{"id":"https://openalex.org/W4364302332","doi":"https://doi.org/10.1109/tmm.2023.3265842","title":"Prompt-Based Learning for Unpaired Image Captioning","display_name":"Prompt-Based Learning for Unpaired Image Captioning","publication_year":2023,"publication_date":"2023-04-10","ids":{"openalex":"https://openalex.org/W4364302332","doi":"https://doi.org/10.1109/tmm.2023.3265842"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3265842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3265842","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005997048","display_name":"Peipei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peipei Zhu","raw_affiliation_strings":["School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411426","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0001-6117-6745"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727060","display_name":"Lin Zhu","orcid":"https://orcid.org/0000-0001-6487-0441"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhu","raw_affiliation_strings":["School of Computer Science, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087628708","display_name":"Zhenglong Sun","orcid":"https://orcid.org/0000-0002-8135-1659"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenglong Sun","raw_affiliation_strings":["School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050904","display_name":"Wei\u2010Shi Zheng","orcid":"https://orcid.org/0000-0001-8327-0003"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Shi Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631216","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0003-2197-9038"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002277899","display_name":"Chang Wen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Changwen Chen","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5005997048"],"corresponding_institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":4.6827,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96166397,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"379","last_page":"393"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9768999814987183,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.965399980545044,"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/closed-captioning","display_name":"Closed captioning","score":0.9940491318702698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8676600456237793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.623722493648529},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.615319013595581},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5577436685562134},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5148860216140747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49102330207824707},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4856035113334656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41742315888404846},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.41706582903862},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41459906101226807},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3455815613269806}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9940491318702698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676600456237793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.623722493648529},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.615319013595581},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5577436685562134},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5148860216140747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49102330207824707},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4856035113334656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41742315888404846},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.41706582903862},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41459906101226807},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3455815613269806},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3265842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3265842","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2366631306","display_name":null,"funder_award_id":"62102205","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"},{"id":"https://openalex.org/F4320327514","display_name":"Beijing Institute of Technology Research Fund Program for Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2173180041","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2588822708","https://openalex.org/W2706870434","https://openalex.org/W2745461083","https://openalex.org/W2885138528","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2890718122","https://openalex.org/W2896348597","https://openalex.org/W2906314281","https://openalex.org/W2913618459","https://openalex.org/W2963084599","https://openalex.org/W2963175879","https://openalex.org/W2963622213","https://openalex.org/W2963743213","https://openalex.org/W2963846044","https://openalex.org/W2963992143","https://openalex.org/W2965922392","https://openalex.org/W2970327218","https://openalex.org/W2974212192","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2987327987","https://openalex.org/W2990307191","https://openalex.org/W2992478697","https://openalex.org/W3004328990","https://openalex.org/W3009270862","https://openalex.org/W3018388102","https://openalex.org/W3034493371","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3041184466","https://openalex.org/W3045147787","https://openalex.org/W3086385316","https://openalex.org/W3103211586","https://openalex.org/W3110019360","https://openalex.org/W3135254306","https://openalex.org/W3153427360","https://openalex.org/W3172675210","https://openalex.org/W3185341429","https://openalex.org/W3188542058","https://openalex.org/W3198377975","https://openalex.org/W3198571508","https://openalex.org/W3202527317","https://openalex.org/W3207493267","https://openalex.org/W3210065386","https://openalex.org/W3210129272","https://openalex.org/W4205304057","https://openalex.org/W4249013746","https://openalex.org/W4282968790","https://openalex.org/W4287891464","https://openalex.org/W4292828275","https://openalex.org/W4294568686","https://openalex.org/W4312238419","https://openalex.org/W4312320490","https://openalex.org/W4312651322","https://openalex.org/W4312818263","https://openalex.org/W4312971576","https://openalex.org/W4391451889","https://openalex.org/W6715501732","https://openalex.org/W6739636028","https://openalex.org/W6743895910","https://openalex.org/W6763509872","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6797265648","https://openalex.org/W6798350552"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4388002133"],"abstract_inverted_index":{"Unpaired":[0],"Image":[1],"Captioning":[2],"(UIC)":[3],"has":[4],"been":[5],"developed":[6],"to":[7,40,71,142],"learn":[8,41],"image":[9,80],"descriptions":[10],"from":[11,81,149],"unaligned":[12],"vision-language":[13],"sample":[14],"pairs.":[15],"Existing":[16],"works":[17,36],"usually":[18],"tackle":[19],"this":[20,67,113],"task":[21],"using":[22],"adversarial":[23,132],"learning":[24,99,133],"and":[25,47,108,120,154,167],"visual":[26,123],"concept":[27],"reward":[28],"based":[29,198],"on":[30,164],"reinforcement":[31],"learning.":[32],"However,":[33],"these":[34],"existing":[35],"were":[37],"only":[38],"able":[39],"limited":[42],"cross-domain":[43,74],"information":[44,76],"in":[45,66,100,158],"vision":[46,109],"language":[48],"domains,":[49],"which":[50],"restrains":[51],"the":[52,59,73,82,86,131,150,156,165,172,177,183,196],"captioning":[53,152,174],"performance":[54],"of":[55,61,97,176,193],"UIC.":[56],"Inspired":[57],"by":[58,94],"success":[60],"Vision-Language":[62],"Pre-Trained":[63],"Models":[64],"(VL-PTMs)":[65],"research,":[68],"we":[69],"attempt":[70],"infer":[72],"cue":[75],"about":[77],"a":[78,115,137,190],"given":[79],"large":[83],"VL-PTMs":[84,197],"for":[85,125,195],"UIC":[87,186],"task.":[88],"This":[89],"research":[90,194],"is":[91,118,140],"also":[92],"motivated":[93],"recent":[95],"successes":[96],"prompt":[98,117,139],"many":[101],"downstream":[102],"multi-modal":[103],"tasks,":[104],"including":[105],"image-text":[106],"retrieval":[107],"question":[110],"answering.":[111],"In":[112,135],"work,":[114],"semantic":[116],"introduced":[119],"aggregated":[121],"with":[122],"features":[124],"more":[126],"accurate":[127],"caption":[128],"prediction":[129],"under":[130],"framework.":[134],"addition,":[136],"metric":[138],"designed":[141],"select":[143],"high-quality":[144],"pseudo":[145],"image-caption":[146],"samples":[147],"obtained":[148],"basic":[151],"model":[153,157,187],"refine":[155],"an":[159],"iterative":[160],"manner.":[161],"Extensive":[162],"experiments":[163],"COCO":[166],"Flickr30":[168],"K":[169],"datasets":[170],"validate":[171],"promising":[173],"ability":[175],"proposed":[178,184],"model.":[179],"We":[180],"expect":[181],"that":[182],"prompt-based":[185],"will":[188],"stimulate":[189],"new":[191],"line":[192],"captioning.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":8}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}