{"id":"https://openalex.org/W4394586590","doi":"https://doi.org/10.1109/iske60036.2023.10481500","title":"Positional Feature Generator-Based Transformer for Image Captioning","display_name":"Positional Feature Generator-Based Transformer for Image Captioning","publication_year":2023,"publication_date":"2023-11-17","ids":{"openalex":"https://openalex.org/W4394586590","doi":"https://doi.org/10.1109/iske60036.2023.10481500"},"language":"en","primary_location":{"id":"doi:10.1109/iske60036.2023.10481500","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iske60036.2023.10481500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 18th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","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/A5106765225","display_name":"Shuai He","orcid":"https://orcid.org/0009-0002-4447-6791"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai He","raw_affiliation_strings":["School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038725235","display_name":"Xiaobao Yang","orcid":"https://orcid.org/0000-0003-1515-8663"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobao Yang","raw_affiliation_strings":["School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China","School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210136859"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068927949","display_name":"Sugang Ma","orcid":"https://orcid.org/0000-0002-8588-8111"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sugang Ma","raw_affiliation_strings":["School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101333314","display_name":"Bohui Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohui Song","raw_affiliation_strings":["School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063982599","display_name":"Ziqing He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqing He","raw_affiliation_strings":["School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100590502","display_name":"Wei Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Luo","raw_affiliation_strings":["School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi&#x0027;an University of Posts and Telecommunications,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210136859"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"418","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.9941999912261963,"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":0.8976069688796997},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7480747103691101},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6855003833770752},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5036036372184753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4752117097377777},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4452635645866394},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44390103220939636},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41660356521606445},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39838677644729614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3305102586746216},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.22965297102928162},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13458630442619324},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09922412037849426}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8976069688796997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480747103691101},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6855003833770752},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5036036372184753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4752117097377777},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4452635645866394},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44390103220939636},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41660356521606445},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39838677644729614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3305102586746216},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.22965297102928162},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13458630442619324},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09922412037849426},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iske60036.2023.10481500","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iske60036.2023.10481500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 18th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2912150279","https://openalex.org/W2946976711","https://openalex.org/W2952122856","https://openalex.org/W2963101956","https://openalex.org/W2963925437","https://openalex.org/W2964110616","https://openalex.org/W2965697393","https://openalex.org/W2968660381","https://openalex.org/W2974212192","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W2995971510","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3094502228","https://openalex.org/W3102094970","https://openalex.org/W3124149278","https://openalex.org/W3138516171","https://openalex.org/W3139049060","https://openalex.org/W3149261839","https://openalex.org/W3155806510","https://openalex.org/W3195680250","https://openalex.org/W3197762246","https://openalex.org/W3200520312","https://openalex.org/W3203790606","https://openalex.org/W4221143761","https://openalex.org/W4221147537","https://openalex.org/W4224247648","https://openalex.org/W4226013992","https://openalex.org/W4292972218","https://openalex.org/W4362710615","https://openalex.org/W4385245566","https://openalex.org/W6621906925","https://openalex.org/W6677994088","https://openalex.org/W6682631176","https://openalex.org/W6772203101","https://openalex.org/W6775034530","https://openalex.org/W6792695861","https://openalex.org/W6793987055","https://openalex.org/W6809536152","https://openalex.org/W6811230874"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4323777661","https://openalex.org/W4388184981"],"abstract_inverted_index":{"The":[0],"Transformer-based":[1],"architecture":[2,88],"achieves":[3],"state-of-the-art":[4,160,174],"results":[5],"in":[6,103],"image":[7,105,175],"captioning.":[8],"Due":[9],"to":[10,18,28,65,89,142],"its":[11],"non-recurrent":[12],"nature,":[13],"additional":[14,32,140],"positional":[15,26,95,107,127,135,161,165],"information":[16,27,66,136],"needs":[17],"be":[19],"provided.":[20],"However,":[21],"existing":[22],"advanced":[23],"methods":[24],"attach":[25],"the":[29,41,53,69,76,79,91,125,130,134,152],"model":[30],"by":[31,60,109],"encoding":[33],"or":[34,50],"embedding,":[35],"which":[36,63,112],"is":[37,101,170],"independently":[38],"decoupled":[39],"from":[40],"original":[42,131],"input":[43,58],"features.":[44],"In":[45,81],"addition,":[46],"no":[47],"matter":[48],"absolute":[49,115],"relative":[51,119],"methods,":[52,163],"encodings":[54],"are":[55],"fused":[56],"with":[57,129,172],"features":[59,73,128],"add":[61],"operation,":[62],"leads":[64],"interference":[67],"between":[68],"two":[70],"types":[71],"of":[72,78,154],"and":[74,118,164],"affects":[75],"performance":[77],"model.":[80],"this":[82],"paper,":[83],"we":[84,123],"propose":[85],"a":[86,138],"novel":[87],"remedy":[90],"above":[92],"limitations,":[93],"called":[94],"feature":[96,141,144,166],"generator":[97],"(PFG).":[98],"This":[99],"module":[100],"effective":[102],"modeling":[104],"spatial":[106],"frame":[108],"graph":[110],"structure,":[111],"can":[113],"learn":[114],"position":[116,120],"explicitly":[117],"implicitly.":[121],"Meanwhile,":[122],"concatenate":[124],"captured":[126],"features,":[132],"making":[133],"as":[137],"separate":[139],"avoid":[143],"interference.":[145],"Extensive":[146],"experiments":[147],"on":[148],"MS":[149],"COCO":[150],"validate":[151],"effectiveness":[153],"PFG.":[155],"Moreover,":[156],"PFG":[157],"outperforms":[158],"some":[159,173],"representation":[162],"generator-based":[167],"Transformer":[168],"(PFGT)":[169],"competitive":[171],"captioning":[176],"algorithms.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
