{"id":"https://openalex.org/W2950590791","doi":"https://doi.org/10.18653/v1/p19-1606","title":"Storyboarding of Recipes: Grounded Contextual Generation","display_name":"Storyboarding of Recipes: Grounded Contextual Generation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2950590791","doi":"https://doi.org/10.18653/v1/p19-1606","mag":"2950590791"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1606","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1606","pdf_url":"https://www.aclweb.org/anthology/P19-1606.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1606.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007169600","display_name":"Khyathi Raghavi Chandu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khyathi Chandu","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063241234","display_name":"Eric Nyberg","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Nyberg","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan W Black","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007169600"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6040","last_page":"6046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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":0.9958000183105469,"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":0.7631279230117798},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7537809610366821},{"id":"https://openalex.org/keywords/pluralistic-walkthrough","display_name":"Pluralistic walkthrough","score":0.647255539894104},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5697806477546692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5508145093917847},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.47303885221481323},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4470778703689575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44662904739379883},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4445054233074188},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.295541375875473},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.1972058117389679},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09999185800552368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631279230117798},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7537809610366821},{"id":"https://openalex.org/C188688815","wikidata":"https://www.wikidata.org/wiki/Q7205541","display_name":"Pluralistic walkthrough","level":3,"score":0.647255539894104},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5697806477546692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5508145093917847},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.47303885221481323},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4470778703689575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44662904739379883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4445054233074188},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.295541375875473},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.1972058117389679},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09999185800552368},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1606","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1606","pdf_url":"https://www.aclweb.org/anthology/P19-1606.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1606","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1606","pdf_url":"https://www.aclweb.org/anthology/P19-1606.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950590791.pdf","grobid_xml":"https://content.openalex.org/works/W2950590791.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W79932685","https://openalex.org/W2027687248","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2250379752","https://openalex.org/W2252078615","https://openalex.org/W2558809543","https://openalex.org/W2561658355","https://openalex.org/W2583186419","https://openalex.org/W2605035112","https://openalex.org/W2621430944","https://openalex.org/W2768661419","https://openalex.org/W2784025607","https://openalex.org/W2792795990","https://openalex.org/W2803629811","https://openalex.org/W2804668597","https://openalex.org/W2835434549","https://openalex.org/W2889181380","https://openalex.org/W2891939431","https://openalex.org/W2896348597","https://openalex.org/W2914855263","https://openalex.org/W2952132648","https://openalex.org/W2954801189","https://openalex.org/W2960416371","https://openalex.org/W2962895717","https://openalex.org/W2963045354","https://openalex.org/W2963096510","https://openalex.org/W2963168538","https://openalex.org/W2963223306","https://openalex.org/W2963436881","https://openalex.org/W2963592583","https://openalex.org/W2963993699","https://openalex.org/W2964138343","https://openalex.org/W4206342582","https://openalex.org/W4302570567","https://openalex.org/W4394670287"],"related_works":["https://openalex.org/W1600697036","https://openalex.org/W1601337804","https://openalex.org/W2035858348","https://openalex.org/W2155106162","https://openalex.org/W2010047220","https://openalex.org/W2165440188","https://openalex.org/W2552595315","https://openalex.org/W4231598561","https://openalex.org/W2497634305","https://openalex.org/W3173219617"],"abstract_inverted_index":{"Information":[0],"need":[1],"of":[2,12,33,56,111,117,128,151,158],"humans":[3],"is":[4,114,143],"essentially":[5],"multimodal":[6],"in":[7,27,54,84,93,99,149],"nature,":[8],"enabling":[9],"maximum":[10],"exploitation":[11],"situated":[13],"context.":[14],"We":[15,44,123,154],"introduce":[16,69],"a":[17,46,79,108],"dataset":[18,31],"for":[19,59,166],"sequential":[20,86],"procedural":[21],"(how-to)":[22],"text":[23],"generation":[24,87],"from":[25],"images":[26],"cooking":[28,35],"domain.":[29],"The":[30],"consists":[32],"16,441":[34],"recipes":[36],"with":[37,41],"160,479":[38],"photos":[39],"associated":[40],"different":[42],"steps.":[43],"setup":[45],"baseline":[47,121,147],"motivated":[48],"by":[49,78],"the":[50,60,120,129,146,159],"best":[51,103],"performing":[52,104],"model":[53,105,142,148],"terms":[55,150],"human":[57,126],"evaluation":[58,127],"Visual":[61],"Story":[62],"Telling":[63],"(ViST)":[64],"task.":[65],"In":[66],"addition,":[67],"we":[68],"two":[70],"models":[71],"to":[72],"incorporate":[73],"high":[74],"level":[75],"structure":[76],"learnt":[77],"Finite":[80],"State":[81],"Machine":[82],"(FSM)":[83],"neural":[85],"process":[88],"by:":[89],"(1)":[90],"Scaffolding":[91,97],"Structure":[92,98],"Decoder":[94],"(SSiD)":[95],"(2)":[96],"Loss":[100],"(SSiL).":[101],"Our":[102],"(SSiL)":[106,141],"achieves":[107],"METEOR":[109],"score":[110],"0.31,":[112],"which":[113,133],"an":[115],"improvement":[116],"0.6":[118],"over":[119],"model.":[122],"also":[124,155],"conducted":[125],"generated":[130],"grounded":[131],"recipes,":[132],"reveal":[134],"that":[135,138],"61%":[136],"found":[137],"our":[139],"proposed":[140],"better":[144],"than":[145],"overall":[152],"recipes.":[153],"discuss":[156],"analysis":[157],"output":[160],"highlighting":[161],"key":[162],"important":[163],"NLP":[164],"issues":[165],"prospective":[167],"directions.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}