{"id":"https://openalex.org/W4417182807","doi":"https://doi.org/10.1109/iccv51701.2025.01848","title":"CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning","display_name":"CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417182807","doi":"https://doi.org/10.1109/iccv51701.2025.01848"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.01409","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009725511","display_name":"Kuniaki Saito","orcid":"https://orcid.org/0000-0001-8233-9283"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kuniaki Saito","raw_affiliation_strings":["OMRON SINIC X"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OMRON SINIC X","institution_ids":["https://openalex.org/I146230289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454693","display_name":"Donghyun Kim","orcid":"https://orcid.org/0000-0003-1960-0527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghyun Kim","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032207625","display_name":"Kwanyong Park","orcid":"https://orcid.org/0009-0007-1407-1239"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanyong Park","raw_affiliation_strings":["University of Seoul"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038408644","display_name":"Atsushi Hashimoto","orcid":"https://orcid.org/0000-0002-0799-4269"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Hashimoto","raw_affiliation_strings":["OMRON SINIC X"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OMRON SINIC X","institution_ids":["https://openalex.org/I146230289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077707500","display_name":"Yoshitaka Ushiku","orcid":"https://orcid.org/0000-0002-9014-1389"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshitaka Ushiku","raw_affiliation_strings":["OMRON SINIC X"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OMRON SINIC X","institution_ids":["https://openalex.org/I146230289"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35189409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19872","last_page":"19881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9725000262260437,"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":0.9725000262260437,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.009399999864399433,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0012000000569969416,"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/closed-captioning","display_name":"Closed captioning","score":0.9772999882698059},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5429999828338623},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4837000072002411},{"id":"https://openalex.org/keywords/uniqueness","display_name":"Uniqueness","score":0.4422000050544739},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.43619999289512634},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4058000147342682},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.37389999628067017},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3456000089645386}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9772999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580999732017517},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013999938964844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4921000003814697},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.43619999289512634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4271000027656555},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4058000147342682},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.3440000116825104},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.01409","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01409","pdf_url":"https://arxiv.org/pdf/2507.01409","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.01409","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01409","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.01409","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01409","pdf_url":"https://arxiv.org/pdf/2507.01409","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6352257711","display_name":null,"funder_award_id":"RS-2024-00341514","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"An":[0],"image":[1],"captioning":[2,90],"model":[3,91,159],"flexibly":[4],"switching":[5],"its":[6,68],"language":[7,69,96],"pattern,":[8],"e.g.,":[9,139],"descriptiveness":[10],"and":[11,61,109,146,169],"length,":[12,107],"should":[13],"be":[14,19,194],"useful":[15],"since":[16],"it":[17],"can":[18,93,160],"applied":[20],"to":[21,45,74,86,135],"diverse":[22,95],"applications.":[23],"However,":[24],"despite":[25,188],"the":[26,36,54,75,122,126,136,157,163,166,180],"dramatic":[27],"improvement":[28],"in":[29,182],"generative":[30],"vision-language":[31],"models,":[32],"fine-grained":[33],"control":[34],"over":[35],"properties":[37,55,103,164],"of":[38,104,111,165],"generated":[39],"captions":[40,168],"is":[41],"not":[42,52],"easy":[43],"due":[44],"two":[46,131],"reasons:":[47],"(i)":[48],"existing":[49,63],"models":[50,64],"are":[51],"given":[53],"as":[56,114],"a":[57,82,88,112,142,149],"condition":[58],"during":[59],"training":[60],"(ii)":[62],"cannot":[65],"smoothly":[66,161],"transition":[67],"pattern":[70],"from":[71],"one":[72,140,147],"state":[73],"other.":[76],"Given":[77,121],"this":[78],"challenge,":[79],"we":[80,124],"propose":[81],"new":[83],"approach,":[84],"CaptionSmiths,":[85],"acquire":[87],"single":[89],"that":[92,156],"handle":[94],"patterns.":[97],"First,":[98],"our":[99],"approach":[100],"quantifies":[101],"three":[102],"each":[105],"caption,":[106],"descriptiveness,":[108],"uniqueness":[110],"word,":[113],"continuous":[115],"scalar":[116],"values,":[117,123],"without":[118],"human":[119],"annotation.":[120],"represent":[125],"conditioning":[127],"via":[128],"interpolation":[129],"between":[130],"endpoint":[132],"vectors":[133],"corresponding":[134],"extreme":[137],"states,":[138],"for":[141,148],"very":[143,150],"short":[144],"caption":[145,184],"long":[151],"caption.":[152],"Empirical":[153],"results":[154],"demonstrate":[155],"resulting":[158],"change":[162],"output":[167],"show":[170],"higher":[171],"lexical":[172,190],"alignment":[173],"than":[174],"baselines.":[175],"For":[176],"instance,":[177],"CaptionSmiths":[178],"reduces":[179],"error":[181],"controlling":[183],"length":[185],"by":[186],"506\\%":[187],"better":[189],"alignment.":[191],"Code":[192],"will":[193],"available":[195],"on":[196],"https://github.com/omron-sinicx/captionsmiths.":[197]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}