{"id":"https://openalex.org/W4406319208","doi":"https://doi.org/10.1109/iccv51701.2025.01781","title":"Videoauteur: Towards Long Narrative Video Generation","display_name":"Videoauteur: Towards Long Narrative Video Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406319208","doi":"https://doi.org/10.1109/iccv51701.2025.01781"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01781","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 (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.06173","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016734799","display_name":"Junfei Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junfei Xiao","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051081214","display_name":"Feng Cheng","orcid":"https://orcid.org/0000-0003-2982-9675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Cheng","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112327738","display_name":"Lu Qi","orcid":"https://orcid.org/0000-0002-1577-9462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Qi","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037727565","display_name":"Liangke Gui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangke Gui","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shanchuan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanchuan Lin","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiepeng Cen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiepeng Cen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhibei Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhibei Ma","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Yuille","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033105884","display_name":"Lu Jiang","orcid":"https://orcid.org/0000-0001-6003-7575"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Jiang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88636892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"19163","last_page":"19173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9925000071525574,"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":0.9925000071525574,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9761999845504761,"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/T12461","display_name":"Narrative Theory and Analysis","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.7587533593177795},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.32159751653671265},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.224882572889328},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.1923263967037201}],"concepts":[{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.7587533593177795},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.32159751653671265},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.224882572889328},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.1923263967037201}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01781","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 (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.06173","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.06173","pdf_url":"https://arxiv.org/pdf/2501.06173","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.06173","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.06173","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.06173","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.06173","pdf_url":"https://arxiv.org/pdf/2501.06173","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7734489741","display_name":null,"funder_award_id":"N00014-23-1-2641","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2348886128","https://openalex.org/W2388067091","https://openalex.org/W2367656648","https://openalex.org/W2350200549","https://openalex.org/W2362132076","https://openalex.org/W2965396777","https://openalex.org/W2389168924","https://openalex.org/W2067294484"],"abstract_inverted_index":{"Recent":[0],"video":[1,11,46,81,115,142],"generation":[2,53,82,143],"models":[3,18],"have":[4],"shown":[5],"promising":[6],"results":[7],"in":[8,21,54,66,100,122],"producing":[9],"high-quality":[10],"clips":[12],"lasting":[13],"several":[14],"seconds.":[15],"However,":[16],"these":[17],"face":[19],"challenges":[20],"generating":[22,123],"long":[23],"sequences":[24],"that":[25,134],"convey":[26],"clear":[27],"and":[28,71,80,97,103,126,137],"informative":[29],"events,":[30],"limiting":[31],"their":[32],"ability":[33],"to":[34,49,93,111],"support":[35],"coherent":[36],"narrations.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"present":[42],"a":[43,88],"large-scale":[44],"cooking":[45,56],"dataset":[47,65],"designed":[48],"advance":[50],"long-form":[51],"narrative":[52],"the":[55,60,105,141],"domain.":[57],"We":[58,85],"validate":[59],"quality":[61],"of":[62,68,107],"our":[63],"proposed":[64],"terms":[67],"visual":[69,96,109],"fidelity":[70],"textual":[72],"caption":[73],"accuracy":[74],"using":[75],"state-of-the-art":[76],"Vision-Language":[77],"Models":[78],"(VLMs)":[79],"models,":[83],"respectively.":[84],"further":[86],"introduce":[87],"Long":[89],"Narrative":[90],"Video":[91],"Director":[92],"enhance":[94],"both":[95],"semantic":[98],"coherence":[99],"generated":[101],"videos":[102],"emphasize":[104],"role":[106],"aligning":[108],"embeddings":[110,139],"achieve":[112],"improved":[113],"overall":[114],"quality.":[116],"Our":[117],"method":[118],"demonstrates":[119],"substantial":[120],"improvements":[121],"visually":[124],"detailed":[125],"semantically":[127],"aligned":[128],"keyframes,":[129],"supported":[130],"by":[131],"finetuning":[132],"techniques":[133],"integrate":[135],"text":[136],"image":[138],"within":[140],"process.":[144],"Project":[145],"page:":[146],"https://videoauteur.github.io/":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
