{"id":"https://openalex.org/W7124429428","doi":"https://doi.org/10.1109/ojcs.2026.3654171","title":"AG-CLIP: Attribute-Guided CLIP for Zero-Shot Fine-Grained Recognition","display_name":"AG-CLIP: Attribute-Guided CLIP for Zero-Shot Fine-Grained Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124429428","doi":"https://doi.org/10.1109/ojcs.2026.3654171"},"language":"en","primary_location":{"id":"doi:10.1109/ojcs.2026.3654171","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2026.3654171","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/ojcs.2026.3654171","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123178518","display_name":"Jamil Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I117222138","display_name":"Abu Dhabi University","ror":"https://ror.org/01r3kjq03","country_code":"AE","type":"education","lineage":["https://openalex.org/I117222138"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Jamil Ahmad","raw_affiliation_strings":["Department of Computer Science and Software Engineering, United Arab Emirates University (UAEU), Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0001-8407-5971","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, United Arab Emirates University (UAEU), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I117222138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075409562","display_name":"Mustaqeem Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I117222138","display_name":"Abu Dhabi University","ror":"https://ror.org/01r3kjq03","country_code":"AE","type":"education","lineage":["https://openalex.org/I117222138"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mustaqeem Khan","raw_affiliation_strings":["Department of Computer Science and Software Engineering, United Arab Emirates University (UAEU), Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, United Arab Emirates University (UAEU), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I117222138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123218591","display_name":"Wail Guiaeab","orcid":null},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wail Guiaeab","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6490-4648","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123214506","display_name":"Abdulmotaleb Elsaddik","orcid":null},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdulmotaleb Elsaddik","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7690-8547","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123215841","display_name":"Giulia De Masi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141120","display_name":"Sorbonne University Abu Dhabi","ror":"https://ror.org/03e1ymy32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210141120"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Giulia De Masi","raw_affiliation_strings":["SAFIR, Sorbonne University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0003-3284-880X","affiliations":[{"raw_affiliation_string":"SAFIR, Sorbonne University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210141120"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fakhri Karray","orcid":"https://orcid.org/0000-0002-4217-1372"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fakhri Karray","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-4217-1372","affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06848999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"365","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2467000037431717,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2467000037431717,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09130000323057175,"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":0.08780000358819962,"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/discriminative-model","display_name":"Discriminative model","score":0.8037999868392944},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5896000266075134},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5493999719619751},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5367000102996826},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5313000082969666},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44130000472068787},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.38929998874664307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34369999170303345},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.328900009393692}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8037999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6783999800682068},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4458000063896179},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ojcs.2026.3654171","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2026.3654171","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05461268v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05461268","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Open Journal of the Computer Society, 2026, pp.1-11. &#x27E8;10.1109/OJCS.2026.3654171&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2026.3654171","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2026.3654171","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"fine-grained":[1,17,120,192],"recognition":[2,193],"is":[3],"challenging":[4],"due":[5],"to":[6,68,77,98,117],"high":[7],"visual":[8,44],"similarities":[9],"between":[10],"classes":[11,121],"and":[12,144,150],"the":[13,47,91,95,142,177],"inferior":[14],"encoding":[15],"of":[16,90,179],"features":[18],"in":[19,194],"embedding":[20],"models.":[21],"In":[22],"this":[23],"work,":[24],"we":[25],"present":[26],"an":[27,35,52,72],"attribute-guided":[28,112],"Contrastive":[29],"Language-Image":[30],"Pre-training":[31],"(AG-CLIP)":[32],"model":[33,60,97],"with":[34,87],"additional":[36,131],"attribute":[37,53,84,182],"encoder.":[38],"Our":[39,111,154],"approach":[40,140],"first":[41],"identifies":[42],"relevant":[43,79],"attributes":[45,64,103,126],"from":[46],"textual":[48],"class":[49],"descriptions":[50],"using":[51],"mining":[54],"module":[55],"leveraging":[56],"a":[57,107,195],"large":[58],"language":[59],"(LLM)":[61],"GPT-4o.":[62],"The":[63,83,173],"are":[65],"then":[66,93],"used":[67],"construct":[69],"prompts":[70],"for":[71,190],"open":[73],"vocabulary":[74],"object/region":[75],"detector":[76],"extract":[78],"corresponding":[80],"image":[81],"regions.":[82],"text,":[85],"along":[86],"focused":[88],"regions":[89],"input,":[92],"guides":[94],"CLIP":[96,116,189],"focus":[99],"on":[100,134,141,165],"these":[101],"discriminative":[102],"during":[104],"fine-tuning":[105,129],"through":[106],"context-attribute":[108],"fusion":[109],"module.":[110],"attention":[113],"mechanism":[114],"allows":[115],"effectively":[118],"disambiguate":[119],"by":[122],"highlighting":[123],"their":[124],"distinctive":[125],"without":[127],"requiring":[128],"or":[130,169],"training":[132],"data":[133],"unseen":[135],"classes.":[136],"We":[137],"evaluate":[138],"our":[139],"CUB-200-2011":[143],"plant":[145],"disease":[146],"datasets,":[147],"achieving":[148],"73.3%":[149],"84.6%":[151],"accuracy,":[152],"respectively.":[153],"method":[155],"achieves":[156],"state-of-the-art":[157],"zero-shot":[158,196],"performance,":[159],"outperforming":[160],"prior":[161],"methods":[162],"that":[163],"rely":[164],"external":[166],"knowledge":[167],"bases":[168],"complex":[170],"meta-learning":[171],"strategies.":[172],"strong":[174],"results":[175],"demonstrate":[176],"effectiveness":[178],"injecting":[180],"generic":[181],"awareness":[183],"into":[184],"powerful":[185],"vision-language":[186],"models":[187],"like":[188],"tackling":[191],"manner.":[197]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-17T00:00:00"}
