{"id":"https://openalex.org/W4388157811","doi":"https://doi.org/10.1145/3607540.3617144","title":"Story-to-Images Translation: Leveraging Diffusion Models and Large Language Models for Sequence Image Generation","display_name":"Story-to-Images Translation: Leveraging Diffusion Models and Large Language Models for Sequence Image Generation","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4388157811","doi":"https://doi.org/10.1145/3607540.3617144"},"language":"en","primary_location":{"id":"doi:10.1145/3607540.3617144","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3607540.3617144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on User-centric Narrative Summarization of Long Videos","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/A5005846918","display_name":"Haruka Kumagai","orcid":"https://orcid.org/0009-0002-7278-8303"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Haruka Kumagai","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0002-7278-8303","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064195769","display_name":"Ryosuke Yamaki","orcid":"https://orcid.org/0009-0006-6940-8022"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryosuke Yamaki","raw_affiliation_strings":["Ritsumeikan University & ProPlace Inc., Kyoto, Japan"],"raw_orcid":"https://orcid.org/0009-0006-6940-8022","affiliations":[{"raw_affiliation_string":"Ritsumeikan University & ProPlace Inc., Kyoto, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010523882","display_name":"Hiroki Naganuma","orcid":"https://orcid.org/0000-0002-4595-8381"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hiroki Naganuma","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al & ProPlace Inc., Montr\u00e9al, PQ, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4595-8381","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al & ProPlace Inc., Montr\u00e9al, PQ, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005846918"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.1177,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42803633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"35","issue":null,"first_page":"57","last_page":"63"},"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":0.996399998664856,"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":0.996399998664856,"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":0.9660999774932861,"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":0.960099995136261,"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":0.7623776197433472},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.7577730417251587},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.7445480823516846},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7029539942741394},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.676760733127594},{"id":"https://openalex.org/keywords/hollywood","display_name":"Hollywood","score":0.6629462838172913},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5308566689491272},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.5267181992530823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5144546031951904},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5017850399017334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4898497760295868},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48304086923599243},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44419437646865845},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.42328527569770813},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.34266263246536255},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11280930042266846},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08736112713813782},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07612273097038269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623776197433472},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.7577730417251587},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7445480823516846},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7029539942741394},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.676760733127594},{"id":"https://openalex.org/C2780458788","wikidata":"https://www.wikidata.org/wiki/Q5882564","display_name":"Hollywood","level":2,"score":0.6629462838172913},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5308566689491272},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.5267181992530823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5144546031951904},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5017850399017334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4898497760295868},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48304086923599243},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44419437646865845},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.42328527569770813},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.34266263246536255},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11280930042266846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08736112713813782},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07612273097038269},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.1145/3607540.3617144","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3607540.3617144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on User-centric Narrative Summarization of Long Videos","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2962931774","https://openalex.org/W2963047368","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W3010564927","https://openalex.org/W3093926000","https://openalex.org/W3096831136","https://openalex.org/W3135367836","https://openalex.org/W3169749700","https://openalex.org/W3205612999","https://openalex.org/W4205991051","https://openalex.org/W4281485151","https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4386076676"],"related_works":["https://openalex.org/W2000013842","https://openalex.org/W4362495644","https://openalex.org/W2134714056","https://openalex.org/W4321065355","https://openalex.org/W2997015083","https://openalex.org/W3127743011","https://openalex.org/W2892009878","https://openalex.org/W3167690611","https://openalex.org/W4379381477","https://openalex.org/W4293577743"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"are":[2],"catalyzing":[3],"breakthroughs":[4],"in":[5],"creative":[6],"fields,":[7],"with":[8,54],"a":[9,30,47,50],"notable":[10],"impact":[11],"on":[12,18,57],"text-to-image":[13],"generation.":[14],"This":[15],"study":[16],"centers":[17],"the":[19,77,83],"transformation":[20],"of":[21,27,36,82],"textual":[22],"narratives":[23],"into":[24],"coherent":[25],"sequences":[26],"images":[28],"-":[29],"process":[31],"currently":[32],"hampered":[33],"by":[34],"issues":[35],"consistency":[37,78],"and":[38,59,79],"contextual":[39,80],"fidelity.":[40],"To":[41],"address":[42],"these":[43],"challenges,":[44],"we":[45],"propose":[46],"method":[48],"utilizing":[49],"large":[51],"language":[52],"model,":[53],"an":[55],"emphasis":[56],"context":[58],"character":[60],"information.":[61],"Empirical":[62],"evaluations,":[63],"carried":[64],"out":[65],"using":[66],"Hollywood":[67],"movie":[68],"scripts,":[69],"clearly":[70],"indicate":[71],"that":[72],"our":[73],"approach":[74],"improves":[75],"both":[76],"fidelity":[81],"resulting":[84],"image":[85],"sequences.":[86]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}