{"id":"https://openalex.org/W4390873040","doi":"https://doi.org/10.1109/iccv51070.2023.00279","title":"GePSAn: Generative Procedure Step Anticipation in Cooking Videos","display_name":"GePSAn: Generative Procedure Step Anticipation in Cooking Videos","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390873040","doi":"https://doi.org/10.1109/iccv51070.2023.00279"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.00279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","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/A5093719415","display_name":"Mohamed A. Abdelslam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mohamed A. Abdelslam","raw_affiliation_strings":["Samsung AI Centre"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065422451","display_name":"Samrudhdhi B. Rangrej","orcid":"https://orcid.org/0000-0003-0300-3429"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Samrudhdhi B. Rangrej","raw_affiliation_strings":["Samsung AI Centre"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053295927","display_name":"Isma Hadji","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Isma Hadji","raw_affiliation_strings":["Samsung AI Centre"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003458137","display_name":"Nikita Dvornik","orcid":"https://orcid.org/0000-0003-4770-3427"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Dvornik","raw_affiliation_strings":["Waabi"],"affiliations":[{"raw_affiliation_string":"Waabi","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111900659","display_name":"Konstantinos G. Derpanis","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Konstantinos G. Derpanis","raw_affiliation_strings":["Samsung AI Centre","York University"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"York University","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017305009","display_name":"Afsaneh Fazly","orcid":"https://orcid.org/0000-0002-4479-4901"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Afsaneh Fazly","raw_affiliation_strings":["Samsung AI Centre"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5093719415"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.4939,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67132385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2976","last_page":"2985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8415267467498779},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.8168989419937134},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5364876985549927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5145396590232849},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4937191903591156},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4433179795742035},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43565064668655396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3226877450942993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415267467498779},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.8168989419937134},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5364876985549927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145396590232849},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4937191903591156},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4433179795742035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43565064668655396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3226877450942993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51070.2023.00279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1821462560","https://openalex.org/W2101105183","https://openalex.org/W2326925005","https://openalex.org/W2470142083","https://openalex.org/W2916898195","https://openalex.org/W2952132648","https://openalex.org/W2960416371","https://openalex.org/W2962717182","https://openalex.org/W2963223306","https://openalex.org/W2981635073","https://openalex.org/W2981851019","https://openalex.org/W2993447238","https://openalex.org/W3020843970","https://openalex.org/W3035635319","https://openalex.org/W3085043532","https://openalex.org/W3091846787","https://openalex.org/W3106768499","https://openalex.org/W3108262631","https://openalex.org/W3132567969","https://openalex.org/W3153832461","https://openalex.org/W3176051609","https://openalex.org/W3182683290","https://openalex.org/W3199332348","https://openalex.org/W3203256294","https://openalex.org/W3203711169","https://openalex.org/W4214555767","https://openalex.org/W4294107275","https://openalex.org/W4307845887","https://openalex.org/W4312415723","https://openalex.org/W4312478760","https://openalex.org/W4312660844","https://openalex.org/W4312873759","https://openalex.org/W4313023218","https://openalex.org/W4319299948","https://openalex.org/W4385245566","https://openalex.org/W4386566548","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6739901393","https://openalex.org/W6743827229","https://openalex.org/W6752513430","https://openalex.org/W6761551260","https://openalex.org/W6791353385","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,37,84,91,120,128,147,150,168,193,210],"problem":[3,38,65],"of":[4,14,39,49,86,104,141],"future":[5,50,59,79,176,222],"step":[6,25,80,170,195,223],"anticipation":[7,51],"in":[8,27,42,61,70,156,167],"procedural":[9,17,43,142],"videos.":[10],"Given":[11],"a":[12,21,97,102,137],"video":[13,44,105,129,151,159,211],"an":[15],"ongoing":[16],"activity,":[18],"we":[19,77,95,126,198],"predict":[20],"plausible":[22,58,112,175],"next":[23,92,121,169,194],"procedure":[24],"described":[26],"rich":[28],"natural":[29,62,117],"language.":[30],"While":[31],"most":[32],"previous":[33,71,124],"work":[34],"focuses":[35],"on":[36,136,185,192],"data":[40],"scarcity":[41,131],"datasets,":[45],"another":[46],"core":[47],"challenge":[48],"is":[52],"how":[53],"to":[54,149,209],"account":[55],"for":[56,90,119],"multiple":[57,111,174],"realizations":[60],"settings.":[63],"This":[64],"has":[66],"been":[67],"largely":[68],"overlooked":[69],"work.":[72],"To":[73],"address":[74],"this":[75],"challenge,":[76],"frame":[78],"prediction":[81,171],"as":[82,107],"modelling":[83],"distribution":[85],"all":[87],"possible":[88],"candidates":[89,115],"step.":[93,122],"Specifically,":[94],"design":[96],"generative":[98],"model":[99,135,148,164,180,203],"that":[100,162,201],"takes":[101],"series":[103],"clips":[106],"input,":[108],"and":[109,113,144,158,172,219],"generates":[110,173],"diverse":[114],"(in":[116],"language)":[118],"Following":[123],"work,":[125],"side-step":[127],"annotation":[130],"by":[132],"pretraining":[133],"our":[134,163,179,202],"large":[138],"text-based":[139],"corpus":[140],"activities,":[143],"then":[145],"transfer":[146,206],"domain.":[152],"Our":[153],"experiments,":[154],"both":[155],"textual":[157],"domains,":[160],"show":[161,200],"captures":[165],"diversity":[166],"predictions.":[177],"Moreover,":[178],"establishes":[181],"new":[182],"state-of-the-art":[183],"results":[184],"YouCookII,":[186],"where":[187],"it":[188],"outperforms":[189],"existing":[190],"baselines":[191],"anticipation.":[196],"Finally,":[197],"also":[199],"can":[204],"successfully":[205],"from":[207,225],"text":[208],"domain":[212],"zero-shot,":[213],"i.e.,":[214],"without":[215],"fine-tuning":[216],"or":[217],"adaptation,":[218],"produces":[220],"good-quality":[221],"predictions":[224],"video.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}