{"id":"https://openalex.org/W4400908737","doi":"https://doi.org/10.1109/siu61531.2024.10600738","title":"Turkish Image Captioning with Vision Transformer Based Encoders and Text Decoders","display_name":"Turkish Image Captioning with Vision Transformer Based Encoders and Text Decoders","publication_year":2024,"publication_date":"2024-05-15","ids":{"openalex":"https://openalex.org/W4400908737","doi":"https://doi.org/10.1109/siu61531.2024.10600738"},"language":"en","primary_location":{"id":"doi:10.1109/siu61531.2024.10600738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu61531.2024.10600738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 32nd Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-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/A5061371777","display_name":"Serdar Y\u0131ld\u0131z","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Serdar Y\u0131ld\u0131z","raw_affiliation_strings":["Y&#x0131;ld&#x0131;z Teknik &#x00DC;niversitesi,Bilgisayar M&#x00FC;hendisli&#x011F;i B&#x00F6;l&#x00FC;m&#x00FC;,&#x0130;stanbul,T&#x00FC;rkiye"],"affiliations":[{"raw_affiliation_string":"Y&#x0131;ld&#x0131;z Teknik &#x00DC;niversitesi,Bilgisayar M&#x00FC;hendisli&#x011F;i B&#x00F6;l&#x00FC;m&#x00FC;,&#x0130;stanbul,T&#x00FC;rkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082442670","display_name":"Abbas Memi\u015f","orcid":"https://orcid.org/0000-0003-2645-8071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abbas Memi\u015f","raw_affiliation_strings":["&#x0130;stanbul &#x00DC;niversitesi,Bilgisayar M&#x00FC;hendisli&#x011F;i B&#x00F6;l&#x00FC;m&#x00FC;,&#x0130;stanbul,T&#x00FC;rkiye"],"affiliations":[{"raw_affiliation_string":"&#x0130;stanbul &#x00DC;niversitesi,Bilgisayar M&#x00FC;hendisli&#x011F;i B&#x00F6;l&#x00FC;m&#x00FC;,&#x0130;stanbul,T&#x00FC;rkiye","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036755640","display_name":"Song\u00fcl Albayrak","orcid":"https://orcid.org/0000-0002-1786-6869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song\u00fcl Varl\u0131","raw_affiliation_strings":["Y&#x0131;ld&#x0131;z Teknik &#x00DC;niversitesi,Bilgisayar M&#x00FC;hendisli&#x011F;i B&#x00F6;l&#x00FC;m&#x00FC;,&#x0130;stanbul,T&#x00FC;rkiye"],"affiliations":[{"raw_affiliation_string":"Y&#x0131;ld&#x0131;z Teknik &#x00DC;niversitesi,Bilgisayar M&#x00FC;hendisli&#x011F;i B&#x00F6;l&#x00FC;m&#x00FC;,&#x0130;stanbul,T&#x00FC;rkiye","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061371777"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2419,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49787639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9925000071525574,"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":0.9922999739646912,"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":0.9182083606719971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7062901258468628},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6327334642410278},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.624610185623169},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.6072774529457092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5075570344924927},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47059905529022217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45958179235458374},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4310765862464905},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31952643394470215},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19262832403182983},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1492939293384552},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13091903924942017},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08556133508682251},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07856360077857971}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9182083606719971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062901258468628},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6327334642410278},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.624610185623169},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.6072774529457092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5075570344924927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47059905529022217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45958179235458374},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4310765862464905},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31952643394470215},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19262832403182983},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1492939293384552},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13091903924942017},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08556133508682251},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07856360077857971},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu61531.2024.10600738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu61531.2024.10600738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 32nd Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","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":{"Image":[0],"captioning":[1,37,98],"is":[2,24],"defined":[3],"as":[4],"the":[5,19,22,48,61,64,78,92,95,116],"process":[6],"of":[7,9,21,63,94,109,128,133,138,143,148,153,159],"describing":[8],"images":[10,23,51],"by":[11,40,69],"computer":[12],"systems":[13],"automatically.":[14],"Thus,":[15],"visual":[16],"information":[17],"regarding":[18],"content":[20],"expressed":[25],"in":[26,101],"textual":[27],"form.":[28],"This":[29],"paper":[30],"presents":[31],"a":[32,56,73,86,105,125,130,135,140,145,150,156],"deep":[33],"learning-based":[34],"Turkish":[35,96,110],"image":[36,66,81,97,111],"study":[38],"implemented":[39],"using":[41],"vision":[42,57],"transformers":[43],"and":[44,124,155],"text":[45,87],"decoders.":[46],"In":[47,77,115],"proposed":[49],"study,":[50],"are":[52,67,83],"initially":[53],"encoded":[54,65],"with":[55],"transformer-based":[58],"module.":[59,76],"Afterwards,":[60],"features":[62],"normalized":[68],"passing":[70],"them":[71],"through":[72],"feature":[74],"projection":[75],"final":[79],"stage,":[80],"captions":[82],"generated":[84],"via":[85],"decoder":[88],"block.":[89],"To":[90],"test":[91],"performance":[93],"system":[99],"presented":[100],"this":[102],"paper,":[103],"TasvirEt,":[104],"benchmark":[106],"dataset":[107],"consisting":[108],"captions,":[112],"was":[113],"used.":[114],"tests":[117],"performed,":[118],"quite":[119],"successful":[120],"results":[121],"were":[122,161],"observed":[123],"BLEU-1":[126],"value":[127,132,137,142,147,152,158],"0.3406,":[129],"BLEU-2":[131],"0.2110,":[134],"BLEU-3":[136],"0.1253,":[139],"BLEU-4":[141],"0.0690,":[144],"METEOR":[146],"0.1610,":[149],"ROUGE-L":[151],"0.3145":[154],"CIDEr":[157],"0.3879":[160],"measured.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}
