{"id":"https://openalex.org/W4304080462","doi":"https://doi.org/10.1145/3503161.3548295","title":"Detach and Attach: Stylized Image Captioning without Paired Stylized Dataset","display_name":"Detach and Attach: Stylized Image Captioning without Paired Stylized Dataset","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080462","doi":"https://doi.org/10.1145/3503161.3548295"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548295","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548295","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083893200","display_name":"Yutong Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yutong Tan","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067997634","display_name":"Zheng Lin","orcid":"https://orcid.org/0000-0002-8432-1658"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Lin","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001781730","display_name":"Peng Fu","orcid":"https://orcid.org/0000-0001-9899-8566"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Fu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014223736","display_name":"Mingyu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Zheng","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087617391","display_name":"Lanrui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanrui Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627572","display_name":"Yanan Cao","orcid":"https://orcid.org/0000-0003-3534-1094"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanan Cao","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015344604","display_name":"Weipinng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weipinng Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5083893200"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.4772,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73154458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4733","last_page":"4741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9961000084877014,"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":0.9846000075340271,"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/stylized-fact","display_name":"Stylized fact","score":0.9869434833526611},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7509891986846924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287008166313171},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6419674158096313},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5448193550109863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5258453488349915},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5236020684242249},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5196355581283569},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09124261140823364}],"concepts":[{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.9869434833526611},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7509891986846924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287008166313171},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6419674158096313},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5448193550109863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5258453488349915},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5236020684242249},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5196355581283569},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09124261140823364},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548295","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3548295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548295","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5}],"awards":[{"id":"https://openalex.org/G128251435","display_name":null,"funder_award_id":"61906187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1433666547","display_name":null,"funder_award_id":"61976207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304080462.pdf","grobid_xml":"https://content.openalex.org/works/W4304080462.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1631260214","https://openalex.org/W1832693441","https://openalex.org/W2101105183","https://openalex.org/W2481240925","https://openalex.org/W2759181158","https://openalex.org/W2822349497","https://openalex.org/W2890231609","https://openalex.org/W2962917899","https://openalex.org/W2969214802","https://openalex.org/W2997248215","https://openalex.org/W3206055785"],"related_works":["https://openalex.org/W2529311304","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Stylized":[0],"Image":[1],"Captioning":[2],"aims":[3],"to":[4,34,74,81,87,110,165,177,180,190,205,220],"generate":[5,35,181],"captions":[6,37,51],"with":[7],"accurate":[8],"image":[9,17,178,196,225],"content":[10,179,226],"and":[11,18,26,63,85,127,171,197,210,228],"stylized":[12,19,36,40,104,108,162,182],"elements":[13],"simultaneously.":[14],"However,":[15,121],"large-scaled":[16,161],"caption":[20,41],"pairs":[21],"cost":[22],"lots":[23],"of":[24,49,136,140,217,224],"resources":[25],"are":[27,129],"usually":[28],"unavailable.":[29],"Therefore,":[30],"it's":[31],"a":[32,70,82,141,150,186],"challenge":[33],"without":[38],"paired":[39],"dataset.":[42],"Previous":[43],"work":[44],"on":[45,69,154,243],"controlling":[46],"the":[47,92,112,116,132,145,174,192,195,198,206,236],"style":[48,76,84,96,101,113,158,169,175,218],"generated":[50],"in":[52,131,137,239],"an":[53],"unsupervised":[54],"way":[55],"can":[56],"be":[57],"divided":[58],"into":[59],"two":[60,222],"ways:":[61],"implicitly":[62],"explicitly.":[64],"The":[65],"former":[66],"mainly":[67],"relies":[68],"well-trained":[71],"language":[72,119],"model":[73],"capture":[75],"knowledge,":[77],"which":[78],"is":[79],"limited":[80],"single":[83],"hard":[86],"handle":[88],"multi-style":[89],"task.":[90],"Thus,":[91],"latter":[93],"uses":[94],"extra":[95],"constraints":[97],"such":[98,124],"as":[99,125],"outlined":[100],"labels":[102],"or":[103],"words":[105,139],"extracted":[106],"from":[107,160],"sentences":[109],"control":[111],"rather":[114],"than":[115],"trained":[117],"style-specific":[118],"model.":[120],"certain":[122],"styles,":[123],"humorous":[126],"romance,":[128],"implied":[130,244],"whole":[133],"sentence,":[134],"instead":[135],"some":[138],"sentence.":[142],"To":[143],"address":[144],"problems":[146],"above,":[147],"we":[148,212],"propose":[149],"two-step":[151],"method":[152,234],"based":[153],"Transformer:":[155],"firstly":[156],"detach":[157],"representations":[159,176,219],"text-only":[163],"corpus":[164],"provide":[166],"more":[167],"holistic":[168],"supervision,":[170],"secondly":[172],"attach":[173],"captions.":[183],"We":[184],"learn":[185],"shared":[187],"image-text":[188],"space":[189],"narrow":[191],"gap":[193],"between":[194,208],"text":[199],"modality":[200],"for":[201],"better":[202],"attachment.":[203],"Due":[204],"trade-off":[207],"semantics":[209],"style,":[211],"explore":[213],"three":[214],"injection":[215],"methods":[216],"balance":[221],"requirements":[223],"preservation":[227],"stylization.":[229],"Experiments":[230],"show":[231],"that":[232],"our":[233],"outperforms":[235],"state-of-the-art":[237],"systems":[238],"overall":[240],"performance,":[241],"especially":[242],"styles.":[245]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}