{"id":"https://openalex.org/W4411336742","doi":"https://doi.org/10.1109/jiot.2025.3579587","title":"Transformer-Based Nonautoregressive Image Captioning via Guided Keyword Generation and Learnable Positional Encoding for IoT Devices","display_name":"Transformer-Based Nonautoregressive Image Captioning via Guided Keyword Generation and Learnable Positional Encoding for IoT Devices","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4411336742","doi":"https://doi.org/10.1109/jiot.2025.3579587"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2025.3579587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3579587","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","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/A5067164185","display_name":"Yuanqiu Liu","orcid":"https://orcid.org/0009-0006-7676-2599"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqiu Liu","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0006-7676-2599","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102728606","display_name":"Hong Yu","orcid":"https://orcid.org/0000-0003-4807-1812"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Yu","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-4807-1812","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729918","display_name":"Hui Li","orcid":"https://orcid.org/0000-0002-8802-4896"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001008172","display_name":"Xin Han","orcid":"https://orcid.org/0000-0002-1694-7712"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Han","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403816","display_name":"Xiaotong Zhang","orcid":"https://orcid.org/0000-0002-5013-8476"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotong Zhang","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-5013-8476","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029498141","display_name":"Han Liu","orcid":"https://orcid.org/0000-0001-6921-2050"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6921-2050","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7104685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":"17","first_page":"35320","last_page":"35328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9876999855041504,"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":0.9483147263526917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8360703587532043},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7162631750106812},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5762727856636047},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5710612535476685},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44923830032348633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4412647783756256},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40625613927841187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39543989300727844},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10272151231765747}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9483147263526917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360703587532043},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7162631750106812},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5762727856636047},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5710612535476685},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44923830032348633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4412647783756256},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40625613927841187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39543989300727844},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10272151231765747},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3579587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3579587","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G11042728","display_name":null,"funder_award_id":"62206038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1288713985","display_name":null,"funder_award_id":"62106035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G600704232","display_name":null,"funder_award_id":"HZKY20220419","funder_id":"https://openalex.org/F4320336581","funder_display_name":"Chunhui Project Foundation of the Education Department of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336581","display_name":"Chunhui Project Foundation of the Education Department of China","ror":null},{"id":"https://openalex.org/F4320336656","display_name":"Thousand Young Talents Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2145607950","https://openalex.org/W2194775991","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963434219","https://openalex.org/W2963536265","https://openalex.org/W2963736842","https://openalex.org/W2964253311","https://openalex.org/W3035366542","https://openalex.org/W3035463379","https://openalex.org/W3093394956","https://openalex.org/W3138516171","https://openalex.org/W3174046981","https://openalex.org/W3205981128","https://openalex.org/W3210150990","https://openalex.org/W4221147537","https://openalex.org/W4282968790","https://openalex.org/W4312289196","https://openalex.org/W4312561350","https://openalex.org/W4313131769","https://openalex.org/W4375868765","https://openalex.org/W4382460199","https://openalex.org/W4385245566","https://openalex.org/W4386072307","https://openalex.org/W4391092966","https://openalex.org/W4393160218","https://openalex.org/W4400770846","https://openalex.org/W4404056934","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6676497082","https://openalex.org/W6682631176","https://openalex.org/W6746208923","https://openalex.org/W6763677924","https://openalex.org/W6771550610","https://openalex.org/W6779823529","https://openalex.org/W6784094891","https://openalex.org/W6797256274","https://openalex.org/W6844872470"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","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],"emergence":[1],"of":[2,6,21,100,153],"the":[3,37,52,65,98,119,145,157,167,174,178],"Intelligent":[4],"Internet":[5],"Things":[7],"(IIoT)":[8],"has":[9,41,47],"brought":[10],"data":[11,15],"processing":[12,20],"closer":[13],"to":[14,50,89,139,165],"sources,":[16],"especially":[17],"for":[18,56],"real-time":[19],"surveillance":[22],"video":[23],"and":[24,76,94,110,123],"image":[25,57,127,135,146,195],"analysis.":[26],"Image":[27],"captioning":[28,58],"plays":[29],"a":[30,105,130,150,201],"crucial":[31],"role":[32],"in":[33,44,78,104,169,193],"understanding":[34],"images.":[35],"However,":[36],"Transformer":[38],"architecture,":[39],"which":[40,68],"become":[42],"prevalent":[43],"recent":[45],"applications,":[46],"been":[48],"observed":[49],"increase":[51],"computational":[53,71],"resources":[54],"required":[55],"models.":[59,112],"Conventionally,":[60],"most":[61],"existing":[62],"methods":[63],"use":[64,86],"autoregressive":[66,111],"paradigm,":[67],"reduces":[69],"their":[70],"efficiency":[72],"on":[73,182],"edge":[74],"devices":[75],"results":[77,103],"significant":[79],"inference":[80,92,203],"delays.":[81],"In":[82],"this":[83,115],"paper,":[84],"we":[85,117],"non-autoregressive":[87,109,126,158,194],"paradigms":[88],"improve":[90],"its":[91],"speed":[93],"model":[95,132,189,199],"efficiency.":[96],"Nevertheless,":[97],"lack":[99],"effective":[101],"inputs":[102],"performance":[106,192],"gap":[107],"between":[108],"To":[113],"bridge":[114],"gap,":[116],"propose":[118],"learnable":[120],"positional":[121,161],"encoding":[122,162],"keyword":[124],"guided":[125,133],"captioning.":[128,196],"Firstly,":[129],"diffusion":[131],"by":[134],"features":[136],"is":[137,163],"employed":[138],"generate":[140],"keywords":[141],"that":[142,187],"accurately":[143],"reflect":[144],"content,":[147],"thereby":[148],"infusing":[149],"substantial":[151],"amount":[152],"semantic":[154],"information":[155],"into":[156],"decoder.":[159],"Secondly,":[160],"utilized":[164],"guide":[166],"decoder":[168],"generating":[170],"appropriate":[171],"words":[172],"at":[173],"correct":[175],"positions":[176],"within":[177],"caption.":[179],"Extensive":[180],"experiments":[181],"widely":[183],"used":[184],"benchmarks":[185],"demonstrate":[186],"our":[188,198],"achieves":[190],"state-of-the-art":[191],"Furthermore,":[197],"maintains":[200],"competitive":[202],"speed.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
