{"id":"https://openalex.org/W4417125333","doi":"https://doi.org/10.1145/3757377.3763949","title":"Proteus-ID: ID-Consistent and Motion-Coherent Video Customization","display_name":"Proteus-ID: ID-Consistent and Motion-Coherent Video Customization","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417125333","doi":"https://doi.org/10.1145/3757377.3763949"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","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/A5007638992","display_name":"Guiyu Zhang","orcid":"https://orcid.org/0009-0007-0807-285X"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guiyu Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100578178","display_name":"Shi Chen","orcid":"https://orcid.org/0009-0005-5077-0470"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Shi","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109490779","display_name":"Zijian Jiang","orcid":"https://orcid.org/0009-0009-1607-1640"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Jiang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113415276","display_name":"Xunzhi Xiang","orcid":"https://orcid.org/0009-0006-9629-0410"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunzhi Xiang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021942462","display_name":"Jingjing Qian","orcid":"https://orcid.org/0000-0001-6676-6832"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Qian","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083443210","display_name":"Shaoshuai Shi","orcid":"https://orcid.org/0000-0003-2558-181X"},"institutions":[{"id":"https://openalex.org/I4210090512","display_name":"Guangzhou Experimental Station","ror":"https://ror.org/00f2c2516","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210090512","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoshuai Shi","raw_affiliation_strings":["DiDi Global, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"DiDi Global, Guangzhou, China","institution_ids":["https://openalex.org/I4210090512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100392353","display_name":"Li Jiang","orcid":"https://orcid.org/0000-0001-7058-6957"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5007638992"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":1.2784,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86308807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9059000015258789,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9059000015258789,"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/T11448","display_name":"Face recognition and analysis","score":0.02969999983906746,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.015399999916553497,"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/identity","display_name":"Identity (music)","score":0.6464999914169312},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6310999989509583},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5530999898910522},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.508400022983551},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5034000277519226},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.43860000371932983},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.42559999227523804},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41440001130104065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531999945640564},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6464999914169312},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6310999989509583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559999942779541},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.508400022983551},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4050000011920929},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2906000018119812},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1755205674","https://openalex.org/W1901129140","https://openalex.org/W2183341477","https://openalex.org/W2605982830","https://openalex.org/W2963876278","https://openalex.org/W2964309882","https://openalex.org/W2969985801","https://openalex.org/W3035693354","https://openalex.org/W3083765505","https://openalex.org/W3109908659","https://openalex.org/W3153469116","https://openalex.org/W4214922754","https://openalex.org/W4312933868","https://openalex.org/W4385489997","https://openalex.org/W4386076027","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4402703076","https://openalex.org/W4402704510","https://openalex.org/W4402727092","https://openalex.org/W4402727613","https://openalex.org/W4402727853","https://openalex.org/W4402753339","https://openalex.org/W4404527320","https://openalex.org/W4404900558","https://openalex.org/W4409263204","https://openalex.org/W4412587918","https://openalex.org/W4413147351","https://openalex.org/W4415797654","https://openalex.org/W4415798255"],"related_works":[],"abstract_inverted_index":{"Video":[0],"identity":[1,31,85,113,183,196],"customization":[2],"seeks":[3],"to":[4,93],"synthesize":[5],"realistic,":[6],"temporally":[7],"coherent":[8,91],"videos":[9],"of":[10],"a":[11,15,20,57,70,83,88,104,128,155,191],"specific":[12],"subject,":[13],"given":[14],"single":[16],"reference":[17],"image":[18],"and":[19,39,41,63,79,97,164,170,187],"text":[21,185],"prompt.":[22],"This":[23],"task":[24],"presents":[25],"two":[26],"core":[27],"challenges:":[28],"(1)":[29],"maintaining":[30],"consistency":[32],"while":[33],"aligning":[34],"with":[35],"the":[36,94],"described":[37],"appearance":[38],"actions,":[40],"(2)":[42],"generating":[43],"natural,":[44],"fluid":[45],"motion":[46,139,142,188],"without":[47,144],"unrealistic":[48],"stiffness.":[49],"To":[50,148],"address":[51],"these":[52],"challenges,":[53],"we":[54,68,102,122,152],"introduce":[55],"Proteus-ID,":[56],"novel":[58],"diffusion-based":[59],"framework":[60],"for":[61,162,172,194],"identity-consistent":[62],"motion-coherent":[64],"video":[65,195],"customization.":[66,197],"First,":[67],"propose":[69,123],"Multimodal":[71],"Identity":[72,106],"Fusion":[73],"(MIF)":[74],"module":[75],"that":[76,110,132,177],"unifies":[77],"visual":[78],"textual":[80],"cues":[81],"into":[82],"joint":[84],"representation":[86],"using":[87],"Q-Former,":[89],"providing":[90],"guidance":[92],"diffusion":[95],"model":[96],"eliminating":[98],"modality":[99],"imbalance.":[100],"Second,":[101],"present":[103],"Time-Aware":[105],"Injection":[107],"(TAII)":[108],"mechanism":[109],"dynamically":[111],"modulates":[112],"conditioning":[114],"across":[115],"denoising":[116],"steps,":[117],"improving":[118],"fine-detail":[119],"reconstruction.":[120],"Third,":[121],"Adaptive":[124],"Motion":[125],"Learning":[126],"(AML),":[127],"motion-aware":[129],"optimization":[130],"strategy":[131],"reweights":[133],"training":[134,163],"loss":[135],"based":[136],"on":[137],"optical-flow-derived":[138],"heatmaps,":[140],"enhancing":[141],"realism":[143],"requiring":[145],"additional":[146],"inputs.":[147],"support":[149],"this":[150],"task,":[151],"construct":[153],"Proteus-Bench,":[154],"high-quality":[156],"dataset":[157],"comprising":[158],"200K":[159],"curated":[160],"clips":[161],"150":[165],"individuals":[166],"from":[167],"diverse":[168],"professions":[169],"ethnicities":[171],"evaluation.":[173],"Extensive":[174],"experiments":[175],"demonstrate":[176],"Proteus-ID":[178],"outperforms":[179],"prior":[180],"methods":[181],"in":[182],"preservation,":[184],"alignment,":[186],"quality,":[189],"establishing":[190],"new":[192],"benchmark":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-08T00:00:00"}