{"id":"https://openalex.org/W7131095643","doi":"https://doi.org/10.1109/iccvw69036.2025.00399","title":"Generating Visually Consistent Images for Storytelling via Narrative Graph Prompting","display_name":"Generating Visually Consistent Images for Storytelling via Narrative Graph Prompting","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131095643","doi":"https://doi.org/10.1109/iccvw69036.2025.00399"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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/A5103066975","display_name":"Andrew Y. Shin","orcid":"https://orcid.org/0000-0001-6713-0609"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andrew Shin","raw_affiliation_strings":["Keio University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113223463","display_name":"Kunitake Kaneko","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunitake Kaneko","raw_affiliation_strings":["Keio University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65442447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3831","last_page":"3836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7537000179290771,"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":0.7537000179290771,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.052799999713897705,"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/T10799","display_name":"Data Visualization and Analytics","score":0.036400001496076584,"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/narrative","display_name":"Narrative","score":0.6988000273704529},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.5562999844551086},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.524399995803833},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5116000175476074},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4641999900341034},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.45730000734329224},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.45410001277923584},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.42320001125335693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268999814987183},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.6988000273704529},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299999713897705},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.524399995803833},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.42320001125335693},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3986999988555908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37869998812675476},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C63075964","wikidata":"https://www.wikidata.org/wiki/Q3277307","display_name":"Visual rhetoric","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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":5,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2969985801","https://openalex.org/W4312933868","https://openalex.org/W4385535331","https://openalex.org/W4386072096"],"related_works":[],"abstract_inverted_index":{"While":[0],"generative":[1],"AI":[2],"has":[3],"accomplished":[4],"significant":[5],"advances":[6],"in":[7,22,54],"visual":[8,12,52,61,98,110,124,133,158],"qualities,":[9],"generating":[10],"coherent":[11,156],"narratives":[13],"over":[14,146],"timeline":[15],"still":[16],"remains":[17],"challenging":[18],"due":[19],"to":[20,50,91],"inconsistencies":[21],"recurring":[23],"elements,":[24,69,148],"such":[25,70],"as":[26,71],"characters":[27],"and":[28,63,74,142,155],"settings,":[29,73],"across":[30],"different":[31],"frames":[32],"or":[33],"scenes.":[34],"This":[35,106],"paper":[36],"introduces":[37],"Narrative":[38],"Graph":[39],"Prompting,":[40],"a":[41,46,77,136],"novel":[42],"strategy":[43],"that":[44,109],"employs":[45],"structured":[47,130],"graph":[48,90],"representation":[49],"enforce":[51],"consistency":[53,65],"AI-generated":[55],"stories.":[56],"Our":[57],"approach":[58,131],"defines":[59],"canonical":[60],"attributes":[62],"unique":[64],"identifiers":[66],"for":[67,97,138,152],"key":[68],"characters,":[72],"objects,":[75],"within":[76],"central":[78],"narrative":[79,140],"graph.":[80],"An":[81],"orchestrating":[82],"Large":[83],"Language":[84],"Model":[85],"(LLM)":[86],"then":[87],"leverages":[88],"this":[89,129],"generate":[92],"highly":[93],"detailed,":[94],"scene-specific":[95],"prompts":[96],"generation":[99],"models,":[100],"critically":[101],"injecting":[102],"these":[103],"consistent":[104],"identifiers.":[105],"method":[107],"ensures":[108],"models":[111],"render":[112],"elements":[113],"with":[114],"maintained":[115],"appearance":[116],"throughout":[117],"the":[118,121,150],"narrative,":[119],"reducing":[120],"occurrences":[122],"of":[123],"drift.":[125],"We":[126],"demonstrate":[127],"how":[128],"enhances":[132],"consistency,":[134],"provides":[135],"framework":[137],"scalable":[139],"generation,":[141],"offers":[143],"fine-grained":[144],"control":[145],"story":[147],"paving":[149],"way":[151],"more":[153],"compelling":[154],"AI-powered":[157],"storytelling.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-24T00:00:00"}