{"id":"https://openalex.org/W4415537693","doi":"https://doi.org/10.1145/3746027.3755764","title":"Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization","display_name":"Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537693","doi":"https://doi.org/10.1145/3746027.3755764"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5067404678","display_name":"Haolong CHEN","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huiyi Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiawei Peng","orcid":"https://orcid.org/0009-0005-1751-239X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Peng","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044120384","display_name":"Kaihua Tang","orcid":"https://orcid.org/0000-0002-1008-7053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaihua Tang","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074742406","display_name":"Xin Geng","orcid":"https://orcid.org/0000-0001-7729-0622"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Geng","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064752243","display_name":"Xu Yang","orcid":"https://orcid.org/0000-0002-8276-2679"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067404678"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1599881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5130","last_page":"5139"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9976000189781189,"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":0.9939000010490417,"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/set","display_name":"Set (abstract data type)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5228000283241272},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5156000256538391},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45489999651908875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6209999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6060000061988831},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5228000283241272},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27399998903274536}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3740420203","display_name":null,"funder_award_id":"2242025K30024","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8845568983","display_name":null,"funder_award_id":"BK20220819","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W3035524453","https://openalex.org/W3122241445","https://openalex.org/W4385571445","https://openalex.org/W4390873312","https://openalex.org/W4401362547"],"related_works":[],"abstract_inverted_index":{"In-context":[0],"learning":[1],"(ICL)":[2],"enables":[3],"Large":[4],"Vision-Language":[5],"Models":[6],"(LVLMs)":[7],"to":[8,10,30,61,76,97,121,149],"adapt":[9],"new":[11],"tasks":[12],"without":[13],"parameter":[14],"updates,":[15],"using":[16],"a":[17,21,41,90,99,152,195],"few":[18],"demonstrations":[19,28],"from":[20,132],"large":[22],"support":[23,52,134],"set.":[24],"However,":[25],"selecting":[26,40],"informative":[27,102,154],"leads":[29],"high":[31],"computational":[32,158],"and":[33,43,57,101,165,199],"memory":[34],"costs.":[35],"While":[36],"some":[37],"methods":[38,66],"explore":[39],"small":[42],"representative":[44],"coreset":[45,142,148,155],"in":[46,78,203],"the":[47,111,116,133,138,145,200,207],"text":[48],"classification,":[49],"evaluating":[50],"all":[51],"set":[53],"samples":[54,59,120,131],"remains":[55],"costly,":[56],"discarded":[58],"lead":[60],"unnecessary":[62],"information":[63],"loss.":[64],"These":[65],"may":[67],"also":[68],"be":[69,122],"less":[70],"effective":[71],"for":[72,118,178,213],"image":[73,167,179],"classification":[74,168,180],"due":[75],"differences":[77],"feature":[79],"spaces.":[80],"Given":[81],"these":[82],"limitations,":[83],"we":[84,136,170,191],"propose":[85],"Key-based":[86],"Coreset":[87],"Optimization":[88],"(KeCO),":[89],"novel":[91],"framework":[92,212],"that":[93,172],"leverages":[94],"untapped":[95,130],"data":[96],"construct":[98],"compact":[100],"coreset.":[103],"We":[104],"introduce":[105],"visual":[106],"features":[107],"as":[108,115],"keys":[109,139],"within":[110],"coreset,":[112],"which":[113],"serve":[114],"anchor":[117],"identifying":[119],"updated":[123],"through":[124],"different":[125],"selection":[126],"strategies.":[127],"By":[128],"leveraging":[129],"set,":[135],"update":[137],"of":[140,186,210],"selected":[141],"samples,":[143],"enabling":[144],"randomly":[146],"initialized":[147],"evolve":[150],"into":[151],"more":[153,187],"under":[156,194],"low":[157],"cost.":[159],"Through":[160],"extensive":[161],"experiments":[162],"on":[163],"coarse-grained":[164],"fine-grained":[166],"benchmarks,":[169],"demonstrate":[171],"KeCO":[173,193],"effectively":[174],"enhances":[175],"ICL":[176],"performance":[177,202],"task,":[181],"achieving":[182],"an":[183],"average":[184],"improvement":[185],"than":[188],"20%.":[189],"Notably,":[190],"evaluate":[192],"simulated":[196],"online":[197],"scenario,":[198],"strong":[201],"this":[204],"scenario":[205],"highlights":[206],"practical":[208],"value":[209],"our":[211],"resource-constrained":[214],"real-world":[215],"scenarios.":[216]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}