{"id":"https://openalex.org/W4399485604","doi":"https://doi.org/10.1109/i2ct61223.2024.10544216","title":"Audio Description of Videos Using Machine Learning","display_name":"Audio Description of Videos Using Machine Learning","publication_year":2024,"publication_date":"2024-04-05","ids":{"openalex":"https://openalex.org/W4399485604","doi":"https://doi.org/10.1109/i2ct61223.2024.10544216"},"language":"en","primary_location":{"id":"doi:10.1109/i2ct61223.2024.10544216","doi":"https://doi.org/10.1109/i2ct61223.2024.10544216","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/i2ct61223.2024.10544216","pdf_url":null,"source":{"id":"https://openalex.org/S4363607804","display_name":"IEEE International Conference for Convergence in Technology (I2CT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 9th International Conference for Convergence in Technology (I2CT)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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":null,"display_name":"Robin Roy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Robin Roy","raw_affiliation_strings":["PES University,Department of Computer Science,Bengaluru,India","Department of Computer Science, PES University, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of Computer Science,Bengaluru,India","institution_ids":["https://openalex.org/I196608512"]},{"raw_affiliation_string":"Department of Computer Science, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099073061","display_name":"Shreya Manepalli","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shreya Manepalli","raw_affiliation_strings":["PES University,Department of Computer Science,Bengaluru,India","Department of Computer Science, PES University, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of Computer Science,Bengaluru,India","institution_ids":["https://openalex.org/I196608512"]},{"raw_affiliation_string":"Department of Computer Science, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104323940","display_name":"Shreeya Rajan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shreeya Rajan","raw_affiliation_strings":["PES University,Department of Computer Science,Bengaluru,India","Department of Computer Science, PES University, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of Computer Science,Bengaluru,India","institution_ids":["https://openalex.org/I196608512"]},{"raw_affiliation_string":"Department of Computer Science, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101375744","display_name":"Sharanya Mishra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sharanya Mishra","raw_affiliation_strings":["PES University,Department of Computer Science,Bengaluru,India","Department of Computer Science, PES University, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of Computer Science,Bengaluru,India","institution_ids":["https://openalex.org/I196608512"]},{"raw_affiliation_string":"Department of Computer Science, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076680657","display_name":"Gambhire Swati Sampatrao","orcid":"https://orcid.org/0000-0001-7054-161X","observed_orcids":["https://orcid.org/0000-0001-7054-161X"]},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gambhire Swati Sampatrao","raw_affiliation_strings":["PES University,Department of Computer Science,Bengaluru,India","Department of Computer Science, PES University, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of Computer Science,Bengaluru,India","institution_ids":["https://openalex.org/I196608512"]},{"raw_affiliation_string":"Department of Computer Science, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196608512"],"apc_list":null,"apc_paid":null,"fwci":3.4385,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90605051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03539999946951866,"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":0.019300000742077827,"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/audio-description","display_name":"audio description","score":0.9789999723434448},{"id":"https://openalex.org/keywords/video-accessibility","display_name":"video accessibility","score":0.8859999775886536},{"id":"https://openalex.org/keywords/visual-impairment","display_name":"visual impairment","score":0.9760000109672546},{"id":"https://openalex.org/keywords/speech-generation","display_name":"speech generation","score":0.42800000309944153},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.800000011920929},{"id":"https://openalex.org/keywords/assistive-technology","display_name":"assistive technology","score":0.6200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860414981842041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5675684809684753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36936306953430176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35399001836776733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3406134843826294}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/i2ct61223.2024.10544216","doi":"https://doi.org/10.1109/i2ct61223.2024.10544216","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/i2ct61223.2024.10544216","pdf_url":null,"source":{"id":"https://openalex.org/S4363607804","display_name":"IEEE International Conference for Convergence in Technology (I2CT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 9th International Conference for Convergence in Technology (I2CT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7578999996185303,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2513874664","https://openalex.org/W2803525166","https://openalex.org/W2889924266","https://openalex.org/W2941092099","https://openalex.org/W2972589507","https://openalex.org/W2986670728","https://openalex.org/W3092189939","https://openalex.org/W3095909497","https://openalex.org/W3134971540","https://openalex.org/W3160237369","https://openalex.org/W3205782068","https://openalex.org/W4245692952","https://openalex.org/W4361298885","https://openalex.org/W4382562154"],"related_works":["https://openalex.org/W7124986753","https://openalex.org/W4410296547","https://openalex.org/W4390485407","https://openalex.org/W4407352311","https://openalex.org/W4399897519","https://openalex.org/W3160237369","https://openalex.org/W3032743533","https://openalex.org/W4413980540","https://openalex.org/W4413068139","https://openalex.org/W2079060176"],"abstract_inverted_index":{"This":[0],"research":[1,132],"paper":[2],"proposes":[3],"an":[4],"innovative":[5],"approach":[6],"leveraging":[7],"machine":[8],"learning":[9],"techniques":[10],"to":[11,41,66,134],"enhance":[12],"the":[13,33,52,59,76,82,124,128,135],"accessibility":[14,129],"of":[15,35,51,107,137],"visual":[16,26,43,109,117],"content,":[17],"such":[18],"as":[19,78],"movies":[20],"and":[21,55,73,94,122,144],"videos,":[22],"for":[23,103,146],"individuals":[24],"with":[25,116],"impairments.":[27],"Our":[28,61],"strategy":[29],"is":[30,65,141],"based":[31],"on":[32,88],"usage":[34],"Audio":[36],"Description,":[37],"which":[38],"enables":[39],"viewers":[40],"understand":[42,121],"context":[44],"by":[45],"offering":[46],"a":[47],"thorough":[48],"audio":[49,57,101],"description":[50],"scenes,":[53],"activities,":[54],"related":[56],"in":[58,81,99],"video.":[60,83],"model\u2019s":[62],"main":[63],"goal":[64],"produce":[67],"voice":[68],"output":[69],"captions":[70],"that":[71,114,140],"succinctly":[72],"vividly":[74],"explain":[75],"events":[77],"they":[79],"happen":[80],"We":[84],"tried":[85],"this":[86],"method":[87,112],"several":[89,92],"videos":[90],"across":[91],"domains,":[93],"it":[95],"achieved":[96],"great":[97],"accuracy":[98],"providing":[100],"descriptions":[102],"these":[104],"videos.":[105],"Regardless":[106],"their":[108],"ability,":[110],"our":[111,131],"guarantees":[113],"people":[115],"impairments":[118],"may":[119],"completely":[120],"appreciate":[123],"information.":[125],"By":[126],"bridging":[127],"gap,":[130],"contributes":[133],"creation":[136],"multimedia":[138],"content":[139],"more":[142],"inclusive":[143],"valuable":[145],"all":[147],"viewers.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-06-11T00:00:00"}
