{"id":"https://openalex.org/W4404704987","doi":"https://doi.org/10.1142/s146902682442001x","title":"Swin-Caption: Swin Transformer-Based Image Captioning with Feature Enhancement and Multi-Stage Fusion","display_name":"Swin-Caption: Swin Transformer-Based Image Captioning with Feature Enhancement and Multi-Stage Fusion","publication_year":2024,"publication_date":"2024-11-25","ids":{"openalex":"https://openalex.org/W4404704987","doi":"https://doi.org/10.1142/s146902682442001x"},"language":"en","primary_location":{"id":"doi:10.1142/s146902682442001x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s146902682442001x","pdf_url":null,"source":{"id":"https://openalex.org/S206936884","display_name":"International Journal of Computational Intelligence and Applications","issn_l":"1469-0268","issn":["1469-0268","1757-5885"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence and Applications","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/A5101978972","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0003-1544-693X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["Beijing Institute for Scientific and Engineering Computing, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China","Faculty of Science, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0003-1544-693X","affiliations":[{"raw_affiliation_string":"Beijing Institute for Scientific and Engineering Computing, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Science, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111059473","display_name":"Yidi Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidi Jiao","raw_affiliation_strings":["Faculty of Science, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697546","display_name":"Xiaoran Li","orcid":"https://orcid.org/0000-0003-2100-5751"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoran Li","raw_affiliation_strings":["Faculty of Science, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115589185","display_name":"Jing Li","orcid":"https://orcid.org/0000-0001-9593-6765"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["Faculty of Science, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science, Beijing University of Technology, Beijing, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457206","display_name":"Haitao Wang","orcid":"https://orcid.org/0000-0001-6910-974X"},"institutions":[{"id":"https://openalex.org/I4210146077","display_name":"China National Institute of Standardization","ror":"https://ror.org/03qzxj964","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210146077"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Wang","raw_affiliation_strings":["Fundamental Standardization, China National Institute of Standardization, Beijing, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundamental Standardization, China National Institute of Standardization, Beijing, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I4210146077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035901540","display_name":"Xinyu Cao","orcid":"https://orcid.org/0000-0002-4403-9762"},"institutions":[{"id":"https://openalex.org/I4210146077","display_name":"China National Institute of Standardization","ror":"https://ror.org/03qzxj964","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210146077"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Cao","raw_affiliation_strings":["Fundamental Standardization, China National Institute of Standardization, Beijing, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundamental Standardization, China National Institute of Standardization, Beijing, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I4210146077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2044,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.508506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"24","issue":"03","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9965999722480774,"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":0.9884999990463257,"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":0.9723056554794312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8919607996940613},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6817176342010498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6203595399856567},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.612140953540802},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5107159614562988},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49632054567337036},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4827412962913513},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4617133140563965},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39637547731399536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3770257830619812}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9723056554794312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8919607996940613},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6817176342010498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6203595399856567},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.612140953540802},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5107159614562988},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49632054567337036},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4827412962913513},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4617133140563965},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39637547731399536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3770257830619812},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s146902682442001x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s146902682442001x","pdf_url":null,"source":{"id":"https://openalex.org/S206936884","display_name":"International Journal of Computational Intelligence and Applications","issn_l":"1469-0268","issn":["1469-0268","1757-5885"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G342522193","display_name":null,"funder_award_id":"12272011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G901025815","display_name":null,"funder_award_id":"2022YFB3806000","funder_id":"https://openalex.org/F4320335774","funder_display_name":"Key Technologies Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335774","display_name":"Key Technologies Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2221837760","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2604178507","https://openalex.org/W2997248215","https://openalex.org/W3042529555","https://openalex.org/W3096691356","https://openalex.org/W3106925514","https://openalex.org/W3132366366","https://openalex.org/W3138516171","https://openalex.org/W3204740508","https://openalex.org/W3210416604","https://openalex.org/W4205357838","https://openalex.org/W4220696681","https://openalex.org/W4282920689","https://openalex.org/W4282962858","https://openalex.org/W4296197540","https://openalex.org/W4311310217","https://openalex.org/W4312811763","https://openalex.org/W4313890505"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"The":[0,109],"objective":[1],"of":[2,22,31,59],"image":[3,26,41,73,79,105],"captioning":[4,42],"is":[5,54,68,84,99],"to":[6,9,70,86,101],"empower":[7],"computers":[8],"generate":[10],"human-like":[11],"sentences":[12],"autonomously,":[13],"describing":[14],"a":[15,36,77,96],"provided":[16],"image.":[17],"To":[18],"tackle":[19],"the":[20,51,57,88,113,123],"challenges":[21],"insufficient":[23],"accuracy":[24],"in":[25,56,116],"feature":[27,44,66,74],"extraction":[28],"and":[29,46,80,104,119,128],"underutilization":[30],"visual":[32],"information,":[33],"we":[34],"present":[35],"Swin":[37,52],"Transformer-based":[38],"model":[39,111,115],"for":[40,62],"with":[43],"enhancement":[45,67],"multi-stage":[47,78],"fusion":[48,82],"(Swin-Caption).":[49],"Initially,":[50],"Transformer":[53],"employed":[55],"capacity":[58],"an":[60],"encoder":[61],"extracting":[63],"images,":[64],"while":[65],"adopted":[69],"gather":[71],"additional":[72],"information.":[75],"Subsequently,":[76],"semantic":[81,89,103],"module":[83],"constructed":[85],"utilize":[87],"information":[90],"from":[91],"past":[92],"time":[93],"steps.":[94],"Lastly,":[95],"two-layer":[97],"LSTM":[98],"utilized":[100],"decode":[102],"data,":[106],"generating":[107],"captions.":[108],"proposed":[110],"outperforms":[112],"baseline":[114],"experimental":[117],"tests":[118],"instance":[120],"analysis":[121],"on":[122],"public":[124],"datasets":[125],"Flickr8K,":[126],"Flickr30K,":[127],"MS-COCO.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
