{"id":"https://openalex.org/W4392411986","doi":"https://doi.org/10.1109/ijcb57857.2023.10448749","title":"Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation","display_name":"Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4392411986","doi":"https://doi.org/10.1109/ijcb57857.2023.10448749"},"language":"en","primary_location":{"id":"doi:10.1109/ijcb57857.2023.10448749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb57857.2023.10448749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Joint Conference on Biometrics (IJCB)","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/A5023639280","display_name":"Md Mahedi Hasan","orcid":"https://orcid.org/0000-0002-6337-3571"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Mahedi Hasan","raw_affiliation_strings":["West Virginia University,Morgantown,West Virginia,USA","West Virginia University, Morgantown, West Virginia, USA"],"affiliations":[{"raw_affiliation_string":"West Virginia University,Morgantown,West Virginia,USA","institution_ids":["https://openalex.org/I12097938"]},{"raw_affiliation_string":"West Virginia University, Morgantown, West Virginia, USA","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021852735","display_name":"Nasser M. Nasrabadi","orcid":"https://orcid.org/0000-0001-8730-627X"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nasser Nasrabadi","raw_affiliation_strings":["West Virginia University,Morgantown,West Virginia,USA","West Virginia University, Morgantown, West Virginia, USA"],"affiliations":[{"raw_affiliation_string":"West Virginia University,Morgantown,West Virginia,USA","institution_ids":["https://openalex.org/I12097938"]},{"raw_affiliation_string":"West Virginia University, Morgantown, West Virginia, USA","institution_ids":["https://openalex.org/I12097938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023639280"],"corresponding_institution_ids":["https://openalex.org/I12097938"],"apc_list":null,"apc_paid":null,"fwci":0.3777,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6250832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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":0.9988999962806702,"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.7530150413513184},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.7128363847732544},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6654167175292969},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.5858762860298157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43513017892837524},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38402023911476135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3748255670070648},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35277098417282104},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3412644863128662},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06491300463676453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530150413513184},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.7128363847732544},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6654167175292969},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.5858762860298157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43513017892837524},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38402023911476135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3748255670070648},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35277098417282104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3412644863128662},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06491300463676453},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb57857.2023.10448749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb57857.2023.10448749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1834627138","https://openalex.org/W1921523184","https://openalex.org/W1966572524","https://openalex.org/W1993741228","https://openalex.org/W2034829813","https://openalex.org/W2064675550","https://openalex.org/W2131774270","https://openalex.org/W2194775991","https://openalex.org/W2507235960","https://openalex.org/W2793708128","https://openalex.org/W2894786240","https://openalex.org/W2894964039","https://openalex.org/W2962964995","https://openalex.org/W2963626105","https://openalex.org/W2963882743","https://openalex.org/W2963966654","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2969985801","https://openalex.org/W2978017171","https://openalex.org/W2980088508","https://openalex.org/W2985380233","https://openalex.org/W3015686580","https://openalex.org/W3104526144","https://openalex.org/W3113043394","https://openalex.org/W3120992250","https://openalex.org/W3167584510","https://openalex.org/W3169129566","https://openalex.org/W3174194560","https://openalex.org/W3177224328","https://openalex.org/W3184735396","https://openalex.org/W3202738183","https://openalex.org/W4312402191","https://openalex.org/W4312409772","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6640185926","https://openalex.org/W6726497184","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6768851824","https://openalex.org/W6780226713","https://openalex.org/W6791353385","https://openalex.org/W6798805250"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2256933480","https://openalex.org/W2027854990","https://openalex.org/W2132337154","https://openalex.org/W2384651879","https://openalex.org/W2985118265"],"abstract_inverted_index":{"We":[0,185],"introduce":[1],"caption-guided":[2],"face":[3,17,34,45,193],"recognition":[4,18,194],"(CGFR)":[5],"as":[6,47,75],"a":[7,48,87,111,114,134,165,181],"new":[8],"framework":[9,190,209],"to":[10,23,55],"improve":[11],"the":[12,56,59,62,67,100,119,125,142,146,152,158,171,187,204,212],"performance":[13,63,202,213],"of":[14,50,58,145,161,214],"commercial-off-the-shelf":[15],"(COTS)":[16],"(FR)":[19],"systems.":[20],"In":[21,82],"contrast":[22],"combining":[24],"soft":[25],"biometrics":[26],"(e.g.,":[27],"facial":[28,41,70],"marks,":[29],"gender,":[30],"and":[31,69,104,113,121,127,169,173,197,199,220],"age)":[32],"with":[33,164,176],"images,":[35],"in":[36,78,216],"this":[37,83,95],"work,":[38],"we":[39,85,132],"use":[40],"descriptions":[42],"provided":[43],"by":[44,64,97,150,179],"examiners":[46],"piece":[49],"auxiliary":[51],"information.":[52],"However,":[53],"due":[54],"heterogeneity":[57],"modalities,":[60],"improving":[61,118],"directly":[65],"fusing":[66],"textual":[68,128,135,143,162],"features":[71,144,163,178],"is":[72],"very":[73],"challenging,":[74],"both":[76,217],"lie":[77],"different":[79],"embedding":[80],"spaces.":[81],"paper,":[84],"propose":[86],"contextual":[88,153],"feature":[89,136],"aggregation":[90],"module":[91,138,156],"(CFAM)":[92],"that":[93,140],"addresses":[94],"issue":[96],"effectively":[98],"exploiting":[99],"fine-grained":[101],"word-region":[102],"interaction":[103],"global":[105],"image-caption":[106],"association.":[107],"Specifically,":[108],"CFAM":[109],"adopts":[110],"self-attention":[112],"cross-attention":[115],"scheme":[116],"for":[117],"intra-modality":[120],"inter-modality":[122],"relationship":[123],"between":[124],"image":[126],"features,":[129],"respectively.":[130],"Additionally,":[131],"design":[133],"refinement":[137],"(TFRM)":[139],"refines":[141],"pre-trained":[147],"BERT":[148],"encoder":[149],"updating":[151],"embeddings.":[154],"This":[155],"enhances":[157],"discriminative":[159],"power":[160],"cross-modal":[166],"projection":[167],"loss":[168],"realigns":[170],"word":[172],"caption":[174],"embeddings":[175],"visual":[177],"incorporating":[180],"visual-semantic":[182],"alignment":[183],"loss.":[184],"implemented":[186],"proposed":[188],"CGFR":[189],"on":[191,203],"two":[192],"models":[195],"(ArcFace":[196],"AdaFace)":[198],"evaluated":[200],"its":[201],"Multi-Modal":[205],"CelebA-HQ":[206],"dataset.":[207],"Our":[208],"significantly":[210],"improves":[211],"ArcFace":[215],"1:1":[218],"verification":[219],"1:N":[221],"identification":[222],"protocol.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}