{"id":"https://openalex.org/W4405785376","doi":"https://doi.org/10.1109/iros58592.2024.10801660","title":"Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning","display_name":"Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785376","doi":"https://doi.org/10.1109/iros58592.2024.10801660"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5042000257","display_name":"Jishnu Jaykumar P","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jishnu Jaykumar P","raw_affiliation_strings":["University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039566019","display_name":"Kamalesh Palanisamy","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamalesh Palanisamy","raw_affiliation_strings":["University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067607006","display_name":"Yu-Wei Chao","orcid":"https://orcid.org/0000-0002-5476-4343"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Wei Chao","raw_affiliation_strings":["NVIDIA,Seattle,WA,USA,98105"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Seattle,WA,USA,98105","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101382802","display_name":"Xinya Du","orcid":"https://orcid.org/0000-0003-4255-8013"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinya Du","raw_affiliation_strings":["University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101426810","display_name":"Xiang Yu","orcid":"https://orcid.org/0000-0001-9431-5131"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Xiang","raw_affiliation_strings":["University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042000257"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.916,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92331684,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2594","last_page":"2601"},"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":0.9584000110626221,"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":0.9584000110626221,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7867608070373535},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6241360306739807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5274978876113892},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4307858943939209},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3732498288154602},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35239654779434204},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3402697741985321},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08961763978004456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867608070373535},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6241360306739807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5274978876113892},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4307858943939209},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3732498288154602},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35239654779434204},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3402697741985321},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08961763978004456},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1875842236","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2068127265","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2277195237","https://openalex.org/W2533598788","https://openalex.org/W2796346823","https://openalex.org/W2798836702","https://openalex.org/W2952122856","https://openalex.org/W2964105864","https://openalex.org/W2964194231","https://openalex.org/W3034942609","https://openalex.org/W3099587965","https://openalex.org/W3108975329","https://openalex.org/W3198377975","https://openalex.org/W3207187156","https://openalex.org/W4312933868","https://openalex.org/W4313175608","https://openalex.org/W4383108184","https://openalex.org/W4386790226","https://openalex.org/W4390874269","https://openalex.org/W6600983433","https://openalex.org/W6638677478","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6758126075","https://openalex.org/W6760378562","https://openalex.org/W6780975210","https://openalex.org/W6791353385","https://openalex.org/W6844194202","https://openalex.org/W6846342132","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"We":[0,112],"propose":[1,77],"a":[2,50],"novel":[3],"framework":[4],"for":[5,22,35,72,92,125,135],"few-shot":[6,23,36,54,93,126],"learning":[7],"by":[8,18,119],"leveraging":[9],"large-scale":[10],"vision-language":[11],"models":[12],"such":[13],"as":[14,128,130],"CLIP":[15,48],"[1].":[16],"Motivated":[17],"unimodal":[19],"prototypical":[20],"networks":[21],"learning,":[24,127],"we":[25,76],"introduce":[26],"Proto-CLIP":[27,39,105],"which":[28],"utilizes":[29],"image":[30,42,70,80],"prototypes":[31,34,68,83],"and":[32,43,81,109],"text":[33,44,82],"learning.":[37],"Specifically,":[38],"adapts":[40],"the":[41,59,66,79,85,97,114,132],"encoder":[45],"embeddings":[46,57],"from":[47,58,100],"in":[49,131],"joint":[51],"fashion":[52],"using":[53],"examples.":[55],"The":[56],"two":[60],"encoders":[61],"are":[62],"used":[63],"to":[64,96],"compute":[65],"respective":[67],"of":[69,84,103,116],"classes":[71],"classification.":[73],"During":[74],"adaptation,":[75],"aligning":[78],"corresponding":[86],"classes.":[87],"Such":[88],"alignment":[89],"is":[90],"beneficial":[91],"classification":[94],"due":[95],"reinforced":[98],"contributions":[99],"both":[101,107],"types":[102],"prototypes.":[104],"has":[106],"training-free":[108],"fine-tuned":[110],"variants.":[111],"demonstrate":[113],"effectiveness":[115],"our":[117],"method":[118],"conducting":[120],"experiments":[121],"on":[122],"benchmark":[123],"datasets":[124],"well":[129],"real":[133],"world":[134],"robot":[136],"perception<sup":[137],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}