{"id":"https://openalex.org/W4214758171","doi":"https://doi.org/10.1007/s00530-022-00902-0","title":"Image and audio caps: automated captioning of background sounds and images using deep learning","display_name":"Image and audio caps: automated captioning of background sounds and images using deep learning","publication_year":2022,"publication_date":"2022-02-26","ids":{"openalex":"https://openalex.org/W4214758171","doi":"https://doi.org/10.1007/s00530-022-00902-0"},"language":"en","primary_location":{"id":"doi:10.1007/s00530-022-00902-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00530-022-00902-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00530-022-00902-0.pdf","source":{"id":"https://openalex.org/S112262039","display_name":"Multimedia Systems","issn_l":"0942-4962","issn":["0942-4962","1432-1882"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00530-022-00902-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110750223","display_name":"M. Poongodi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"M. Poongodi","raw_affiliation_strings":["Department of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001299811","display_name":"Mounir Hamdi","orcid":"https://orcid.org/0000-0002-9766-0085"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mounir Hamdi","raw_affiliation_strings":["Department of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100371075","display_name":"Huihui Wang","orcid":"https://orcid.org/0000-0002-4098-5313"},"institutions":[{"id":"https://openalex.org/I117309725","display_name":"St. Bonaventure University","ror":"https://ror.org/026bv4494","country_code":"US","type":"education","lineage":["https://openalex.org/I117309725"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huihui Wang","raw_affiliation_strings":["CyberSecurity Program, St. Bonaventure University, St. Bonaventure, NY, 14778, USA"],"affiliations":[{"raw_affiliation_string":"CyberSecurity Program, St. Bonaventure University, St. Bonaventure, NY, 14778, USA","institution_ids":["https://openalex.org/I117309725"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110750223"],"corresponding_institution_ids":["https://openalex.org/I4210144839"],"apc_list":null,"apc_paid":null,"fwci":11.1647,"has_fulltext":true,"cited_by_count":76,"citation_normalized_percentile":{"value":0.99263783,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"29","issue":"5","first_page":"2951","last_page":"2959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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":0.9980000257492065,"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":0.8721245527267456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8509184122085571},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6441330909729004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6304376125335693},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5961776375770569},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.5417377352714539},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4463995099067688},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4296780228614807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38201919198036194},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3286750316619873}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8721245527267456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8509184122085571},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6441330909729004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6304376125335693},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5961776375770569},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.5417377352714539},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4463995099067688},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4296780228614807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38201919198036194},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3286750316619873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s00530-022-00902-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00530-022-00902-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00530-022-00902-0.pdf","source":{"id":"https://openalex.org/S112262039","display_name":"Multimedia Systems","issn_l":"0942-4962","issn":["0942-4962","1432-1882"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Systems","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-163425","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-163425","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:figshare.com:article/21597084","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Image_and_audio_caps_automated_captioning_of_background_sounds_and_images_using_deep_learning/21597084","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.57945/manara.21597084.v1","is_oa":true,"landing_page_url":"https://doi.org/10.57945/manara.21597084.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407052475","display_name":"Qatar National Library","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1007/s00530-022-00902-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00530-022-00902-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00530-022-00902-0.pdf","source":{"id":"https://openalex.org/S112262039","display_name":"Multimedia Systems","issn_l":"0942-4962","issn":["0942-4962","1432-1882"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320319188","display_name":"Hamad Bin Khalifa University","ror":"https://ror.org/03eyq4y97"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4214758171.pdf","grobid_xml":"https://content.openalex.org/works/W4214758171.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W747247434","https://openalex.org/W937378240","https://openalex.org/W1485902897","https://openalex.org/W1504678909","https://openalex.org/W1921503324","https://openalex.org/W1963831556","https://openalex.org/W1986044926","https://openalex.org/W2019240280","https://openalex.org/W2021786386","https://openalex.org/W2063440615","https://openalex.org/W2080585174","https://openalex.org/W2091332674","https://openalex.org/W2103383070","https://openalex.org/W2110891953","https://openalex.org/W2111951743","https://openalex.org/W2165232329","https://openalex.org/W2165640605","https://openalex.org/W2165986142","https://openalex.org/W2168874115","https://openalex.org/W2170996950","https://openalex.org/W2293066912","https://openalex.org/W2303707495","https://openalex.org/W2603831296","https://openalex.org/W2798636681","https://openalex.org/W2805143365","https://openalex.org/W2926061468","https://openalex.org/W2942105358","https://openalex.org/W2996421194","https://openalex.org/W3033901474","https://openalex.org/W3036931357","https://openalex.org/W3039680028","https://openalex.org/W3048949829","https://openalex.org/W3080477479","https://openalex.org/W3080499510","https://openalex.org/W3085604187","https://openalex.org/W3093836107","https://openalex.org/W3103998378","https://openalex.org/W3119610945","https://openalex.org/W3119789064","https://openalex.org/W3130268572","https://openalex.org/W3135672363","https://openalex.org/W3135939397","https://openalex.org/W3144299160","https://openalex.org/W3161271154","https://openalex.org/W3166199893","https://openalex.org/W3178811037","https://openalex.org/W3180962798","https://openalex.org/W3182324909","https://openalex.org/W3184868206","https://openalex.org/W3193034409","https://openalex.org/W3194356584","https://openalex.org/W3209438245","https://openalex.org/W3217401178","https://openalex.org/W4233752196","https://openalex.org/W4255815195"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","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/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Abstract":[0],"Image":[1],"recognition":[2],"based":[3,77],"on":[4,13,78],"computers":[5],"is":[6,18,116,122],"something":[7],"human":[8],"beings":[9],"have":[10,64,112],"been":[11,65,113],"working":[12],"for":[14],"many":[15],"years.":[16],"It":[17,115],"one":[19],"of":[20,28,90,103,110,127],"the":[21,26,60,79,83,124],"most":[22],"difficult":[23],"tasks":[24],"in":[25],"field":[27],"computer":[29,96],"science,":[30],"and":[31,54,68,82,94,105],"improvements":[32],"to":[33,48,59,70,130],"this":[34,42,72,121,132],"system":[35],"are":[36,75,85],"made":[37],"when":[38],"we":[39,44],"speak.":[40],"In":[41],"paper,":[43],"propose":[45,50],"a":[46,56,88,106],"methodology":[47],"automatically":[49],"an":[51],"appropriate":[52],"title":[53],"add":[55],"specific":[57],"sound":[58],"image.":[61],"Two":[62],"models":[63],"extensively":[66],"trained":[67],"combined":[69],"achieve":[71],"effect.":[73],"Sounds":[74],"recommended":[76],"image":[80],"scene":[81],"headings":[84],"generated":[86],"using":[87],"combination":[89],"natural":[91],"language":[92],"processing":[93],"state-of-the-art":[95],"vision":[97],"models.":[98],"A":[99],"Top":[100,107],"5":[101],"accuracy":[102,109],"67%":[104],"1":[108],"53%":[111],"achieved.":[114],"also":[117,123],"worth":[118],"mentioning":[119],"that":[120],"first":[125],"model":[126],"its":[128],"kind":[129],"make":[131],"forecast.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":29}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}