{"id":"https://openalex.org/W4403792326","doi":"https://doi.org/10.1145/3664647.3680635","title":"DiffTV: Identity-Preserved Thermal-to-Visible Face Translation via Feature Alignment and Dual-Stage Conditions","display_name":"DiffTV: Identity-Preserved Thermal-to-Visible Face Translation via Feature Alignment and Dual-Stage Conditions","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792326","doi":"https://doi.org/10.1145/3664647.3680635"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680635","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680635","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3680635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102212132","display_name":"Jingyu Lin","orcid":"https://orcid.org/0000-0003-1897-4148"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jingyu Lin","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1897-4148","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045219220","display_name":"Zhao GuiQin","orcid":"https://orcid.org/0000-0001-7029-9755"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiqin Zhao","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7029-9755","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090060116","display_name":"Jing Xu","orcid":"https://orcid.org/0000-0001-7110-5377"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Xu","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7110-5377","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603104","display_name":"Guoli Wang","orcid":"https://orcid.org/0000-0001-8685-3968"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoli Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8685-3968","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013380680","display_name":"Zejin Wang","orcid":"https://orcid.org/0000-0002-0073-4122"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejin Wang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0073-4122","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084047603","display_name":"Antitza Dantcheva","orcid":"https://orcid.org/0000-0003-0107-7029"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antitza Dantcheva","raw_affiliation_strings":["INRIA, Valbonne, France"],"raw_orcid":"https://orcid.org/0000-0003-0107-7029","affiliations":[{"raw_affiliation_string":"INRIA, Valbonne, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021845515","display_name":"Lan Du","orcid":"https://orcid.org/0000-0002-9925-0223"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lan Du","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9925-0223","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072508861","display_name":"Cunjian Chen","orcid":"https://orcid.org/0000-0002-2926-9762"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Cunjian Chen","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2926-9762","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10930","last_page":"10938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9923999905586243,"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/dual","display_name":"Dual (grammatical number)","score":0.6845674514770508},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6615790128707886},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5823767185211182},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5808109045028687},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.5613136887550354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5351736545562744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5067539811134338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3962634801864624},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11001753807067871},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1095932126045227},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07916489243507385},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07426711916923523},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05667829513549805}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6845674514770508},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6615790128707886},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5823767185211182},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5808109045028687},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.5613136887550354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5351736545562744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5067539811134338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3962634801864624},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11001753807067871},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1095932126045227},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07916489243507385},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07426711916923523},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05667829513549805},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3664647.3680635","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680635","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:monash.edu:openaire/3c4f823b-9754-4c5f-99f0-4e83bc2b2d73","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/3c4f823b-9754-4c5f-99f0-4e83bc2b2d73","pdf_url":null,"source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lin, J, Zhao, G, Xu, J, Wang, G, Wang, Z, Dantcheva, A, Du, L & Chen, C 2024, DiffTV : Identity-Preserved Thermal-to-Visible Face Translation via Feature Alignment and Dual-Stage Conditions. in Y Luo, T Do & Y Yan (eds), Proceedings of the 32nd ACM International Conference on Multimedia. Association for Computing Machinery (ACM), New York NY USA, pp. 10930-10938, ACM International Conference on Multimedia 2024, Melbourne, Victoria, Australia, 28/10/24. https://doi.org/10.1145/3664647.3680635","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-04916919v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04916919v1/document","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://dl.acm.org/doi/proceedings/10.1145/3664647","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3664647.3680635","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680635","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2904856314","https://openalex.org/W2940551087","https://openalex.org/W2962785568","https://openalex.org/W2962898354","https://openalex.org/W2963073614","https://openalex.org/W2969985801","https://openalex.org/W2990138404","https://openalex.org/W2995936506","https://openalex.org/W3010093963","https://openalex.org/W3021195052","https://openalex.org/W3023702633","https://openalex.org/W3034956129","https://openalex.org/W3093222528","https://openalex.org/W3102910076","https://openalex.org/W3119532581","https://openalex.org/W3153171492","https://openalex.org/W3159018159","https://openalex.org/W3161402421","https://openalex.org/W3186754109","https://openalex.org/W4312533752","https://openalex.org/W4312933868","https://openalex.org/W4312951237","https://openalex.org/W4319299887","https://openalex.org/W4321020777","https://openalex.org/W4379928193","https://openalex.org/W4386076368","https://openalex.org/W4386076617","https://openalex.org/W4389539696","https://openalex.org/W4390873054","https://openalex.org/W4390873689"],"related_works":["https://openalex.org/W2329386257","https://openalex.org/W2503350049","https://openalex.org/W2397616145","https://openalex.org/W2397320258","https://openalex.org/W4324058133","https://openalex.org/W648618910","https://openalex.org/W4393624937","https://openalex.org/W4296658948","https://openalex.org/W3167355683","https://openalex.org/W2132337154"],"abstract_inverted_index":{"The":[0],"thermal-to-visible":[1],"(T2V)":[2],"face":[3,10,50],"translation":[4,89],"task":[5,28],"is":[6,149],"essential":[7],"for":[8,85],"enabling":[9],"verification":[11],"in":[12,143],"low-light":[13],"or":[14],"dark":[15],"conditions":[16],"by":[17],"converting":[18],"thermal":[19,45],"infrared":[20],"faces":[21,29,55],"into":[22],"their":[23],"visible":[24,64,119],"counterparts.":[25],"However,":[26],"this":[27],"two":[30],"primary":[31],"challenges.":[32],"First,":[33],"the":[34,38,41,58,62,77,107,137],"inherent":[35],"differences":[36],"between":[37],"modalities":[39],"hinder":[40],"effective":[42],"use":[43],"of":[44,61,140],"information":[46,129],"to":[47,130],"guide":[48,131],"RGB":[49,54],"reconstruction.":[51],"Second,":[52],"translated":[53],"often":[56],"lack":[57],"identity":[59,115,147],"details":[60],"corresponding":[63],"faces,":[65],"such":[66],"as":[67],"skin":[68],"color.":[69],"To":[70],"tackle":[71],"these":[72],"challenges,":[73],"we":[74],"introduce":[75],"DiffTV,":[76,141],"first":[78],"Latent":[79],"Diffusion":[80],"Model":[81],"(LDM)":[82],"specifically":[83],"designed":[84],"T2V":[86],"facial":[87],"image":[88],"with":[90,118],"a":[91,99,122],"focus":[92],"on":[93],"preserving":[94],"identity.":[95],"Our":[96],"approach":[97],"proposes":[98],"novel":[100],"heterogeneous":[101],"feature":[102],"alignment":[103],"strategy":[104,126],"that":[105],"bridges":[106],"modal":[108],"gap":[109],"and":[110],"extracts":[111],"both":[112],"coarse-and":[113],"fine-grained":[114],"features":[116],"consistent":[117],"images.":[120],"Furthermore,":[121],"dual-stage":[123],"condition":[124],"injection":[125],"introduces":[127],"control":[128],"identity-preserved":[132],"translation.":[133],"Experimental":[134],"results":[135],"demonstrate":[136],"superior":[138],"performance":[139],"particularly":[142],"scenarios":[144],"where":[145],"maintaining":[146],"integrity":[148],"critical.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
