[126],"approach":[127],"achieves":[128],"higher":[129],"text":[130],"accuracies":[132,152],"than":[133],"strong":[135],"zero-shot":[136,166],"baseline":[137],"on":[138],"two":[139],"instructional":[140],"video":[142],"sets,":[144],"CrossTask":[145],"YouCook2.":[147],"achieve":[150],"comparative":[151],"against":[153],"fully-supervised":[155],"with":[157],"narrow":[160],"difference,":[161],"spite":[163],"our":[165],"setting.":[167]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
