{"id":"https://openalex.org/W4388118920","doi":"https://doi.org/10.23919/eusipco58844.2023.10290046","title":"Knowledge Distillation for Efficient Audio-Visual Video Captioning","display_name":"Knowledge Distillation for Efficient Audio-Visual Video Captioning","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388118920","doi":"https://doi.org/10.23919/eusipco58844.2023.10290046"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10290046","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10290046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-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/A5087114343","display_name":"\u00d6zkan \u00c7AYLI","orcid":"https://orcid.org/0000-0002-3389-3867"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00d6zkan \u00c7ayli","raw_affiliation_strings":["Electrical and Electronics Engineering, İzmir Katip Çelebi University,Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Electronics Engineering, İzmir Katip Çelebi University,Türkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063512115","display_name":"Volkan K\u0131l\u0131\u00e7","orcid":"https://orcid.org/0000-0002-3164-1981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Volkan Kili\u00e7","raw_affiliation_strings":["Electrical and Electronics Engineering, İzmir Katip Çelebi University,Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Electronics Engineering, İzmir Katip Çelebi University,Türkiye","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4491,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64667944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"745","last_page":"749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980000257492065,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9347357749938965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8491266965866089},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5988343954086304},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5760198831558228},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5739421844482422},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.552083432674408},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4900714159011841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4849443733692169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4746183454990387},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46282416582107544},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32558107376098633},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.28803470730781555},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22385457158088684}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9347357749938965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8491266965866089},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5988343954086304},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5760198831558228},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5739421844482422},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.552083432674408},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4900714159011841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4849443733692169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4746183454990387},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46282416582107544},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32558107376098633},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28803470730781555},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22385457158088684},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10290046","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10290046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2425121537","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2890123008","https://openalex.org/W2900560726","https://openalex.org/W2918626955","https://openalex.org/W2952825952","https://openalex.org/W2963864497","https://openalex.org/W3038667391","https://openalex.org/W3041439482","https://openalex.org/W3094550259","https://openalex.org/W3096297644","https://openalex.org/W3189036352","https://openalex.org/W3205708381","https://openalex.org/W3210574093","https://openalex.org/W4200269433","https://openalex.org/W4206759476","https://openalex.org/W4224030391","https://openalex.org/W4280550634","https://openalex.org/W4280567182","https://openalex.org/W4289785182","https://openalex.org/W4296070204","https://openalex.org/W4297775537","https://openalex.org/W4305008490","https://openalex.org/W4312898271","https://openalex.org/W4312905520","https://openalex.org/W4372266890","https://openalex.org/W4385822505","https://openalex.org/W6638667902","https://openalex.org/W6682631176","https://openalex.org/W6682824805","https://openalex.org/W6725318829","https://openalex.org/W6737664043","https://openalex.org/W6754684794","https://openalex.org/W6755942961","https://openalex.org/W6759697587","https://openalex.org/W6799494382","https://openalex.org/W6806864707","https://openalex.org/W6840679096","https://openalex.org/W6846246120","https://openalex.org/W6847068019","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Automatically":[0],"describing":[1],"audio-visual":[2,77,98],"content":[3],"with":[4,64,127],"texts,":[5],"namely":[6],"video":[7],"captioning,":[8],"has":[9],"received":[10],"significant":[11],"attention":[12],"due":[13,42],"to":[14,43,56],"its":[15],"potential":[16],"applications":[17],"across":[18],"diverse":[19],"fields.":[20],"Deep":[21],"neural":[22],"networks":[23],"are":[24,34],"the":[25,44,48,80,86,94,111,121],"dominant":[26],"methods,":[27],"offering":[28],"state-of-the-art":[29],"performance.":[30],"However,":[31],"these":[32],"methods":[33],"often":[35],"undeployable":[36],"in":[37,97,134],"low-power":[38],"devices":[39],"like":[40],"smartphones":[41],"large":[45],"size":[46],"of":[47,76,82],"model":[49],"parameters.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"exploit":[57],"simple":[58],"pooling":[59],"front-end":[60],"and":[61,69],"down-sampling":[62],"algorithms":[63],"knowledge":[65,83],"distillation":[66,84],"for":[67,104],"audio":[68],"visual":[70],"attributes":[71],"using":[72],"a":[73,128],"reduced":[74],"number":[75],"frames.":[78],"With":[79],"help":[81],"from":[85],"teacher":[87],"model,":[88],"our":[89,116],"proposed":[90,117],"method":[91],"greatly":[92],"reduces":[93,120],"redundant":[95],"information":[96],"streams":[99],"without":[100],"losing":[101],"critical":[102],"contexts":[103],"caption":[105],"generation.":[106],"Extensive":[107],"experimental":[108],"evaluations":[109],"on":[110],"MSR-VTT":[112],"dataset":[113],"demonstrate":[114],"that":[115],"approach":[118],"significantly":[119],"inference":[122],"time":[123],"by":[124],"about":[125],"80%":[126],"small":[129],"sacrifice":[130],"(less":[131],"than":[132],"0.02%)":[133],"captioning":[135],"accuracy.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}