{"id":"https://openalex.org/W4387754140","doi":"https://doi.org/10.1109/icnc-fskd59587.2023.10281090","title":"Swin Transformer-based Image Captioning with Feature Enhancement and Multi-stage Fusion","display_name":"Swin Transformer-based Image Captioning with Feature Enhancement and Multi-stage Fusion","publication_year":2023,"publication_date":"2023-07-29","ids":{"openalex":"https://openalex.org/W4387754140","doi":"https://doi.org/10.1109/icnc-fskd59587.2023.10281090"},"language":"en","primary_location":{"id":"doi:10.1109/icnc-fskd59587.2023.10281090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnc-fskd59587.2023.10281090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100349618","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0003-1299-9854"},"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 University of Technology,Faculty of Science,Beijing,China","Beijing Institute for Scientific and Engineering Computing, Beijing University of Technology, Beijing, China","Faculty of Science, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Science,Beijing,China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Institute for Scientific and Engineering Computing, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Science, Beijing University of Technology, Beijing, China","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":["Beijing University of Technology,Faculty of Science,Beijing,China","Faculty of Science, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Science,Beijing,China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Science, Beijing University of Technology, Beijing, China","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":["Beijing University of Technology,Faculty of Science,Beijing,China","Faculty of Science, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Science,Beijing,China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101828523","display_name":"Jing Li","orcid":"https://orcid.org/0000-0002-8235-9038"},"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":["Beijing University of Technology,Faculty of Science,Beijing,China","Faculty of Science, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Science,Beijing,China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457231","display_name":"Haitao Wang","orcid":"https://orcid.org/0000-0002-6775-0346"},"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":["China National Institute of Standardization,Fundamental Standardization,Beijing,China","Fundamental Standardization, China National Institute of Standardization, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China National Institute of Standardization,Fundamental Standardization,Beijing,China","institution_ids":["https://openalex.org/I4210146077"]},{"raw_affiliation_string":"Fundamental Standardization, China National Institute of Standardization, Beijing, China","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":["China National Institute of Standardization,Fundamental Standardization,Beijing,China","Fundamental Standardization, China National Institute of Standardization, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China National Institute of Standardization,Fundamental Standardization,Beijing,China","institution_ids":["https://openalex.org/I4210146077"]},{"raw_affiliation_string":"Fundamental Standardization, China National Institute of Standardization, Beijing, China","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":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9957000017166138,"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":0.9905999898910522,"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":0.9654098749160767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8078631162643433},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6843775510787964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6390112638473511},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6211711168289185},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5721898674964905},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48082125186920166},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47281113266944885},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46382513642311096},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.444292813539505},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4263848066329956},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3803589940071106},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08905920386314392},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06481081247329712}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9654098749160767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078631162643433},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6843775510787964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6390112638473511},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6211711168289185},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5721898674964905},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48082125186920166},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47281113266944885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46382513642311096},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.444292813539505},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4263848066329956},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3803589940071106},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08905920386314392},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06481081247329712},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnc-fskd59587.2023.10281090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnc-fskd59587.2023.10281090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1603598191","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1969616664","https://openalex.org/W2010351326","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2131179926","https://openalex.org/W2221837760","https://openalex.org/W2550553598","https://openalex.org/W2600463316","https://openalex.org/W2601748485","https://openalex.org/W2604178507","https://openalex.org/W2997248215","https://openalex.org/W3096691356","https://openalex.org/W3106925514","https://openalex.org/W3132366366","https://openalex.org/W3138516171","https://openalex.org/W3210416604","https://openalex.org/W4205357838","https://openalex.org/W4226236069","https://openalex.org/W4313890505","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6600334730","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6639118148","https://openalex.org/W6676497082","https://openalex.org/W6678262379","https://openalex.org/W6685230081","https://openalex.org/W6739901393","https://openalex.org/W6810574305"],"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":[0,112],"objective":[1],"of":[2,22,31,57,63],"image":[3,26,39,65,77,82,107],"captioning":[4,40],"involves":[5],"empowering":[6],"computers":[7],"to":[8,72,89,102],"autonomously":[9],"produce":[10],"human-like":[11],"sentences":[12],"that":[13],"depict":[14],"a":[15,36,80],"provided":[16],"image.":[17],"To":[18],"address":[19],"the":[20,49,55,61,91,104,122],"issues":[21],"insufficient":[23],"accuracy":[24],"in":[25,54,118],"feature":[27,43,68],"extraction":[28],"and":[29,45,67,83,106,109,126],"underutilization":[30],"visual":[32],"information,":[33],"we":[34],"propose":[35],"Swin":[37,50],"Transformer-based":[38],"model":[41,114],"with":[42],"enhancement":[44,69],"multi-stage":[46,81],"fusion.":[47],"First,":[48],"Transformer":[51],"is":[52,70,87,100],"employed":[53],"capacity":[56],"an":[58],"encoder":[59],"for":[60],"purpose":[62],"extracting":[64],"features,":[66],"adopted":[71],"capture":[73],"more":[74],"information":[75,93,108],"about":[76],"features.":[78],"Then,":[79],"semantic":[84,92,105],"fusion":[85],"module":[86],"constructed":[88],"utilize":[90],"from":[94],"past":[95],"time":[96],"steps.":[97],"Finally,":[98],"LSTM":[99],"used":[101],"decode":[103],"generate":[110],"captions.":[111],"proposed":[113],"achieves":[115],"better":[116],"results":[117],"baseline":[119],"tests":[120],"on":[121],"public":[123],"datasets":[124],"Flickr8K":[125],"Flickr30K.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
