{"id":"https://openalex.org/W4405812528","doi":"https://doi.org/10.1109/access.2024.3522510","title":"ImproveYourVideos: Architectural Improvements for Text-to-Video Generation Pipeline","display_name":"ImproveYourVideos: Architectural Improvements for Text-to-Video Generation Pipeline","publication_year":2024,"publication_date":"2024-12-26","ids":{"openalex":"https://openalex.org/W4405812528","doi":"https://doi.org/10.1109/access.2024.3522510"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3522510","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3522510","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3522510","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032078392","display_name":"Vladimir Arkhipkin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vladimir Arkhipkin","raw_affiliation_strings":["Sber AI Research, Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0001-2850-6412","affiliations":[{"raw_affiliation_string":"Sber AI Research, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013973022","display_name":"Zein Shaheen","orcid":"https://orcid.org/0000-0001-6802-2896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zein Shaheen","raw_affiliation_strings":["Sber AI Research, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sber AI Research, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052169416","display_name":"Viacheslav Vasilev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viacheslav Vasilev","raw_affiliation_strings":["Sber AI Research, Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0007-9368-7524","affiliations":[{"raw_affiliation_string":"Sber AI Research, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083285740","display_name":"Elizaveta Dakhova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elizaveta Dakhova","raw_affiliation_strings":["Sber AI Research, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sber AI Research, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075050471","display_name":"Konstantin Sobolev","orcid":"https://orcid.org/0000-0003-2969-3501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantin Sobolev","raw_affiliation_strings":["Artificial Intelligence Research Institute, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0003-2969-3501","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086303779","display_name":"Andrey Kuznetsov","orcid":"https://orcid.org/0000-0001-6446-8663"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrey Kuznetsov","raw_affiliation_strings":["Sber AI Research, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sber AI Research, Moscow, Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069881176","display_name":"Denis Dimitrov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denis Dimitrov","raw_affiliation_strings":["Sber AI Research, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sber AI Research, Moscow, Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5032078392"],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.1166,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90532175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"1986","last_page":"2003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9901999831199646,"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":0.7642547488212585},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6758080720901489},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.43716591596603394},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19049054384231567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642547488212585},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6758080720901489},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.43716591596603394},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19049054384231567}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3522510","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3522510","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5349f361e79a41d18732d885f9e2ebd4","is_oa":true,"landing_page_url":"https://doaj.org/article/5349f361e79a41d18732d885f9e2ebd4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 1986-2003 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3522510","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3522510","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2558805089","https://openalex.org/W2769654144","https://openalex.org/W2962785568","https://openalex.org/W2964033924","https://openalex.org/W3031246127","https://openalex.org/W4294541506","https://openalex.org/W4297697565","https://openalex.org/W4312423208","https://openalex.org/W4312633146","https://openalex.org/W4312847199","https://openalex.org/W4312933868","https://openalex.org/W4385136259","https://openalex.org/W4386065764","https://openalex.org/W4386071957","https://openalex.org/W4390874580","https://openalex.org/W4402727736","https://openalex.org/W6726983635","https://openalex.org/W6745420753","https://openalex.org/W6750642828","https://openalex.org/W6756789066","https://openalex.org/W6768115207","https://openalex.org/W6771861442","https://openalex.org/W6790720088","https://openalex.org/W6793801364","https://openalex.org/W6794385437","https://openalex.org/W6797331426","https://openalex.org/W6804184823","https://openalex.org/W6809884996","https://openalex.org/W6809885388","https://openalex.org/W6810125463","https://openalex.org/W6810793953","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6838785959","https://openalex.org/W6842542927","https://openalex.org/W6844305113","https://openalex.org/W6845281891","https://openalex.org/W6846135447","https://openalex.org/W6846820273","https://openalex.org/W6846959760","https://openalex.org/W6848096045","https://openalex.org/W6854463369","https://openalex.org/W6855459923","https://openalex.org/W6856100209","https://openalex.org/W6856290213","https://openalex.org/W6856700853","https://openalex.org/W6857267394","https://openalex.org/W6857981686","https://openalex.org/W6858062379","https://openalex.org/W6858865347","https://openalex.org/W6859013395","https://openalex.org/W6859214647","https://openalex.org/W6859329810"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"text-to-video":[3,49],"models":[4,19],"have":[5,26],"made":[6],"impressive":[7],"strides":[8],"toward":[9],"producing":[10],"high-quality":[11],"results.":[12],"However,":[13],"the":[14,56,108,121,126,134,137,142],"architectural":[15],"aspects":[16],"of":[17,107],"these":[18],"remain":[20],"largely":[21],"unexplored,":[22],"as":[23,76],"prior":[24],"studies":[25],"used":[27],"well-known":[28],"approaches":[29,118],"that":[30,97,106,133],"offer":[31],"minimal":[32],"variation":[33],"between":[34],"models.":[35],"This":[36],"study":[37],"aims":[38],"to":[39,75,125],"address":[40],"this":[41],"gap":[42],"by":[43],"systematically":[44],"exploring":[45],"alternative":[46,70],"options":[47],"for":[48,119],"architecture":[50,96],"building":[51],"blocks,":[52,78],"specifically":[53],"focusing":[54],"on":[55],"temporal":[57,71,77],"layer,":[58],"frame":[59,94],"interpolation":[60,95,112],"model,":[61],"and":[62,67,86,148],"autoencoder.":[63],"Firstly,":[64],"we":[65,90,115],"propose":[66],"compare":[68],"various":[69],"consistency":[72],"modules,":[73],"referred":[74],"which":[79],"demonstrate":[80],"improvements":[81],"in":[82],"generation":[83],"quality":[84],"metrics":[85],"human":[87],"evaluation.":[88],"Secondly,":[89],"introduce":[91],"a":[92],"novel":[93],"offers":[98],"an":[99],"inference":[100],"speed":[101],"boost":[102],"over":[103],"three":[104],"times":[105],"standard":[109],"Masked":[110],"Frame":[111],"approach.":[113],"Finally,":[114],"evaluate":[116],"different":[117],"extending":[120],"MoVQ":[122],"image":[123],"autoencoder":[124],"video":[127],"domain.":[128],"The":[129],"experimental":[130],"results":[131],"show":[132],"model":[135,143,152],"with":[136,144],"proposed":[138],"modifications":[139],"strongly":[140],"outperforms":[141],"classical":[145],"blocks":[146],"quantitatively":[147],"qualitatively.":[149],"Our":[150],"final":[151],"is":[153],"available":[154],"here:":[155],"<uri":[156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/ai-forever/KandinskyVideo</uri>.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
