{"id":"https://openalex.org/W4393392493","doi":"https://doi.org/10.1007/s11063-024-11527-x","title":"Self-Enhanced Attention for Image Captioning","display_name":"Self-Enhanced Attention for Image Captioning","publication_year":2024,"publication_date":"2024-04-01","ids":{"openalex":"https://openalex.org/W4393392493","doi":"https://doi.org/10.1007/s11063-024-11527-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11063-024-11527-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11527-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11527-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11527-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100930998","display_name":"Qingyu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyu Sun","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390006","display_name":"Juan Zhang","orcid":"https://orcid.org/0000-0001-5089-723X"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Juan Zhang","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055905608","display_name":"Zhijun Fang","orcid":"https://orcid.org/0000-0001-8563-5678"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Fang","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071398995","display_name":"Yongbin Gao","orcid":"https://orcid.org/0000-0001-9930-0502"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbin Gao","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100390006"],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":2.6286,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91094773,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"56","issue":"2","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9948999881744385,"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":0.9858999848365784,"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/closed-captioning","display_name":"Closed captioning","score":0.9425790905952454},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.8154616355895996},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5855772495269775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5848885774612427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4089275598526001}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9425790905952454},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.8154616355895996},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5855772495269775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5848885774612427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4089275598526001}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11063-024-11527-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11527-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11527-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11063-024-11527-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11527-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11527-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393392493.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W1981276685","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2603777577","https://openalex.org/W2740118378","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2887272576","https://openalex.org/W2904711804","https://openalex.org/W2962784628","https://openalex.org/W2962918138","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963686907","https://openalex.org/W2979956313","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3015437081","https://openalex.org/W3034655362","https://openalex.org/W3034885317","https://openalex.org/W3035284526","https://openalex.org/W3035383808","https://openalex.org/W3107503524","https://openalex.org/W3126988965","https://openalex.org/W3127256111","https://openalex.org/W3129050402","https://openalex.org/W3153200530","https://openalex.org/W3167939936","https://openalex.org/W3169823210","https://openalex.org/W3175824375","https://openalex.org/W4285491539","https://openalex.org/W4303444943","https://openalex.org/W4311774713","https://openalex.org/W4311808028","https://openalex.org/W4312712450","https://openalex.org/W4387530892","https://openalex.org/W6600018615"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Abstract":[0],"Image":[1],"captioning,":[2],"which":[3,99],"involves":[4],"automatically":[5],"generating":[6,117],"textual":[7],"descriptions":[8],"based":[9,127],"on":[10,128,146],"the":[11,26,30,48,63,67,101,105,109,118,125,139,147,151,168,176,184,188],"content":[12],"of":[13,50,66,81,108,141,187,190],"images,":[14],"has":[15],"garnered":[16],"increasing":[17],"attention":[18,93,119],"from":[19],"researchers.":[20],"Recently,":[21],"Transformers":[22,37],"have":[23],"emerged":[24],"as":[25,74],"preferred":[27],"choice":[28],"for":[29],"language":[31],"model":[32],"in":[33,78,104],"image":[34],"captioning":[35],"models.":[36],"leverage":[38],"self-attention":[39,68,102],"mechanisms":[40],"to":[41,71,132,175],"address":[42,85],"gradient":[43,51],"accumulation":[44],"issues":[45],"and":[46,157],"eliminate":[47],"risk":[49],"explosion":[52],"commonly":[53],"associated":[54],"with":[55,153,195],"RNN":[56],"networks.":[57],"However,":[58],"a":[59,91],"challenge":[60,189],"arises":[61],"when":[62,165],"input":[64],"features":[65,194],"mechanism":[69,94,103],"belong":[70],"different":[72,154],"categories,":[73],"it":[75,122],"may":[76],"result":[77],"ineffective":[79],"highlighting":[80,192],"important":[82,135,193],"features.":[83,136],"To":[84,137],"this":[86],"issue,":[87],"our":[88,113,196],"paper":[89],"proposes":[90],"novel":[92],"called":[95],"Self-Enhanced":[96],"Attention":[97],"(SEA),":[98],"replaces":[100],"decoder":[106],"part":[107],"Transformer":[110],"model.":[111],"In":[112],"proposed":[114,197],"SEA,":[115,142,167],"after":[116],"weight":[120],"matrix,":[121],"further":[123],"adjusts":[124],"matrix":[126],"its":[129],"own":[130],"distribution":[131],"effectively":[133,191],"highlight":[134],"evaluate":[138],"effectiveness":[140],"we":[143],"conducted":[144],"experiments":[145],"COCO":[148],"dataset,":[149],"comparing":[150],"results":[152,162],"visual":[155],"models":[156],"training":[158],"strategies.":[159],"The":[160],"experimental":[161],"demonstrate":[163],"that":[164],"using":[166,180],"CIDEr":[169],"score":[170],"is":[171],"significantly":[172],"higher":[173],"compared":[174],"scores":[177],"obtained":[178],"without":[179],"SEA.":[181],"This":[182],"indicates":[183],"successful":[185],"addressing":[186],"mechanism.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}