{"id":"https://openalex.org/W4404393436","doi":"https://doi.org/10.1142/s0218001424540181","title":"Multi-Layer Gated Recurrent Unit-Based Recurrent Neural Network for Image Captioning","display_name":"Multi-Layer Gated Recurrent Unit-Based Recurrent Neural Network for Image Captioning","publication_year":2024,"publication_date":"2024-11-15","ids":{"openalex":"https://openalex.org/W4404393436","doi":"https://doi.org/10.1142/s0218001424540181"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001424540181","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001424540181","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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/A5087114343","display_name":"\u00d6zkan \u00c7AYLI","orcid":"https://orcid.org/0000-0002-3389-3867"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"\u00d6zkan \u00c7ayl\u0131","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3389-3867","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063512115","display_name":"Volkan K\u0131l\u0131\u00e7","orcid":"https://orcid.org/0000-0002-3164-1981"},"institutions":[{"id":"https://openalex.org/I250383648","display_name":"Izmir K\u00e2tip \u00c7elebi University","ror":"https://ror.org/024nx4843","country_code":"TR","type":"education","lineage":["https://openalex.org/I250383648"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Volkan K\u0131l\u0131\u00e7","raw_affiliation_strings":["Department of Electrical and Electronics Engineering, \u0130zmir Katip \u00c7elebi University, \u00c7i\u011fli 35620, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0002-3164-1981","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, \u0130zmir Katip \u00c7elebi University, \u00c7i\u011fli 35620, T\u00fcrkiye","institution_ids":["https://openalex.org/I250383648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001374957","display_name":"Aytu\u011f Onan","orcid":"https://orcid.org/0000-0002-9434-5880"},"institutions":[{"id":"https://openalex.org/I250383648","display_name":"Izmir K\u00e2tip \u00c7elebi University","ror":"https://ror.org/024nx4843","country_code":"TR","type":"education","lineage":["https://openalex.org/I250383648"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Aytu\u011f Onan","raw_affiliation_strings":["Department of Computer Engineering, \u0130zmir Katip \u00c7elebi University, \u00c7i\u011fli 35620, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0002-9434-5880","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, \u0130zmir Katip \u00c7elebi University, \u00c7i\u011fli 35620, T\u00fcrkiye","institution_ids":["https://openalex.org/I250383648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8393-5703","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52899981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"39","issue":"05","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":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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973999857902527,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9936000108718872,"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":0.9348364472389221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7448780536651611},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6944584846496582},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6822757124900818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6469001173973083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5960320234298706},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5783684253692627},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5348889231681824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4276273250579834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3828890919685364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1096179187297821}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9348364472389221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448780536651611},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6944584846496582},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6822757124900818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6469001173973083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5960320234298706},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5783684253692627},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5348889231681824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4276273250579834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3828890919685364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1096179187297821},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001424540181","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001424540181","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2133512280","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2506483933","https://openalex.org/W2531409750","https://openalex.org/W2625940279","https://openalex.org/W2896348597","https://openalex.org/W2907279673","https://openalex.org/W2945222541","https://openalex.org/W2953322005","https://openalex.org/W2963267809","https://openalex.org/W2964081807","https://openalex.org/W3005983418","https://openalex.org/W3006208340","https://openalex.org/W3015437081","https://openalex.org/W3019166713","https://openalex.org/W3109016160","https://openalex.org/W3110019360","https://openalex.org/W3128801341","https://openalex.org/W3184750812","https://openalex.org/W4210628514","https://openalex.org/W4312938727","https://openalex.org/W4386075661"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W4281697769"],"abstract_inverted_index":{"Generating":[0],"natural":[1,18],"language":[2,19],"descriptions":[3],"of":[4,106,137,151,174],"an":[5,39],"image,":[6],"namely":[7],"image":[8,22,66],"captioning,":[9,67],"has":[10,93,160],"received":[11],"much":[12],"attention":[13],"in":[14,32,72,96,117],"computer":[15],"vision":[16],"and":[17,47,84,145,168],"processing.":[20],"Recent":[21],"captioning":[23],"models":[24],"are":[25,49,69],"mainly":[26],"based":[27],"on":[28,164],"the":[29,73,78,90,110,129,135,138,143,149,165,172,179],"encoder-decoder":[30],"framework":[31,62],"which":[33,133],"visual":[34,79],"information":[35,80,108,140],"is":[36,63],"extracted":[37],"by":[38,51],"encoder,":[40],"e.g.":[41,54],"using":[42,55],"convolutional":[43],"neural":[44,57],"network":[45,58],"(CNN),":[46],"captions":[48],"generated":[50],"a":[52,122],"decoder,":[53,132],"recurrent":[56,125],"(RNN).":[59],"Although":[60],"this":[61,115,118],"promising":[64],"for":[65,76],"there":[68],"still":[70],"issues":[71],"RNN":[74,91,131,158],"decoder":[75,92,159],"exploiting":[77],"to":[81,103,148],"generate":[82],"grammatically":[83],"semantically":[85,152],"correct":[86],"captions.":[87,154],"More":[88],"specifically,":[89],"limited":[94],"ability":[95],"dealing":[97],"with":[98],"long-term":[99],"complex":[100],"dependencies,":[101],"leading":[102],"ineffective":[104],"use":[105],"contextual":[107],"from":[109],"encoded":[111],"data.":[112],"To":[113],"address":[114],"issue,":[116],"paper,":[119],"we":[120],"introduce":[121],"multi-layer":[123],"gated":[124],"unit":[126],"(ML-GRU)":[127],"within":[128],"conventional":[130],"enables":[134],"modulation":[136],"relevant":[139],"flow":[141],"inside":[142],"unit,":[144],"thus":[146],"leads":[147],"generation":[150],"coherent":[153],"The":[155],"proposed":[156,176],"ML-GRU-based":[157],"been":[161],"extensively":[162],"evaluated":[163],"MSCOCO":[166],"dataset,":[167],"experimental":[169],"results":[170],"demonstrate":[171],"advantage":[173],"our":[175],"approach":[177],"over":[178],"state-of-the-art":[180],"approaches":[181],"across":[182],"multiple":[183],"performance":[184],"metrics.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-11-15T00:00:00"}