{"id":"https://openalex.org/W7155570254","doi":"https://doi.org/10.1145/3799830.3799856","title":"V-SAT: Video Subtitle Annotation Tool","display_name":"V-SAT: Video Subtitle Annotation Tool","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7155570254","doi":"https://doi.org/10.1145/3799830.3799856"},"language":null,"primary_location":{"id":"doi:10.1145/3799830.3799856","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799856","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799830.3799856","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134481675","display_name":"Arpita Kundu","orcid":"https://orcid.org/0009-0004-8593-2110"},"institutions":[{"id":"https://openalex.org/I1336379959","display_name":"Mahindra Group (India)","ror":"https://ror.org/05mxsz225","country_code":"IN","type":"company","lineage":["https://openalex.org/I1336379959"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arpita Kundu","raw_affiliation_strings":["LTIMindTree, Kolkata, India"],"raw_orcid":"https://orcid.org/0009-0004-8593-2110","affiliations":[{"raw_affiliation_string":"LTIMindTree, Kolkata, India","institution_ids":["https://openalex.org/I1336379959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042034956","display_name":"Joyita Chakraborty","orcid":"https://orcid.org/0009-0008-8294-7957"},"institutions":[{"id":"https://openalex.org/I1336379959","display_name":"Mahindra Group (India)","ror":"https://ror.org/05mxsz225","country_code":"IN","type":"company","lineage":["https://openalex.org/I1336379959"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Joyita Chakraborty","raw_affiliation_strings":["LTIMindtree, Kolkata, India"],"raw_orcid":"https://orcid.org/0009-0008-8294-7957","affiliations":[{"raw_affiliation_string":"LTIMindtree, Kolkata, India","institution_ids":["https://openalex.org/I1336379959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016584618","display_name":"Anindita Desarkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1336379959","display_name":"Mahindra Group (India)","ror":"https://ror.org/05mxsz225","country_code":"IN","type":"company","lineage":["https://openalex.org/I1336379959"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anindita Desarkar","raw_affiliation_strings":["LTIMindTree, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0001-5604-5900","affiliations":[{"raw_affiliation_string":"LTIMindTree, Kolkata, India","institution_ids":["https://openalex.org/I1336379959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134546059","display_name":"Aritra Sen","orcid":"https://orcid.org/0009-0008-0792-1968"},"institutions":[{"id":"https://openalex.org/I1336379959","display_name":"Mahindra Group (India)","ror":"https://ror.org/05mxsz225","country_code":"IN","type":"company","lineage":["https://openalex.org/I1336379959"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aritra Sen","raw_affiliation_strings":["LTIMindTree, Kolkata, India"],"raw_orcid":"https://orcid.org/0009-0008-0792-1968","affiliations":[{"raw_affiliation_string":"LTIMindTree, Kolkata, India","institution_ids":["https://openalex.org/I1336379959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112376650","display_name":"SJ Patil","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104682","display_name":"Mahindra and Mahindra Limited (India)","ror":"https://ror.org/01c5dd102","country_code":"IN","type":"company","lineage":["https://openalex.org/I1336379959","https://openalex.org/I4210104682"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srushti Anil Patil","raw_affiliation_strings":["LTIMindTree, Mumbai, India"],"raw_orcid":"https://orcid.org/0009-0005-1103-1659","affiliations":[{"raw_affiliation_string":"LTIMindTree, Mumbai, India","institution_ids":["https://openalex.org/I4210104682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033850130","display_name":"Vishwanathan Raman","orcid":null},"institutions":[{"id":"https://openalex.org/I43663321","display_name":"Hindustan Institute of Technology and Science","ror":"https://ror.org/037tgdn13","country_code":"IN","type":"education","lineage":["https://openalex.org/I43663321"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vishwanathan Raman","raw_affiliation_strings":["LTIMindTree, Chennai, India"],"raw_orcid":"https://orcid.org/0009-0003-7520-5457","affiliations":[{"raw_affiliation_string":"LTIMindTree, Chennai, India","institution_ids":["https://openalex.org/I43663321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5134481675"],"corresponding_institution_ids":["https://openalex.org/I1336379959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94062851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"426","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.824400007724762,"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":0.824400007724762,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.04309999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.027400000020861626,"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/subtitle","display_name":"Subtitle","score":0.9656000137329102},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6998999714851379},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5636000037193298},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.41359999775886536},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.39879998564720154},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.376800000667572}],"concepts":[{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.9656000137329102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667999863624573},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6998999714851379},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5385000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019999742507935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4375},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799830.3799856","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799856","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3799830.3799856","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799856","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2135708429","https://openalex.org/W2959980708","https://openalex.org/W3018962734","https://openalex.org/W3034625919","https://openalex.org/W3097777922","https://openalex.org/W3157703700","https://openalex.org/W3207158787","https://openalex.org/W4285105502","https://openalex.org/W4307137011","https://openalex.org/W4317794530","https://openalex.org/W4389891243","https://openalex.org/W4400316688","https://openalex.org/W4402683164","https://openalex.org/W4411447826"],"related_works":[],"abstract_inverted_index":{"The":[0],"surge":[1],"of":[2,89,138],"audiovisual":[3],"content":[4],"on":[5],"streaming":[6],"platforms":[7],"and":[8,17,45,65,84,104,116,136],"social":[9],"media":[10],"has":[11],"heightened":[12],"the":[13,46,122,150],"demand":[14],"for":[15,140,154],"accurate":[16],"accessible":[18],"subtitles.":[19],"However,":[20],"existing":[21],"subtitle":[22,90,156],"generation":[23],"methods\u2014primarily":[24],"speech-based":[25],"transcription":[26],"or":[27,37],"OCR-based":[28],"extraction\u2014suffer":[29],"from":[30,113,126],"several":[31],"shortcomings,":[32],"including":[33],"poor":[34],"synchronization,":[35],"incorrect":[36],"harmful":[38],"text,":[39],"inconsistent":[40],"formatting,":[41],"inappropriate":[42],"reading":[43],"speeds,":[44],"inability":[47],"to":[48,50,128],"adapt":[49],"dynamic":[51],"audio-visual":[52],"contexts.":[53],"Current":[54],"approaches":[55],"often":[56],"address":[57],"isolated":[58],"issues,":[59],"leaving":[60],"post-editing":[61],"as":[62],"a":[63,78,86],"labor-intensive":[64],"time-consuming":[66],"process.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"introduce":[72],"V-SAT":[73,109],"(Video":[74],"Subtitle":[75,118],"Annotation":[76],"Tool),":[77],"unified":[79],"framework":[80],"that":[81],"automatically":[82],"detects":[83],"corrects":[85],"wide":[87],"range":[88],"quality":[91,119],"issues.":[92,143],"By":[93],"combining":[94],"Large":[95],"Language":[96],"Models":[97,100],"(LLMs),":[98],"Vision-Language":[99],"(VLMs),":[101],"Image":[102],"Processing,":[103],"Automatic":[105],"Speech":[106],"Recognition":[107],"(ASR),":[108],"leverages":[110],"contextual":[111],"cues":[112],"both":[114],"audio":[115],"video.":[117],"improved,":[120],"with":[121],"SUBER":[123],"score":[124],"reduced":[125],"9.6":[127],"3.54":[129],"after":[130],"resolving":[131],"all":[132],"language":[133],"mode":[134,142],"issues":[135],"F1-scores":[137],"~0.80":[139],"image":[141],"Human-in-the-loop":[144],"validation":[145],"ensures":[146],"high-quality":[147],"results,":[148],"providing":[149],"first":[151],"comprehensive":[152],"solution":[153],"robust":[155],"annotation.":[157]},"counts_by_year":[],"updated_date":"2026-04-25T06:06:54.107920","created_date":"2026-04-25T00:00:00"}
