{"id":"https://openalex.org/W4390537607","doi":"https://doi.org/10.1007/s10772-023-10081-6","title":"Scene text visual question answering by using YOLO and STN","display_name":"Scene text visual question answering by using YOLO and STN","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390537607","doi":"https://doi.org/10.1007/s10772-023-10081-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-023-10081-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10772-023-10081-6","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","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/A5093644085","display_name":"Kimiya Nourali","orcid":null},"institutions":[{"id":"https://openalex.org/I928334797","display_name":"Semnan University","ror":"https://ror.org/029gksw03","country_code":"IR","type":"education","lineage":["https://openalex.org/I928334797"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Kimiya Nourali","raw_affiliation_strings":["Computer Science Department, Semnan University, Semnan, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Semnan University, Semnan, Iran","institution_ids":["https://openalex.org/I928334797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048410534","display_name":"Elham Dolkhani","orcid":"https://orcid.org/0009-0008-1098-9648"},"institutions":[{"id":"https://openalex.org/I86958956","display_name":"Ferdowsi University of Mashhad","ror":"https://ror.org/00g6ka752","country_code":"IR","type":"education","lineage":["https://openalex.org/I86958956"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Elham Dolkhani","raw_affiliation_strings":["Computer Engineering Department, Ferdowsi University of Mashhad, Mashhad, Iran"],"raw_orcid":"https://orcid.org/0009-0008-1098-9648","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Ferdowsi University of Mashhad, Mashhad, Iran","institution_ids":["https://openalex.org/I86958956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048410534"],"corresponding_institution_ids":["https://openalex.org/I86958956"],"apc_list":{"value":2780,"currency":"USD","value_usd":2780},"apc_paid":null,"fwci":0.9734,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71921832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"1","first_page":"69","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9970999956130981,"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":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.8758394718170166},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8173409700393677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7469068169593811},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5961353778839111},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5322012305259705},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5285369753837585},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.5186302065849304},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4840320944786072},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.434490829706192},{"id":"https://openalex.org/keywords/perspective-distortion","display_name":"Perspective distortion","score":0.42195630073547363},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4214520752429962},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4143877625465393},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3528461456298828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8758394718170166},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8173409700393677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7469068169593811},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5961353778839111},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5322012305259705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5285369753837585},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5186302065849304},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4840320944786072},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.434490829706192},{"id":"https://openalex.org/C2779989122","wikidata":"https://www.wikidata.org/wiki/Q15889487","display_name":"Perspective distortion","level":3,"score":0.42195630073547363},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4214520752429962},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4143877625465393},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3528461456298828},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10772-023-10081-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10772-023-10081-6","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W1933349210","https://openalex.org/W1981283549","https://openalex.org/W1988461287","https://openalex.org/W2052208218","https://openalex.org/W2125102738","https://openalex.org/W2294053032","https://openalex.org/W2493916176","https://openalex.org/W2532759528","https://openalex.org/W2555182955","https://openalex.org/W2559655401","https://openalex.org/W2802292638","https://openalex.org/W2809273748","https://openalex.org/W2810983211","https://openalex.org/W2885195348","https://openalex.org/W2942148945","https://openalex.org/W2963260436","https://openalex.org/W2963517393","https://openalex.org/W2963712589","https://openalex.org/W2965066169","https://openalex.org/W2979382951","https://openalex.org/W2982220924","https://openalex.org/W2988326850","https://openalex.org/W2990714382","https://openalex.org/W3015736093","https://openalex.org/W3034336960","https://openalex.org/W3046590903","https://openalex.org/W3086275027","https://openalex.org/W3109301572","https://openalex.org/W3186371728","https://openalex.org/W3205961173","https://openalex.org/W3212386989","https://openalex.org/W3212817138","https://openalex.org/W3215633354","https://openalex.org/W4210344316","https://openalex.org/W4242367138","https://openalex.org/W4388007692","https://openalex.org/W4388189392","https://openalex.org/W4388191243","https://openalex.org/W4390873674","https://openalex.org/W6628927728","https://openalex.org/W6639461050","https://openalex.org/W6682137061","https://openalex.org/W6750227808","https://openalex.org/W6776917783","https://openalex.org/W6797083773"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W1964182740","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W3127964174","https://openalex.org/W4200629926"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
