{"id":"https://openalex.org/W4415709229","doi":"https://doi.org/10.1109/icme59968.2025.11210028","title":"EPIC: Efficient Prompt Interaction for Text-Image Classification","display_name":"EPIC: Efficient Prompt Interaction for Text-Image Classification","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709229","doi":"https://doi.org/10.1109/icme59968.2025.11210028"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5001344569","display_name":"Xin\u2010Yao Yu","orcid":"https://orcid.org/0000-0003-3576-5815"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyao Yu","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058002649","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0001-8094-1991"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111270301","display_name":"Zeyu Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Ling","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034985742","display_name":"Ziwei Niu","orcid":"https://orcid.org/0000-0003-0171-5158"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Niu","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042681907","display_name":"Zhenjia Bai","orcid":"https://orcid.org/0009-0008-3969-3007"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjia Bai","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101677487","display_name":"Rui Qin","orcid":"https://orcid.org/0000-0002-9822-5835"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Qin","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101700166","display_name":"Yen-Wei Chen","orcid":"https://orcid.org/0000-0002-8740-0351"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yen-Wei Chen","raw_affiliation_strings":["Ritsumeikan University,College of Information Science,Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,College of Information Science,Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090814258","display_name":"Lanfen Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanfen Lin","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5001344569"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34014387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5999000072479248,"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":0.5999000072479248,"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/T10028","display_name":"Topic Modeling","score":0.07970000058412552,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05290000140666962,"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/leverage","display_name":"Leverage (statistics)","score":0.7307999730110168},{"id":"https://openalex.org/keywords/resource-consumption","display_name":"Resource consumption","score":0.6855999827384949},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6610999703407288},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.45249998569488525},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.37860000133514404},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.32670000195503235}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7307999730110168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264000177383423},{"id":"https://openalex.org/C2777480716","wikidata":"https://www.wikidata.org/wiki/Q23582796","display_name":"Resource consumption","level":2,"score":0.6855999827384949},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6610999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662000179290771},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48890000581741333},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2296448531","https://openalex.org/W2787581402","https://openalex.org/W2888471892","https://openalex.org/W2964010806","https://openalex.org/W3093051361","https://openalex.org/W3143320354","https://openalex.org/W3155978629","https://openalex.org/W3169309079","https://openalex.org/W3198377975","https://openalex.org/W4285300583","https://openalex.org/W4308236449","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4385801378","https://openalex.org/W4386047824","https://openalex.org/W4386071547"],"related_works":[],"abstract_inverted_index":{"In":[0,57],"recent":[1],"years,":[2],"large-scale":[3],"pre-trained":[4],"multimodal":[5,21,66],"models":[6,42],"(LMMs)":[7],"generally":[8],"emerge":[9],"to":[10,52,93,121],"integrate":[11,86],"the":[12,117,131,141],"vision":[13],"and":[14,85,110,133],"language":[15],"modalities,":[16],"achieving":[17,137],"considerable":[18],"success":[19],"in":[20,34],"tasks,":[22],"such":[23],"as":[24],"text-image":[25,74],"classification.":[26],"The":[27],"growing":[28],"size":[29],"of":[30,116],"LMMs,":[31],"however,":[32],"results":[33],"a":[35,62],"significant":[36],"computational":[37,107],"cost":[38],"for":[39,43,73],"fine-tuning":[40,123],"these":[41],"downstream":[44],"tasks.":[45],"Hence,":[46],"prompt-based":[47,65],"interaction":[48,67],"strategy":[49],"is":[50],"studied":[51],"align":[53],"modalities":[54,88],"more":[55],"efficiently.":[56],"this":[58,101],"context,":[59],"we":[60,78],"propose":[61],"novel":[63],"efficient":[64],"strategy,":[68],"namely":[69],"Efficient":[70],"Prompt":[71],"Interaction":[72],"Classification":[75],"(EPIC).":[76],"Specifically,":[77],"utilize":[79],"temporal":[80],"prompts":[81],"on":[82,130,140],"intermediate":[83],"layers,":[84],"different":[87],"with":[89],"similarity-based":[90],"prompt":[91],"interaction,":[92],"leverage":[94],"sufficient":[95],"information":[96],"exchange":[97],"between":[98],"modalities.":[99],"Utilizing":[100],"approach,":[102],"our":[103],"method":[104],"achieves":[105],"reduced":[106],"resource":[108],"consumption":[109],"fewer":[111],"trainable":[112],"parameters":[113],"(about":[114],"1%":[115],"foundation":[118],"model)":[119],"compared":[120],"other":[122],"strategies.":[124],"Furthermore,":[125],"it":[126],"demonstrates":[127],"superior":[128],"performance":[129,139],"UPMC-Food101":[132],"SNLI-VE":[134],"datasets,":[135],"while":[136],"comparable":[138],"MM-IMDB":[142],"dataset.":[143]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}