{"id":"https://openalex.org/W4392305749","doi":"https://doi.org/10.5220/0012312200003636","title":"DiT-Head: High Resolution Talking Head Synthesis Using Diffusion Transformers","display_name":"DiT-Head: High Resolution Talking Head Synthesis Using Diffusion Transformers","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392305749","doi":"https://doi.org/10.5220/0012312200003636"},"language":"en","primary_location":{"id":"doi:10.5220/0012312200003636","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012312200003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0012312200003636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104251075","display_name":"Aaron Mir","orcid":null},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Aaron Mir","raw_affiliation_strings":["Artificial Intelligence Research Centre, Department of Computer Science, City, University of London, Northampton Square, EC1V 0HB, London, U.K., --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Centre, Department of Computer Science, City, University of London, Northampton Square, EC1V 0HB, London, U.K., --- Select a Country ---","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031842436","display_name":"Eduardo Alonso","orcid":"https://orcid.org/0000-0002-3306-695X"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eduardo Alonso","raw_affiliation_strings":["Artificial Intelligence Research Centre, Department of Computer Science, City, University of London, Northampton Square, EC1V 0HB, London, U.K., --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Centre, Department of Computer Science, City, University of London, Northampton Square, EC1V 0HB, London, U.K., --- Select a Country ---","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006233243","display_name":"Esther Mondrag\u00f3n","orcid":"https://orcid.org/0000-0003-4180-1261"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Esther Mondrag\u00f3n","raw_affiliation_strings":["Artificial Intelligence Research Centre, Department of Computer Science, City, University of London, Northampton Square, EC1V 0HB, London, U.K., --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Centre, Department of Computer Science, City, University of London, Northampton Square, EC1V 0HB, London, U.K., --- Select a Country ---","institution_ids":["https://openalex.org/I180825142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104251075"],"corresponding_institution_ids":["https://openalex.org/I180825142"],"apc_list":null,"apc_paid":null,"fwci":1.6942,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82916304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9369000196456909,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9369000196456909,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6238644123077393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5661101341247559},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4949292540550232},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2612416744232178},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18431413173675537},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11273571848869324},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09834063053131104}],"concepts":[{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6238644123077393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5661101341247559},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4949292540550232},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2612416744232178},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18431413173675537},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11273571848869324},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09834063053131104},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0012312200003636","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012312200003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.city.ac.uk:31834","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/e=2Ealonso.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/31834/1/Mir_Alonso_Mondragon.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"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":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.5220/0012312200003636","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012312200003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,45,61],"propose":[1],"a":[2,20,28,92,104],"novel":[3],"talking":[4,58],"head":[5,59],"synthesis":[6],"pipeline":[7],"called":[8],"\u201dDiT-Head,\u201d":[9],"which":[10],"is":[11,33],"based":[12],"on":[13],"diffusion":[14,29],"transformers":[15],"and":[16,35,47,52,76,101,109],"uses":[17],"audio":[18],"as":[19],"condition":[21],"to":[22,38,88,115],"drive":[23],"the":[24,82],"denoising":[25],"process":[26],"of":[27,57,73,84,95,107],"model.":[30],"Our":[31,79],"method":[32],"scalable":[34],"can":[36,66],"generalise":[37],"multiple":[39],"identities":[40],"while":[41],"producing":[42],"high-quality":[43],"results.":[44],"train":[46],"evaluate":[48],"our":[49,64,85,110,116],"proposed":[50,86],"approach":[51,87],"compare":[53],"against":[54],"existing":[55],"methods":[56,70],"synthesis.":[60],"show":[62],"that":[63],"model":[65],"compete":[67],"with":[68],"these":[69],"in":[71],"terms":[72],"visual":[74],"quality":[75],"lip-sync":[77],"accuracy.":[78],"results":[80,108],"highlight":[81],"potential":[83],"be":[89],"used":[90],"for":[91],"wide":[93],"range":[94],"applications":[96],"including":[97],"virtual":[98],"assistants,":[99],"entertainment,":[100],"education.":[102],"For":[103],"video":[105],"demonstration":[106],"user":[111],"study,":[112],"please":[113],"refer":[114],"supplementary":[117],"material.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}