{"id":"https://openalex.org/W4403017044","doi":"https://doi.org/10.1587/transinf.2024edp7036","title":"UTStyleCap4K: Generating Image Captions with Sentimental Styles","display_name":"UTStyleCap4K: Generating Image Captions with Sentimental Styles","publication_year":2024,"publication_date":"2024-10-01","ids":{"openalex":"https://openalex.org/W4403017044","doi":"https://doi.org/10.1587/transinf.2024edp7036"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024edp7036","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7036","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/3/E108.D_2024EDP7036/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","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/transinf/E108.D/3/E108.D_2024EDP7036/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088750520","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0003-4992-1639"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chi ZHANG","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455259","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-9277-1539"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Li TAO","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048624196","display_name":"Toshihiko Yamasaki","orcid":"https://orcid.org/0000-0002-1784-2314"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihiko YAMASAKI","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11652871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E108.D","issue":"3","first_page":"266","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9933000206947327,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9675999879837036,"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/computer-science","display_name":"Computer science","score":0.8535566926002502},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.56793612241745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5424398183822632},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4660934507846832},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3504226803779602},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.337388813495636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535566926002502},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.56793612241745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5424398183822632},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4660934507846832},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3504226803779602},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.337388813495636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024edp7036","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7036","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/3/E108.D_2024EDP7036/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024edp7036","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7036","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/3/E108.D_2024EDP7036/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403017044.pdf","grobid_xml":"https://content.openalex.org/works/W4403017044.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2277195237","https://openalex.org/W2575842049","https://openalex.org/W2625940279","https://openalex.org/W2822349497","https://openalex.org/W2896457183","https://openalex.org/W2913618459","https://openalex.org/W2943885184","https://openalex.org/W2955956881","https://openalex.org/W2963062932","https://openalex.org/W2963084599","https://openalex.org/W2963448089","https://openalex.org/W2969214802","https://openalex.org/W2986670728","https://openalex.org/W2992478697","https://openalex.org/W2997248215","https://openalex.org/W2997591391","https://openalex.org/W3030163527","https://openalex.org/W3034316193","https://openalex.org/W3107015116","https://openalex.org/W3107848485","https://openalex.org/W3110157234","https://openalex.org/W3183226462","https://openalex.org/W3203247740","https://openalex.org/W4213019668","https://openalex.org/W4286586606","https://openalex.org/W4294967780","https://openalex.org/W4312344082","https://openalex.org/W4312605942","https://openalex.org/W4317897818","https://openalex.org/W4319317262","https://openalex.org/W4376312115","https://openalex.org/W4384918448","https://openalex.org/W4386076530","https://openalex.org/W4386651352","https://openalex.org/W4394625850","https://openalex.org/W4404166661"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Stylized":[0],"image":[1,8,77,120],"captioning":[2,121],"is":[3,93,180],"the":[4,45,49,101,105,111,114,150,155,159,169,194,199],"task":[5],"of":[6,52,154,171,182,185],"generating":[7,183],"captions":[9,74,79,157,184],"that":[10,90,148,177],"have":[11,25],"a":[12,60,84,132,137],"description":[13,36],"style,":[14],"such":[15],"as":[16],"positive":[17,70],"or":[18],"negative":[19,73],"sentiments.":[20],"Recently,":[21],"deep":[22],"learning":[23],"models":[24,126],"reached":[26],"high":[27],"performance":[28,201],"in":[29,80,95,100],"this":[30,56],"task,":[31],"but":[32],"they":[33,41],"still":[34],"lack":[35],"accuracy":[37],"and":[38,40,48,71,97,107,152,165,191,197],"diversity,":[39],"often":[42],"suffer":[43],"from":[44,142],"small":[46],"size":[47],"low":[50],"descriptiveness":[51],"existing":[53,118],"datasets.":[54,122],"In":[55],"paper,":[57],"we":[58],"introduce":[59],"new":[61,138],"dataset,":[62,113,116],"UTStyleCap4K,":[63],"which":[64],"contains":[65],"4,644":[66],"images":[67],"with":[68],"three":[69,72,186],"for":[75],"every":[76],"(27,864":[78],"total),":[81],"collected":[82],"by":[83,162],"crowdsourcing":[85],"service.":[86],"Experimental":[87,174],"results":[88,175],"show":[89,176],"our":[91,128,178,203],"dataset":[92,129],"accurate":[94],"meaning":[96],"sentiments,":[98],"diverse":[99],"ways":[102],"to":[103,110,130],"describe":[104],"styles,":[106,188],"less":[108],"similar":[109],"base":[112],"MSCOCO":[115],"than":[117],"stylized":[119],"We":[123,134],"train":[124],"multiple":[125],"on":[127,202],"set":[131],"baseline.":[133],"also":[135],"propose":[136],"Bidirectional":[139],"Encoder":[140],"Representations":[141],"Transformers":[143],"(BERT)":[144],"based":[145],"model,":[146],"StyleCapBERT,":[147],"controls":[149],"length":[151,164],"style":[153,166],"generated":[156],"at":[158,193],"same":[160,195],"time,":[161,196],"introducing":[163],"information":[167],"into":[168],"embeddings":[170],"caption":[172],"words.":[173],"model":[179],"capable":[181],"sentimental":[187],"positive,":[189],"factual,":[190],"negative,":[192],"achieving":[198],"best":[200],"dataset.":[204]},"counts_by_year":[],"updated_date":"2026-08-19T15:00:24.278416","created_date":"2025-10-10T00:00:00"}
