{"id":"https://openalex.org/W4412880753","doi":"https://doi.org/10.1002/aisy.202500104","title":"End\u2010to\u2010End Attention\u2010Enhanced Transformer for Image Captioning in Biomimetic Wearable Devices","display_name":"End\u2010to\u2010End Attention\u2010Enhanced Transformer for Image Captioning in Biomimetic Wearable Devices","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412880753","doi":"https://doi.org/10.1002/aisy.202500104"},"language":"en","primary_location":{"id":"doi:10.1002/aisy.202500104","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202500104","pdf_url":null,"source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1002/aisy.202500104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024464852","display_name":"Yi Yin","orcid":"https://orcid.org/0000-0003-2807-0476"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongyang Yin","raw_affiliation_strings":["School of Electronic Science and Engineering Nanjing University  Nanjing Jiangsu 210023 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering Nanjing University  Nanjing Jiangsu 210023 China","institution_ids":["https://openalex.org/I36399199","https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hengyu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyu Cao","raw_affiliation_strings":["School of Information and Control Engineering China University of Mining and Technology  Xuzhou Jiangsu 221008 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering China University of Mining and Technology  Xuzhou Jiangsu 221008 China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Lin","orcid":"https://orcid.org/0009-0006-0107-4329"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lin","raw_affiliation_strings":["School of Electronic Science and Engineering Nanjing University  Nanjing Jiangsu 210023 China"],"raw_orcid":"https://orcid.org/0009-0006-0107-4329","affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering Nanjing University  Nanjing Jiangsu 210023 China","institution_ids":["https://openalex.org/I36399199","https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024464852"],"corresponding_institution_ids":["https://openalex.org/I200845125","https://openalex.org/I36399199"],"apc_list":{"value":2750,"currency":"USD","value_usd":2750},"apc_paid":{"value":2750,"currency":"USD","value_usd":2750},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15842293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"12","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":0.9991999864578247,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9983999729156494,"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":0.9262335300445557},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.7352710962295532},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6801642775535583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5227789282798767},{"id":"https://openalex.org/keywords/wearable-technology","display_name":"Wearable technology","score":0.46940577030181885},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39771246910095215},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37793296575546265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3494115471839905},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.30593764781951904},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.28733742237091064},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.15771228075027466}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9262335300445557},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.7352710962295532},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6801642775535583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5227789282798767},{"id":"https://openalex.org/C54290928","wikidata":"https://www.wikidata.org/wiki/Q4845080","display_name":"Wearable technology","level":3,"score":0.46940577030181885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39771246910095215},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37793296575546265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3494115471839905},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30593764781951904},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.28733742237091064},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.15771228075027466},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/aisy.202500104","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202500104","pdf_url":null,"source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:dc4b40ce4bd24daca39719eac634f66e","is_oa":true,"landing_page_url":"https://doaj.org/article/dc4b40ce4bd24daca39719eac634f66e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advanced Intelligent Systems, Vol 7, Iss 12, Pp n/a-n/a (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1002/aisy.202500104","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202500104","pdf_url":null,"source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2999635570","https://openalex.org/W3091588028","https://openalex.org/W3136792391","https://openalex.org/W3137513727","https://openalex.org/W4225163098","https://openalex.org/W4293529812","https://openalex.org/W4320487288","https://openalex.org/W4396918399","https://openalex.org/W4399049659","https://openalex.org/W4401415649","https://openalex.org/W4402754015"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"Existing":[0],"transformer\u2010based":[1],"image":[2,45],"captioning":[3,46],"methods":[4],"face":[5],"two":[6],"primary":[7],"limitations:":[8],"first,":[9],"they":[10],"struggle":[11],"to":[12,29,81,138,152],"adequately":[13],"represent":[14],"visual":[15,55,112],"features":[16,56],"from":[17],"multiple":[18],"regions":[19],"during":[20,35],"the":[21,26,36,51,92,99,120,124,141,150,169,174,177,186,193],"encoding":[22,52],"phase,":[23,53,126],"and":[24,62,69,95,145,155,163],"second,":[25],"decoder":[27],"fails":[28],"effectively":[30,158],"utilize":[31],"future":[32,146,156],"semantic":[33,147],"information":[34,94],"inference":[37],"phase.":[38],"To":[39],"address":[40],"these":[41],"challenges,":[42],"an":[43,132],"attention\u2010enhanced":[44],"model":[47,83,102,151,175],"is":[48,79,103,136],"proposed.":[49],"During":[50],"multigranular":[54],"are":[57],"integrated":[58],"by":[59,89],"combining":[60],"cross\u2010attention":[61],"self\u2010attention":[63,77],"mechanisms,":[64],"fully":[65,90],"utilizing":[66],"both":[67],"grid":[68],"regional":[70],"features.":[71],"Additionally,":[72],"a":[73,115,127,180],"novel":[74],"dense":[75],"global":[76],"module":[78,135],"introduced":[80],"enhance":[82],"performance":[84],"with":[85,131,199],"minimal":[86,200],"computational":[87],"cost":[88],"leveraging":[91],"contextual":[93],"fine\u2010grained":[96],"details":[97],"of":[98],"image.":[100],"This":[101],"particularly":[104],"well\u2010suited":[105],"for":[106,159],"biomimetic":[107],"wearable":[108,194],"devices,":[109],"where":[110],"real\u2010time":[111,197],"assistance":[113],"plays":[114],"crucial":[116],"role":[117],"in":[118,185,207],"enhancing":[119],"user":[121],"experience.":[122],"In":[123],"decoding":[125,129],"bidirectional":[128],"structure":[130],"adaptive":[133],"masking":[134],"designed":[137],"dynamically":[139],"adjust":[140],"focus":[142],"on":[143,168,192],"past":[144],"information,":[148],"enabling":[149],"combine":[153],"historical":[154],"context":[157],"generating":[160],"more":[161],"accurate":[162],"relevant":[164],"descriptions.":[165],"Experimental":[166],"results":[167],"MSCOCO":[170],"dataset":[171],"show":[172],"that":[173],"outperforms":[176],"baseline,":[178],"achieving":[179],"2.1":[181],"percentage":[182],"point":[183],"improvement":[184],"CIDEr":[187],"metric.":[188],"Comprehensive":[189],"hardware":[190],"evaluations":[191],"platform":[195],"demonstrate":[196],"efficiency":[198],"memory":[201],"footprint,":[202],"significantly":[203],"outperforming":[204],"state\u2010of\u2010the\u2010art":[205],"models":[206],"edge":[208],"deployment":[209],"scenarios.":[210]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
