{"id":"https://openalex.org/W4405275045","doi":"https://doi.org/10.1109/iccv51701.2025.01508","title":"STIV: Scalable Text and Image Conditioned Video Generation","display_name":"STIV: Scalable Text and Image Conditioned Video Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405275045","doi":"https://doi.org/10.1109/iccv51701.2025.01508"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01508","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/2412.07730","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109734902","display_name":"Zongyu Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongyu Lin","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602460","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0003-2018-7004"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418493","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-7453-3147"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021836162","display_name":"Jiasen L\u00fc","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiasen Lu","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505071","display_name":"Wenze Hu","orcid":"https://orcid.org/0000-0001-5516-7092"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenze Hu","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112924211","display_name":"Tsu-Jui Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsu-Jui Fu","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jesse Allardice","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse Allardice","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084288655","display_name":"Zhengfeng Lai","orcid":"https://orcid.org/0000-0002-2984-7913"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengfeng Lai","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079245916","display_name":"Liangchen Song","orcid":"https://orcid.org/0000-0002-8366-5088"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangchen Song","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385147","display_name":"Bowen Zhang","orcid":"https://orcid.org/0000-0002-7919-1748"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Zhang","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101475530","display_name":"Chen Cha","orcid":"https://orcid.org/0000-0001-7275-1231"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cha Chen","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026898376","display_name":"Yiran Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiran Fei","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028843823","display_name":"Lezhi Li","orcid":"https://orcid.org/0000-0001-5872-0842"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lezhi Li","raw_affiliation_strings":["Apple,Cupertino,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple,Cupertino,CA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025213473","display_name":"Yizhou Sun","orcid":"https://orcid.org/0000-0003-1812-6843"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinfei Yang","raw_affiliation_strings":["University of California, Los Angeles,Los Angeles,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles,Los Angeles,CA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025213473","display_name":"Yizhou Sun","orcid":"https://orcid.org/0000-0003-1812-6843"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhou Sun","raw_affiliation_strings":["University of California, Los Angeles,Los Angeles,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles,Los Angeles,CA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112656212","display_name":"Yinfei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["University of California, Los Angeles,Los Angeles,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles,Los Angeles,CA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16249","last_page":"16259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9811000227928162,"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":0.9811000227928162,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9574000239372253,"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":0.9383000135421753,"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":0.6445611715316772},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6288393139839172},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5981446504592896},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4848157465457916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42674803733825684},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36050134897232056},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08585149049758911}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6445611715316772},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6288393139839172},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5981446504592896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4848157465457916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42674803733825684},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36050134897232056},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08585149049758911}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01508","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:2412.07730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.07730","pdf_url":"https://arxiv.org/pdf/2412.07730","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.07730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.07730","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2412.07730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.07730","pdf_url":"https://arxiv.org/pdf/2412.07730","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317469","display_name":"Apple","ror":"https://ror.org/059hsda18"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0,165],"field":[1],"of":[2,25,43,173],"video":[3,59,113,121,192,209],"generation":[4,60,193,210],"has":[5],"made":[6],"remarkable":[7],"advancements,":[8],"yet":[9],"there":[10],"remains":[11],"a":[12,16,35,54,70,82,170,184],"pressing":[13],"need":[14],"for":[15,189],"clear,":[17],"systematic":[18],"recipe":[19,188],"that":[20,38],"can":[21,104],"guide":[22],"the":[23,41],"development":[24],"robust":[26],"and":[27,48,56,97,119,131,156,163,186,201,207],"scalable":[28,57],"models.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,195],"present":[34],"comprehensive":[36,125],"study":[37],"systematically":[39],"explores":[40],"interplay":[42],"model":[44,143,167],"architectures,":[45],"training":[46],"recipes,":[47],"data":[49],"curation":[50],"strategies,":[51],"culminating":[52],"in":[53],"simple":[55,139],"text-image-conditioned":[58],"method,":[61],"named":[62],"STIV.":[63],"Our":[64],"framework":[65],"integrates":[66],"image":[67],"condition":[68],"into":[69],"Diffusion":[71],"Transformer":[72],"(DiT)":[73],"through":[74],"frame":[75,115],"replacement,":[76],"while":[77],"incorporating":[78],"text":[79],"conditioning":[80],"via":[81],"joint":[83],"image-text":[84],"conditional":[85],"classifier-free":[86],"guidance.":[87],"This":[88],"design":[89],"enables":[90],"STIV":[91,103,133],"to":[92,108,197],"perform":[93],"both":[94,153],"text-to-video":[95],"(T2V)":[96],"text-image-to-video":[98],"(TI2V)":[99],"tasks":[100],"simultaneously.":[101],"Additionally,":[102],"be":[105],"easily":[106],"extended":[107],"various":[109],"applications,":[110],"such":[111],"as":[112],"prediction,":[114],"interpolation,":[116],"multi-view":[117],"generation,":[118,122],"long":[120],"etc.":[123],"With":[124],"ablation":[126],"studies":[127],"on":[128,149,175],"T2I,":[129],"T2V,":[130,151],"TI2V,":[132],"demonstrate":[134],"strong":[135],"performance,":[136],"despite":[137],"its":[138],"design.":[140],"An":[141],"8.7B":[142],"with":[144],"512":[145,180],"resolution":[146],"achieves":[147,169],"83.1":[148],"VBench":[150,176],"surpassing":[152],"leading":[154],"open":[155],"closed-source":[157],"models":[158],"like":[159],"CogVideoX-5B,":[160],"Pika,":[161],"Kling,":[162],"Gen-3.":[164],"same-sized":[166],"also":[168],"state-of-the-art":[171],"result":[172],"90.1":[174],"I2V":[177],"task":[178],"at":[179],"resolution.":[181],"By":[182],"providing":[183],"transparent":[185],"extensible":[187],"building":[190],"cutting-edge":[191],"models,":[194],"aim":[196],"empower":[198],"future":[199],"research":[200],"accelerate":[202],"progress":[203],"toward":[204],"more":[205],"versatile":[206],"reliable":[208],"solutions.":[211]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}
