{"id":"https://openalex.org/W4393055587","doi":"https://doi.org/10.1109/iccv51701.2025.01058","title":"FaceXFormer: A Unified Transformer for Facial Analysis","display_name":"FaceXFormer: A Unified Transformer for Facial Analysis","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4393055587","doi":"https://doi.org/10.1109/iccv51701.2025.01058"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.12960","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112780566","display_name":"Kartik Narayan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Narayan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004330920","display_name":"Vibashan VS","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vibashan VS","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102762707","display_name":"Rama Chellappa","orcid":"https://orcid.org/0000-0002-7638-1650"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rama Chellappa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004716468","display_name":"Vishal M. Patel","orcid":"https://orcid.org/0000-0002-5239-692X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishal M. Patel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1631,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90655965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11369","last_page":"11382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9890999794006348,"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":0.9890999794006348,"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/transformer","display_name":"Transformer","score":0.5403251051902771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4415290951728821},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17360129952430725},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1581137776374817},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05899745225906372}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5403251051902771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4415290951728821},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17360129952430725},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1581137776374817},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05899745225906372}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.12960","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.12960","pdf_url":"https://arxiv.org/pdf/2403.12960","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2403.12960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.12960","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.12960","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.12960","pdf_url":"https://arxiv.org/pdf/2403.12960","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6238449368","display_name":null,"funder_award_id":"2022-21102100005","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G7051650518","display_name":null,"funder_award_id":"2022-21102100005","funder_id":"https://openalex.org/F4320312530","funder_display_name":"Office of the Director of National Intelligence"}],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393055587.pdf","grobid_xml":"https://content.openalex.org/works/W4393055587.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"In":[0,62],"this":[1],"work,":[2],"we":[3,90,143],"introduce":[4,91],"FaceXFormer,":[5],"an":[6],"end-to-end":[7],"unified":[8,85],"transformer":[9],"model":[10,176],"capable":[11,177],"of":[12,147,150,169,178],"performing":[13],"ten":[14,120,180],"facial":[15,39,114,181],"analysis":[16,49,182],"tasks":[17,23,183],"within":[18,83],"a":[19,66,76,84,93,97,162],"single":[20],"framework.":[21],"These":[22],"include":[24],"face":[25,42,45,48,105,122],"parsing,":[26],"landmark":[27],"detection,":[28],"head":[29],"pose":[30],"estimation,":[31,38],"attribute":[32],"prediction,":[33],"age,":[34],"gender,":[35],"and":[36,44,55,60,106,112,125,131,160],"race":[37],"expression":[40],"recognition,":[41,43],"visibility.":[46],"Traditional":[47],"approaches":[50],"rely":[51],"on":[52,119,152],"task-specific":[53],"architectures":[54],"pre-processing":[56],"techniques,":[57],"limiting":[58],"scalability":[59],"integration.":[61],"contrast,":[63],"FaceXFormer":[64,118,151,172],"employs":[65],"transformer-based":[67],"encoder-decoder":[68],"architecture,":[69],"where":[70],"each":[71],"task":[72,107],"is":[73,173],"represented":[74],"as":[75],"learnable":[77],"token,":[78],"enabling":[79],"seamless":[80],"multi-task":[81,132],"processing":[82],"model.":[86],"To":[87,166],"enhance":[88],"efficiency,":[89],"FaceX,":[92],"lightweight":[94],"decoder":[95],"with":[96],"novel":[98],"bi-directional":[99],"cross-attention":[100],"mechanism,":[101],"which":[102],"jointly":[103],"processes":[104],"tokens":[108],"to":[109],"learn":[110],"robust":[111],"generalized":[113],"representations.":[115],"We":[116],"train":[117],"diverse":[121],"perception":[123],"datasets":[124],"evaluate":[126],"it":[127],"against":[128],"both":[129],"specialized":[130],"models":[133],"across":[134],"multiple":[135],"benchmarks,":[136],"demonstrating":[137],"state-of-the-art":[138],"or":[139],"competitive":[140],"performance.":[141],"Additionally,":[142],"analyze":[144],"the":[145,167,174],"impact":[146],"various":[148],"components":[149],"performance,":[153],"assess":[154],"real-world":[155],"robustness":[156],"in":[157],"\"in-the-wild\"":[158],"settings,":[159],"conduct":[161],"computational":[163],"performance":[164,187],"evaluation.":[165],"best":[168],"our":[170],"knowledge,":[171],"first":[175],"handling":[179],"while":[184],"maintaining":[185],"real-time":[186],"at":[188],"33.21":[189],"FPS.":[190],"Code:":[191],"https://github.com/Kartik-3004/facexformer":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}