{"id":"https://openalex.org/W7164760829","doi":"https://doi.org/10.5715/jnlp.33.537","title":"Enhancing Image Clustering with Captions","display_name":"Enhancing Image Clustering with Captions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164760829","doi":"https://doi.org/10.5715/jnlp.33.537"},"language":"en","primary_location":{"id":"doi:10.5715/jnlp.33.537","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.537","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_537/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_537/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138599520","display_name":"Yuanyuan Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I1282569916","display_name":"Mazda Motor Corporation (Japan)","ror":"https://ror.org/05hk1wv51","country_code":"JP","type":"company","lineage":["https://openalex.org/I1282569916"]},{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuanyuan Cai","raw_affiliation_strings":["Institute of Science Tokyo","Mazda Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]},{"raw_affiliation_string":"Mazda Motor Corporation","institution_ids":["https://openalex.org/I1282569916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010134544","display_name":"Satoshi Kosugi","orcid":"https://orcid.org/0000-0001-7556-9072"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Kosugi","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069989297","display_name":"Kotaro Funakoshi","orcid":"https://orcid.org/0000-0002-4529-4634"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Kotaro Funakoshi","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035876897","display_name":"Manabu Okumura","orcid":"https://orcid.org/0009-0001-7730-1536"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Manabu Okumura","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73360882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"2","first_page":"537","last_page":"569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8720999956130981,"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":0.8720999956130981,"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":0.03020000085234642,"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/T11439","display_name":"Video Analysis and Summarization","score":0.02419999986886978,"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/interpretability","display_name":"Interpretability","score":0.9041000008583069},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7534999847412109},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6439999938011169},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5388000011444092},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41600000858306885},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9041000008583069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537999749183655},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7534999847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7210999727249146},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5715/jnlp.33.537","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.537","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_537/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5715/jnlp.33.537","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.537","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_537/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164760829.pdf","grobid_xml":"https://content.openalex.org/works/W7164760829.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"image":[1,10,44,50,90],"clustering":[2,26,96],"is":[3],"constrained":[4],"by":[5,79,129],"its":[6,14],"reliance":[7],"on":[8,61,66,113,193],"single-modal":[9],"representations,":[11],"which":[12],"limits":[13],"ability":[15],"to":[16,48,133],"capture":[17],"complex":[18],"semantic":[19],"relationships":[20],"and":[21,40,45,84,91,118,148,164,173,183,190,210],"diminishes":[22],"the":[23,43,59,104,124,127,155,161,166,178,184,187],"interpretability":[24,125],"of":[25,106,126,170,180,186],"results.":[27],"This":[28,52],"study":[29,198],"proposes":[30],"a":[31,200],"methodology":[32],"that":[33,70,103,154,207],"initially":[34],"generates":[35],"captions":[36],"directly":[37],"from":[38],"images":[39,209],"then":[41],"integrates":[42],"caption":[46,92],"embeddings":[47,93],"enhance":[49,123],"clustering.":[51],"approach":[53,203],"leverages":[54],"automatically":[55],"generated":[56,211],"captions,":[57],"circumventing":[58],"dependency":[60],"manually":[62],"labeled":[63],"annotations.":[64],"Experiments":[65],"eight":[67],"datasets":[68],"demonstrate":[69,153],"multimodal":[71,115,205],"fusion":[72],"consistently":[73,94],"outperforms":[74],"unimodal":[75],"baselines:":[76],"CLIP":[77],"improves":[78],"approximately":[80],"5%,":[81],"whereas":[82],"BLIP":[83],"BLIP2":[85],"yield":[86],"smaller":[87],"gains.":[88],"Incorporating":[89],"enhances":[95],"accuracy.":[97],"Our":[98],"comparative":[99],"analysis":[100],"further":[101],"revealed":[102],"effectiveness":[105,179],"textual":[107],"features":[108],"varies":[109],"across":[110],"models,":[111],"depending":[112],"their":[114],"training":[116],"strategies":[117],"encoder":[119],"architectures.":[120],"Furthermore,":[121],"we":[122],"clusters":[128],"employing":[130],"language":[131],"models":[132],"generate":[134],"summaries":[135,157],"as":[136],"explanations":[137,145,182],"for":[138],"each":[139],"identified":[140],"cluster.":[141],"We":[142],"evaluate":[143],"these":[144],"through":[146],"quantitative":[147],"human":[149],"assessments.":[150],"The":[151],"results":[152],"GPT-4":[156],"best":[158],"align":[159],"with":[160],"ground-truth":[162],"labels":[163],"outperform":[165],"others":[167],"in":[168],"terms":[169],"accuracy,":[171],"coverage,":[172],"readability.":[174],"These":[175],"findings":[176],"highlight":[177],"sentence-type":[181],"impact":[185],"model":[188],"architecture":[189],"input":[191],"strategy":[192],"explanation":[194],"quality.":[195],"Overall,":[196],"this":[197],"establishes":[199],"novel":[201],"image-clustering":[202],"using":[204],"representations":[206],"combines":[208],"captions.":[212]},"counts_by_year":[],"updated_date":"2026-07-25T17:18:41.151588","created_date":"2026-06-15T00:00:00"}