{"id":"https://openalex.org/W4399911603","doi":"https://doi.org/10.1007/s11042-025-20908-w","title":"Live video captioning","display_name":"Live video captioning","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4399911603","doi":"https://doi.org/10.1007/s11042-025-20908-w"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-025-20908-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-025-20908-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-025-20908-w.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"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 Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-025-20908-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099380769","display_name":"Eduardo Blanco-Fern\u00e1ndez","orcid":null},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduardo Blanco-Fern\u00e1ndez","raw_affiliation_strings":["Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, 28805, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, 28805, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082689781","display_name":"Carlos Guti\u00e9rrez-\u00c1lvarez","orcid":"https://orcid.org/0000-0002-5624-0076"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Guti\u00e9rrez-\u00c1lvarez","raw_affiliation_strings":["Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, 28805, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, 28805, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043825648","display_name":"Nadia Nasri","orcid":"https://orcid.org/0000-0002-9005-6184"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nadia Nasri","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Alicante, San Vicente del Raspeig, 03690, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Alicante, San Vicente del Raspeig, 03690, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087857973","display_name":"Saturnino Maldonado-Basc\u00f3n","orcid":"https://orcid.org/0000-0001-6472-5359"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Saturnino Maldonado-Basc\u00f3n","raw_affiliation_strings":["Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, 28805, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, 28805, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042331786","display_name":"Roberto J. L\u00f3pez-Sastre","orcid":"https://orcid.org/0000-0002-2477-0152"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Roberto J. L\u00f3pez-Sastre","raw_affiliation_strings":["Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, 28805, Spain"],"raw_orcid":"https://orcid.org/0000-0002-2477-0152","affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, 28805, Spain","institution_ids":["https://openalex.org/I189268942"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042331786"],"corresponding_institution_ids":["https://openalex.org/I189268942"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":1.084,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72417707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"84","issue":"35","first_page":"44863","last_page":"44895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9908999800682068,"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":0.9732999801635742,"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":0.9573015570640564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.506311297416687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22031542658805847},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1113831102848053}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9573015570640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.506311297416687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22031542658805847},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1113831102848053}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11042-025-20908-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-025-20908-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-025-20908-w.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"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 Tools and Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2406.14206","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.14206","pdf_url":"https://arxiv.org/pdf/2406.14206","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:ebuah.uah.es:10017/65404","is_oa":true,"landing_page_url":"http://hdl.handle.net/10017/65404","pdf_url":"https://ebuah.uah.es/dspace/bitstream/10017/65404/4/Live_Blanco_MultimedToolsAppl_2025.pdf","source":{"id":"https://openalex.org/S7407055200","display_name":"e_Buah","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"doi:10.48550/arxiv.2406.14206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.14206","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s11042-025-20908-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-025-20908-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-025-20908-w.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"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 Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320323755","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399911603.pdf","grobid_xml":"https://content.openalex.org/works/W4399911603.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W4394615984","https://openalex.org/W4384304120","https://openalex.org/W4396878071","https://openalex.org/W4391647933","https://openalex.org/W4312321660","https://openalex.org/W2425121537","https://openalex.org/W2989322838","https://openalex.org/W4390742808","https://openalex.org/W4386066385","https://openalex.org/W4214663214","https://openalex.org/W2969844053","https://openalex.org/W3047922786","https://openalex.org/W2963916161","https://openalex.org/W2963351113","https://openalex.org/W2962799512","https://openalex.org/W2891303919","https://openalex.org/W3034815696","https://openalex.org/W2963753226","https://openalex.org/W2342437993","https://openalex.org/W2963720581","https://openalex.org/W2800438594","https://openalex.org/W2341313195","https://openalex.org/W2997046622","https://openalex.org/W3194048502","https://openalex.org/W4220664910","https://openalex.org/W3197026988","https://openalex.org/W2073419240","https://openalex.org/W225975350","https://openalex.org/W66452226","https://openalex.org/W2997296614","https://openalex.org/W3208474254","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2133459682","https://openalex.org/W2101105183","https://openalex.org/W1927052826","https://openalex.org/W2883910824","https://openalex.org/W2968104955","https://openalex.org/W4401478775"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403"],"abstract_inverted_index":{"Abstract":[0],"Dense":[1],"video":[2,10,22,47,123],"captioning":[3,121],"involves":[4],"detecting":[5],"and":[6,65,83,160],"describing":[7],"events":[8,64],"within":[9],"sequences.":[11],"Traditional":[12],"methods":[13],"operate":[14],"in":[15,29,49,140],"an":[16,50,161],"offline":[17,147],"setting,":[18],"assuming":[19],"the":[20,63,66,73,78,102,128,133,141,155,165],"entire":[21],"is":[23],"available":[24],"for":[25,46,68,90],"analysis.":[26],"In":[27],"contrast,":[28],"this":[30,91],"work":[31],"we":[32,107,153],"introduce":[33],"a":[34,69,109],"groundbreaking":[35],"paradigm:":[36],"Live":[37],"Video":[38],"Captioning":[39],"(LVC),":[40],"where":[41],"captions":[42],"must":[43],"be":[44],"generated":[45],"streams":[48],"online":[51,92],"manner.":[52],"This":[53],"shift":[54],"brings":[55],"unique":[56],"challenges,":[57],"including":[58],"processing":[59],"partial":[60],"observations":[61],"of":[62,72,81,105,157],"need":[67],"temporal":[70,117],"anticipation":[71],"actions.":[74],"We":[75],"formally":[76],"define":[77],"novel":[79,103],"problem":[80],"LVC":[82,142],"propose":[84],"innovative":[85],"evaluation":[86,162],"metrics":[87,167],"specifically":[88],"designed":[89],"scenario,":[93],"demonstrating":[94],"their":[95],"advantages":[96],"over":[97,122],"traditional":[98],"metrics.":[99],"To":[100,149],"address":[101],"complexities":[104],"LVC,":[106],"present":[108],"new":[110,166],"model":[111,159],"that":[112],"combines":[113],"deformable":[114],"transformers":[115],"with":[116,164],"filtering,":[118],"enabling":[119],"effective":[120],"streams.":[124],"Extensive":[125],"experiments":[126],"on":[127],"ActivityNet":[129],"Captions":[130],"dataset":[131],"validate":[132],"proposed":[134],"approach,":[135],"showcasing":[136],"its":[137],"superior":[138],"performance":[139],"setting":[143],"compared":[144],"to":[145],"state-of-the-art":[146],"methods.":[148],"foster":[150],"further":[151],"research,":[152],"provide":[154],"results":[156],"our":[158],"toolkit":[163],"integrated":[168],"at:":[169],"https://github.com/gramuah/lvc":[170],".":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2024-06-22T00:00:00"}
