{"id":"https://openalex.org/W4406233699","doi":"https://doi.org/10.1145/3711867","title":"Modeling Multi-modal Cross-interaction for Multi-label Few-shot Image Classification Based on Local Feature Selection","display_name":"Modeling Multi-modal Cross-interaction for Multi-label Few-shot Image Classification Based on Local Feature Selection","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4406233699","doi":"https://doi.org/10.1145/3711867"},"language":"en","primary_location":{"id":"doi:10.1145/3711867","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711867","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05078232","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106355302","display_name":"Kun Yan","orcid":"https://orcid.org/0000-0002-1234-6119"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Yan","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China","School of Computer Science, Peking University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059764145","display_name":"Zied Bouraoui","orcid":"https://orcid.org/0000-0002-1662-4163"},"institutions":[{"id":"https://openalex.org/I44563897","display_name":"Universit\u00e9 d'Artois","ror":"https://ror.org/053x9s498","country_code":"FR","type":"education","lineage":["https://openalex.org/I44563897"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zied Bouraoui","raw_affiliation_strings":["CRIL - University of Artois & CNRS, Lens, France","CRIL - University of Artois & CNRS, France"],"affiliations":[{"raw_affiliation_string":"CRIL - University of Artois & CNRS, Lens, France","institution_ids":["https://openalex.org/I44563897","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CRIL - University of Artois & CNRS, France","institution_ids":["https://openalex.org/I44563897","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090973869","display_name":"Fangyun Wei","orcid":"https://orcid.org/0000-0001-8784-4916"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fangyun Wei","raw_affiliation_strings":["School of Computer Science, University of Sydney, Sydney, Australia","School of Computer Science, University of Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001529504","display_name":"Chang Xu","orcid":"https://orcid.org/0000-0002-4756-0609"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chang Xu","raw_affiliation_strings":["The University of Sydney, Sydney, Australia","School of Computer Science, University of Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338689","display_name":"Ping Wang","orcid":"https://orcid.org/0000-0002-8854-2079"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Wang","raw_affiliation_strings":["Peking University, Beijing, China","National Engineering Research Center for Software Engineering, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center for Software Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082611298","display_name":"Shoaib Jameel","orcid":"https://orcid.org/0000-0001-7534-3313"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shoaib Jameel","raw_affiliation_strings":["University of Southampton, Southampton, United Kingdom of Great Britain and Northern Ireland","Electronics and Computer Science, University of Southampton, UK"],"affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I43439940"]},{"raw_affiliation_string":"Electronics and Computer Science, University of Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052196540","display_name":"Steven Schockaert","orcid":"https://orcid.org/0000-0002-9256-2881"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steven Schockaert","raw_affiliation_strings":["Cardiff University, Cardiff, United Kingdom of Great Britain and Northern Ireland","School of Computer Science and Informatics, Cardiff University, UK"],"affiliations":[{"raw_affiliation_string":"Cardiff University, Cardiff, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, UK","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5106355302"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.7712,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88031326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"21","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955999851226807,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9947999715805054,"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":0.8752546310424805},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6657686829566956},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6249822378158569},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6089215874671936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5956515073776245},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5499352216720581},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5420459508895874},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5311008095741272},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5306593179702759},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.45306453108787537},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41953045129776},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34879523515701294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8752546310424805},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6657686829566956},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6249822378158569},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6089215874671936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956515073776245},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5499352216720581},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5420459508895874},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5311008095741272},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5306593179702759},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.45306453108787537},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41953045129776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34879523515701294},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3711867","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711867","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:175190","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:HAL:hal-05078232v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05078232","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"ACM Transactions on Multimedia Computing, Communications and Applications, 2025, 21 (3), pp.80. ⟨10.1145/3711867⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05078232v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05078232","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"ACM Transactions on Multimedia Computing, Communications and Applications, 2025, 21 (3), pp.80. ⟨10.1145/3711867⟩","raw_type":"Journal articles"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4466388606","display_name":null,"funder_award_id":"NVIDIA","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5030940285","display_name":null,"funder_award_id":"2023M","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G589531907","display_name":"Event-Centric Reasoning for Interpreting Everyday Narratives","funder_award_id":"ANR-22-CE23-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6851345361","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7533650627","display_name":"Encyclopedic Lexical Representations for Natural Language Processing","funder_award_id":"EP/V025961/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7643227555","display_name":null,"funder_award_id":"EP/V025961/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2037227137","https://openalex.org/W2146241755","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2330154883","https://openalex.org/W2493916176","https://openalex.org/W2592691248","https://openalex.org/W2736688973","https://openalex.org/W2896457183","https://openalex.org/W2917792613","https://openalex.org/W2930957955","https://openalex.org/W2932399282","https://openalex.org/W2943605315","https://openalex.org/W2963300078","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2964015378","https://openalex.org/W2964105864","https://openalex.org/W2969792713","https://openalex.org/W2970632972","https://openalex.org/W2979689312","https://openalex.org/W2995278328","https://openalex.org/W2997136715","https://openalex.org/W2998420437","https://openalex.org/W3022615309","https://openalex.org/W3030509278","https://openalex.org/W3034312118","https://openalex.org/W3089555680","https://openalex.org/W3119727976","https://openalex.org/W3154314403","https://openalex.org/W3160420592","https://openalex.org/W3162481048","https://openalex.org/W3165691894","https://openalex.org/W3172752666","https://openalex.org/W3173908982","https://openalex.org/W3191562205","https://openalex.org/W3192931333","https://openalex.org/W3197599296","https://openalex.org/W3198377975","https://openalex.org/W3201193395","https://openalex.org/W3204916837","https://openalex.org/W3213643395","https://openalex.org/W3213730158","https://openalex.org/W3215828051","https://openalex.org/W4207020661","https://openalex.org/W4212944375","https://openalex.org/W4221079634","https://openalex.org/W4225323055","https://openalex.org/W4232688373","https://openalex.org/W4236965008","https://openalex.org/W4240153047","https://openalex.org/W4283313485","https://openalex.org/W4283396434","https://openalex.org/W4301409532","https://openalex.org/W4307340220","https://openalex.org/W4308104970","https://openalex.org/W4309724443","https://openalex.org/W4312269975","https://openalex.org/W4312310776","https://openalex.org/W4313331808","https://openalex.org/W4313426864","https://openalex.org/W4383988651","https://openalex.org/W4384644539","https://openalex.org/W4385572959","https://openalex.org/W4386113259","https://openalex.org/W4386790226","https://openalex.org/W4390057594","https://openalex.org/W4390871860","https://openalex.org/W4390873546","https://openalex.org/W4392173891","https://openalex.org/W4395661389","https://openalex.org/W4402704589","https://openalex.org/W4402727766","https://openalex.org/W6735236233","https://openalex.org/W6739901393","https://openalex.org/W6759807521"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,22,33,54,82,89,128,134,167,177],"multi-label":[3,35],"few-shot":[4],"image":[5,40],"classification":[6],"(ML-FSIC)":[7],"is":[8,37,66],"to":[9,13,48,69,121,147,164],"assign":[10],"semantic":[11],"labels":[12],"images,":[14],"in":[15,51,61,103],"settings":[16],"where":[17],"only":[18],"a":[19,62,97,101,141,168,187],"small":[20],"number":[21],"training":[23,83,154],"examples":[24],"are":[25,73,107,161],"available":[26],"for":[27,75],"each":[28],"label.":[29,170],"A":[30],"key":[31],"feature":[32],"the":[34,55,79,86,113,126,129,149,153,157,174,178,195,214],"setting":[36],"that":[38,160,209],"an":[39],"often":[41],"has":[42],"several":[43],"labels,":[44,77],"which":[45,71,76,104,118,191],"typically":[46],"refer":[47],"objects":[49],"appearing":[50],"different":[52],"regions":[53,72],"image.":[56],"When":[57],"estimating":[58],"label":[59,105,179],"prototypes,":[60,137],"metric-based":[63],"setting,":[64],"it":[65],"thus":[67],"important":[68],"determine":[70],"relevant":[74],"but":[78],"limited":[80],"amount":[81],"data":[84],"and":[85,206],"noisy":[87],"nature":[88],"local":[90,150,184],"features":[91,151,185],"make":[92],"this":[93],"highly":[94],"challenging.":[95],"As":[96],"solution,":[98],"we":[99,111,138,172],"propose":[100],"strategy":[102,146],"prototypes":[106,114],"gradually":[108],"refined.":[109],"First,":[110],"initialize":[112],"using":[115,186],"word":[116,197],"embeddings,":[117],"allows":[119],"us":[120],"leverage":[122],"prior":[123],"knowledge":[124],"about":[125],"meaning":[127],"labels.":[130],"Second,":[131],"taking":[132],"advantage":[133],"these":[135,182],"initial":[136,196],"then":[139],"use":[140],"Loss":[142],"Change":[143],"Measurement":[144],"(LCM)":[145],"select":[148],"from":[152],"images":[155],"(i.e.,":[156],"support":[158],"set)":[159],"most":[162],"likely":[163],"be":[165],"representative":[166,183],"given":[169],"Third,":[171],"construct":[173],"final":[175],"prototype":[176],"by":[180],"aggregating":[181],"multi-modal":[188],"cross-interaction":[189],"mechanism,":[190],"again":[192],"relies":[193],"on":[194,201],"embedding-based":[198],"prototypes.":[199],"Experiments":[200],"COCO,":[202],"PASCAL":[203],"VOC,":[204],"NUS-WIDE,":[205],"iMaterialist":[207],"show":[208],"our":[210],"model":[211],"substantially":[212],"improves":[213],"current":[215],"state-of-the-art.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-01-10T00:00:00"}