{"id":"https://openalex.org/W4415537798","doi":"https://doi.org/10.1145/3746027.3754943","title":"LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation","display_name":"LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537798","doi":"https://doi.org/10.1145/3746027.3754943"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754943","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754943","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":"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/A5034669631","display_name":"Wenhui Song","orcid":"https://orcid.org/0009-0005-6410-5447"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenhui Song","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028780369","display_name":"Hanhui Li","orcid":"https://orcid.org/0000-0002-9838-6532"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanhui Li","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076907782","display_name":"Jiehui Huang","orcid":"https://orcid.org/0000-0002-3099-2886"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiehui Huang","raw_affiliation_strings":["Hong Kong University of Science and Technology (HKUST), Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (HKUST), Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043898209","display_name":"Panwen Hu","orcid":"https://orcid.org/0000-0001-6183-6598"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Panwen Hu","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhao Cheng","orcid":"https://orcid.org/0000-0003-3772-9789"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Cheng","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Long Chen","orcid":"https://orcid.org/0009-0001-8083-0340"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101236085","display_name":"Yiqiang Yan","orcid":"https://orcid.org/0009-0008-7709-0602"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqiang Yan","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5034669631"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29672662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9529","last_page":"9538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"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/autoregressive-model","display_name":"Autoregressive model","score":0.667900025844574},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4341999888420105},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4140999913215637},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.36250001192092896},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.359499990940094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34119999408721924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077999711036682},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.667900025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4702000021934509},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4140999913215637},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32019999623298645},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25049999356269836},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754943","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754943","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/G3856460836","display_name":null,"funder_award_id":"62372482","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2886934227","https://openalex.org/W2969985801","https://openalex.org/W4360884927","https://openalex.org/W4386076280","https://openalex.org/W4402660110","https://openalex.org/W4404527320"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"LaVieID,":[5],"a":[6,9,70,100],"novel":[7],"local":[8,71,83],"utoregressive":[10],"vi":[11],"deo":[12],"diffusion":[13,45],"framework":[14],"designed":[15],"to":[16,30,73,94,108,129],"tackle":[17],"the":[18,32,39,56],"challenging":[19],"id":[20],"entity-preserving":[21],"text-to-video":[22],"task.":[23],"The":[24],"key":[25],"idea":[26],"of":[27,34,44,61,81],"LaVieID":[28,68,107,142],"is":[29,104],"mitigate":[31],"loss":[33],"identity":[35,139],"information":[36],"inherent":[37],"in":[38,65],"stochastic":[40],"global":[41,57],"generation":[42],"process":[43],"transformers":[46],"(DiTs)":[47],"from":[48],"both":[49],"spatial":[50],"and":[51,58,91,148,154],"temporal":[52,101,127],"perspectives.":[53],"Specifically,":[54],"unlike":[55],"unstructured":[59],"modeling":[60],"facial":[62,84,97],"latent":[63,76,111,119],"states":[64,77],"existing":[66],"DiTs,":[67],"introduces":[69],"router":[72],"explicitly":[74],"represent":[75],"by":[78],"weighted":[79],"combinations":[80],"fine-grained":[82],"structures.":[85],"This":[86,116],"alleviates":[87],"undesirable":[88],"feature":[89],"interference":[90],"encourages":[92],"DiTs":[93],"capture":[95],"distinctive":[96],"characteristics.":[98],"Furthermore,":[99],"autoregressive":[102],"module":[103,117],"integrated":[105],"into":[106,122],"refine":[109],"denoised":[110],"tokens":[112,120],"before":[113],"video":[114],"decoding.":[115],"divides":[118],"temporally":[121],"chunks,":[123],"exploiting":[124],"their":[125],"long-range":[126],"dependencies":[128],"predict":[130],"biases":[131],"for":[132],"rectifying":[133],"tokens,":[134],"thereby":[135],"significantly":[136],"enhancing":[137],"inter-frame":[138],"consistency.":[140],"Consequently,":[141],"can":[143],"generate":[144],"high-fidelity":[145],"personalized":[146],"videos":[147],"achieve":[149],"state-of-the-art":[150],"performance.":[151],"Our":[152],"code":[153],"models":[155],"are":[156],"available":[157],"at":[158],"https://github.com/ssugarwh/LaVieID.":[159]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}