{"id":"https://openalex.org/W4412151908","doi":"https://doi.org/10.32604/cmc.2025.065169","title":"LREGT: Local Relationship Enhanced Gated Transformer for Image Captioning","display_name":"LREGT: Local Relationship Enhanced Gated Transformer for Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412151908","doi":"https://doi.org/10.32604/cmc.2025.065169"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.065169","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.065169","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials &amp; Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.065169","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101476695","display_name":"Yuting He","orcid":"https://orcid.org/0000-0003-0878-8915"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuting He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051764820","display_name":"Zetao Jiang","orcid":"https://orcid.org/0000-0002-0914-2131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zetao Jiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101476695"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1850168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"84","issue":"3","first_page":"5487","last_page":"5508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9929999709129333,"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":0.9860000014305115,"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":0.902381420135498},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5467320084571838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4709758758544922},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39926642179489136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33733081817626953},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.16948091983795166},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14621281623840332},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05026659369468689}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.902381420135498},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5467320084571838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4709758758544922},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39926642179489136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33733081817626953},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.16948091983795166},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14621281623840332},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05026659369468689}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.065169","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.065169","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials &amp; Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.065169","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.065169","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials &amp; Continua","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2149557440","https://openalex.org/W2887272576","https://openalex.org/W2968660381","https://openalex.org/W2979739834","https://openalex.org/W3119689583","https://openalex.org/W3137159235","https://openalex.org/W3165078055","https://openalex.org/W3165571294","https://openalex.org/W3203790606","https://openalex.org/W3216130706","https://openalex.org/W3217347476","https://openalex.org/W4205357838","https://openalex.org/W4226397058","https://openalex.org/W4283722434","https://openalex.org/W4293529812","https://openalex.org/W4309701236","https://openalex.org/W4311310217","https://openalex.org/W4320487288","https://openalex.org/W4322761295","https://openalex.org/W4393851641","https://openalex.org/W4396803121","https://openalex.org/W4400412379","https://openalex.org/W4402536165","https://openalex.org/W4403182929","https://openalex.org/W4405812114"],"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-based":[1],"image":[2,24,191],"captioning":[3],"models":[4,28],"typically":[5],"rely":[6],"on":[7,49,194],"the":[8,20,39,58,67,75,80,90,102,109,131,136,157,164,184,195],"self-attention":[9],"mechanism":[10],"to":[11,148,162,183],"capture":[12],"long-range":[13],"dependencies,":[14],"which":[15,114],"effectively":[16,33],"extracts":[17,41],"and":[18,43,108,127,176,188,211,231],"leverages":[19],"global":[21,42,126],"correlation":[22],"of":[23,98,167,186,209,214],"features.":[25],"However,":[26],"these":[27,63,168],"still":[29],"face":[30],"challenges":[31],"in":[32,226],"capturing":[34,227],"local":[35,44,128],"associations.":[36],"Moreover,":[37],"since":[38],"encoder":[40,76],"association":[45],"features":[46],"that":[47,123,200],"focus":[48],"different":[50],"semantic":[51,53,233],"information,":[52],"noise":[54,234],"may":[55],"occur":[56],"during":[57,235],"decoding":[59,146],"stage.":[60],"To":[61],"address":[62],"issues,":[64],"we":[65,78,134],"propose":[66,135],"Local":[68,81,91,103],"Relationship":[69,82,92],"Enhanced":[70,83,93],"Gated":[71,139],"Transformer":[72],"(LREGT).":[73],"In":[74,130],"part,":[77,133],"introduce":[79],"Encoder":[84],"(LREE),":[85],"whose":[86],"core":[87],"component":[88],"is":[89],"Module":[94,106,112],"(LREM).":[95],"LREM":[96],"consists":[97],"two":[99],"novel":[100],"designs:":[101],"Correlation":[104],"Perception":[105],"(LCPM)":[107],"Local-Global":[110],"Fusion":[111],"(LGFM),":[113],"are":[115],"beneficial":[116],"for":[117],"generating":[118],"a":[119,206],"comprehensive":[120],"feature":[121,152],"representation":[122],"integrates":[124],"both":[125],"information.":[129],"decoder":[132],"Dual-level":[137],"Multi-branch":[138],"Decoder":[140],"(DMGD).":[141],"It":[142],"first":[143],"creates":[144],"multiple":[145],"branches":[147],"generate":[149],"multi-perspective":[150,169],"contextual":[151,170],"representations.":[153,179],"Subsequently,":[154],"it":[155],"employs":[156],"Dual-Level":[158],"Gating":[159],"Mechanism":[160],"(DLGM)":[161],"model":[163],"multi-level":[165],"relationships":[166,230],"features,":[171],"enhancing":[172],"their":[173],"fine-grained":[174],"semantics":[175],"intrinsic":[177],"relationship":[178],"This":[180],"ultimately":[181],"leads":[182],"generation":[185],"high-quality":[187],"semantically":[189],"rich":[190],"captions.":[192],"Experiments":[193],"standard":[196],"MSCOCO":[197],"dataset":[198],"demonstrate":[199],"LREGT":[201],"achieves":[202],"state-of-the-art":[203],"performance,":[204],"with":[205],"CIDEr":[207],"score":[208,213],"140.8":[210],"BLEU-4":[212],"41.3,":[215],"significantly":[216],"outperforming":[217],"existing":[218],"mainstream":[219],"methods.":[220],"These":[221],"results":[222],"highlight":[223],"LREGT\u2019s":[224],"superiority":[225],"complex":[228],"visual":[229],"resolving":[232],"decoding.":[236]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
