{"id":"https://openalex.org/W7169791949","doi":"https://doi.org/10.1109/access.2026.3715025","title":"CLM: Contrastive Vision\u2013Language Prompting for Multimodal Product Summarization","display_name":"CLM: Contrastive Vision\u2013Language Prompting for Multimodal Product Summarization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7169791949","doi":"https://doi.org/10.1109/access.2026.3715025"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3715025","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3715025","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"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 Access","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/access.2026.3715025","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059962151","display_name":"Rong Nie","orcid":"https://orcid.org/0000-0002-4435-6899"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Nie","raw_affiliation_strings":["Hunan University of Applied Technology"],"raw_orcid":"https://orcid.org/0000-0002-4435-6899","affiliations":[{"raw_affiliation_string":"Hunan University of Applied Technology","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027459275","display_name":"Xiaochun Cheng","orcid":"https://orcid.org/0000-0003-0371-9646"},"institutions":[{"id":"https://openalex.org/I39586589","display_name":"Swansea University","ror":"https://ror.org/053fq8t95","country_code":"GB","type":"education","lineage":["https://openalex.org/I39586589"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaochun Cheng","raw_affiliation_strings":["Swansea University"],"raw_orcid":"https://orcid.org/0009-0002-8090-1003","affiliations":[{"raw_affiliation_string":"Swansea University","institution_ids":["https://openalex.org/I39586589"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91120297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"110514","last_page":"110524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.46219998598098755,"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/T10028","display_name":"Topic Modeling","score":0.46219998598098755,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.15240000188350677,"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/T12031","display_name":"Speech and dialogue systems","score":0.09910000115633011,"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/automatic-summarization","display_name":"Automatic summarization","score":0.7440999746322632},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.296099990606308},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2533999979496002},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2296999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080999851226807},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7440999746322632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849999785423279},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.51419997215271},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2296999990940094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22759999334812164}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3715025","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3715025","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8ddb0f900e5947958b42f413cd6f52b2","is_oa":false,"landing_page_url":"https://doaj.org/article/8ddb0f900e5947958b42f413cd6f52b2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 110514-110524 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3715025","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3715025","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4382307673","display_name":null,"funder_award_id":"EP/W020408/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"product":[1,18,38,81,102,170],"summarization":[2],"aims":[3],"to":[4,104],"generate":[5],"concise":[6],"textual":[7,15,59],"summaries":[8],"for":[9,79],"e-commerce":[10],"products":[11],"by":[12],"jointly":[13],"leveraging":[14],"descriptions":[16],"and":[17,40,57,111,136,154,185,193,207],"images.":[19],"Two":[20],"fundamental":[21],"challenges":[22],"persist":[23],"in":[24,37,187],"this":[25,69],"task:":[26],"1)":[27],"existing":[28],"unimodal":[29],"methods":[30],"discard":[31],"the":[32,62,123,129,165],"rich":[33],"visual":[34,55,89,125],"attributes":[35],"embedded":[36],"images,":[39],"2)":[41],"prior":[42],"multimodal":[43,80],"approaches":[44],"rely":[45],"on":[46,117,122,164,189],"conventional":[47],"image":[48],"encoders":[49],"that":[50,119,150,173,202],"lack":[51],"explicit":[52],"alignment":[53],"between":[54,132],"features":[56],"fine-grained":[58],"attributes,":[60],"limiting":[61],"quality":[63],"of":[64,157,182],"visually":[65,208],"grounded":[66],"generation.":[67],"In":[68],"paper,":[70],"we":[71,143],"propose":[72],"CLM,":[73],"a":[74,88,94,112,145],"contrastive":[75,109],"vision-language":[76],"prompting":[77],"framework":[78],"summarization.":[82],"CLM":[83,174,203],"comprises":[84],"two":[85],"synergistic":[86],"components:":[87],"prompt":[90,146],"predictor":[91],"built":[92],"upon":[93],"half-frozen":[95],"adapter-augmented":[96],"CLIP":[97],"model":[98],"(HFA-CLIP),":[99],"which":[100],"maps":[101],"images":[103],"attribute-level":[105],"reference":[106,158],"words":[107,159],"via":[108],"alignment,":[110],"prompt-guided":[113],"text":[114],"summarizer":[115],"based":[116],"BART":[118],"conditions":[120],"generation":[121],"predicted":[124,138],"prompts.":[126],"To":[127],"mitigate":[128],"distribution":[130],"gap":[131],"oracle":[133],"training":[134,148],"prompts":[135,139],"noisy":[137],"at":[140],"inference":[141],"time,":[142],"introduce":[144],"perturbation":[147],"strategy":[149],"includes":[151],"random":[152],"shuffling":[153],"stochastic":[155],"dropout":[156],"during":[160],"training.":[161],"Extensive":[162],"experiments":[163],"CEPSUM2.0":[166],"benchmark":[167],"across":[168],"three":[169],"categories":[171],"demonstrate":[172],"consistently":[175],"outperforms":[176],"strong":[177],"baselines,":[178],"achieving":[179],"relative":[180],"improvements":[181],"5.9%,":[183],"8.5%,":[184],"23.2%":[186],"ROUGE-1":[188],"home":[190],"appliances,":[191],"clothing,":[192],"cases":[194],"&":[195],"bags,":[196],"respectively.":[197],"Human":[198],"evaluation":[199],"further":[200],"confirms":[201],"produces":[204],"more":[205],"informative":[206],"faithful":[209],"summaries.":[210]},"counts_by_year":[],"updated_date":"2026-07-25T05:54:39.514286","created_date":"2026-07-21T00:00:00"}