{"id":"https://openalex.org/W4415540873","doi":"https://doi.org/10.1145/3746027.3761988","title":"Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations","display_name":"Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540873","doi":"https://doi.org/10.1145/3746027.3761988"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3761988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3761988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104273091","display_name":"Yuji Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuji Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Tencent YouTu Lab, Shanghai, China","Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-7978-9846","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I183067930"]},{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083232013","display_name":"Moran Li","orcid":"https://orcid.org/0000-0002-8149-1117"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Moran Li","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8149-1117","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101735199","display_name":"Xiaobin Hu","orcid":"https://orcid.org/0000-0002-5764-3096"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Hu","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5764-3096","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054879013","display_name":"Ran Yi","orcid":"https://orcid.org/0000-0003-1858-3358"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Yi","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1858-3358","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8891-6766","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Feng","orcid":"https://orcid.org/0009-0002-4416-4907"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Feng","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-4416-4907","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008990100","display_name":"Weijian Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijian Cao","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-2554-1294","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Tencent YouTu Lab, Shanghai, China","Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6592-8411","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I183067930"]},{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4216-8090","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1653-4341","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"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":"13743","last_page":"13750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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":0.9986000061035156,"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/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5534999966621399},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5486999750137329},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5400000214576721},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.421099990606308},{"id":"https://openalex.org/keywords/spatial-coherence","display_name":"Spatial coherence","score":0.41040000319480896},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.40220001339912415},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37709999084472656},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.3400000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062999844551086},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.41040000319480896},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37709999084472656},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3761988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3761988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2268761546","display_name":null,"funder_award_id":"62302297","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3356995396","display_name":null,"funder_award_id":"YG2023QNA35","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2969985801","https://openalex.org/W3116794818","https://openalex.org/W4214745154","https://openalex.org/W4386075779","https://openalex.org/W4393148714","https://openalex.org/W4402582789","https://openalex.org/W4402660110","https://openalex.org/W4402703076","https://openalex.org/W4404527320"],"related_works":[],"abstract_inverted_index":{"Identity-preserving":[0],"text-to-video":[1],"(IPT2V)":[2],"generation,":[3],"which":[4],"aims":[5],"to":[6,126,141],"create":[7],"high-fidelity":[8],"videos":[9],"with":[10,112],"consistent":[11],"human":[12],"identity,":[13],"has":[14],"become":[15],"crucial":[16],"for":[17,30,78,83],"downstream":[18],"applications.":[19],"However,":[20],"current":[21],"end-to-end":[22],"frameworks":[23],"suffer":[24],"a":[25,65,90],"critical":[26],"spatial-temporal":[27,69],"trade-off:":[28],"optimizing":[29],"spatially":[31],"coherent":[32,128],"layouts":[33,79],"of":[34,56],"key":[35],"elements":[36],"(":[37],"e.g.,":[38],"character":[39],"identity":[40,159],"preservation)":[41],"often":[42],"compromises":[43],"instruction-compliant":[44],"temporal":[45,81,109,133],"smoothness,":[46],"while":[47,131],"prioritizing":[48],"dynamic":[49],"realism":[50],"risks":[51],"disrupting":[52],"the":[53,104,113,118,122,132,136,176],"spatial":[54,76,107,119,129],"coherence":[55],"visual":[57],"structures.":[58],"To":[59],"tackle":[60],"this":[61,168],"issue,":[62],"we":[63],"propose":[64],"simple":[66,169],"yet":[67,170],"effective":[68],"decoupled":[70,97,116],"framework":[71],"that":[72,148],"decomposes":[73],"representations":[74],"into":[75,106],"features":[77,82],"and":[80,95,108,163],"motion":[84,143],"dynamics.":[85],"Specifically,":[86],"our":[87,149,173],"paper":[88],"proposes":[89],"semantic":[91],"prompt":[92,105],"optimization":[93],"mechanism":[94],"stage-wise":[96,115],"generation":[98],"paradigm.":[99],"The":[100],"former":[101],"module":[102],"decouples":[103],"components.":[110],"Aligned":[111],"subsequent":[114],"approach,":[117],"prompts":[120,134],"guide":[121],"text-to-image":[123],"(T2I)":[124],"stage":[125,140],"generate":[127],"features,":[130],"direct":[135],"sequential":[137],"image-to-video":[138],"(I2V)":[139],"ensure":[142],"consistency.":[144],"Experimental":[145],"results":[146],"validate":[147],"approach":[150],"achieves":[151],"excellent":[152],"spatiotemporal":[153],"consistency,":[154],"demonstrating":[155],"outstanding":[156],"performance":[157],"in":[158,179],"preservation,":[160],"text":[161],"relevance,":[162],"video":[164],"quality.":[165],"By":[166],"leveraging":[167],"robust":[171],"mechanism,":[172],"algorithm":[174],"secures":[175],"runner-up":[177],"position":[178],"2025":[180],"ACM":[181],"Multimedia":[182],"Challenge.":[183],"Our":[184],"code":[185],"is":[186],"available":[187],"at":[188],"https://github.com/rain152/IPVG.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
