{"id":"https://openalex.org/W4385822505","doi":"https://doi.org/10.21437/interspeech.2023-914","title":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","display_name":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822505","doi":"https://doi.org/10.21437/interspeech.2023-914"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-914","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/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":["University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062202568","display_name":"Qiushi Huang","orcid":"https://orcid.org/0000-0001-7935-6015"},"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"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Qiushi Huang","raw_affiliation_strings":["University of Surrey, UK","Southern University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070892237","display_name":"Xinhao Mei","orcid":"https://orcid.org/0000-0001-6079-5130"},"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":"Xinhao Mei","raw_affiliation_strings":["University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"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":"Qiuqiang Kong","raw_affiliation_strings":["University of Surrey, UK","ByteDance, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153327","display_name":"Jianyuan Sun","orcid":null},"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":"Jianyuan Sun","raw_affiliation_strings":["University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024084275","display_name":"Shengchen Li","orcid":"https://orcid.org/0000-0002-2488-298X"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchen Li","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["ByteDance, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433691","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-1100-4835"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Southern University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103338787","display_name":"Lilian H. Tang","orcid":"https://orcid.org/0009-0009-7543-2792"},"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":"Lilian H. Tang","raw_affiliation_strings":["University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"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":"Mark D. Plumbley","raw_affiliation_strings":["University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":[{"id":"https://openalex.org/I250383648","display_name":"Izmir K\u00e2tip \u00c7elebi University","ror":"https://ror.org/024nx4843","country_code":"TR","type":"education","lineage":["https://openalex.org/I250383648"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Volkan K\u0131l\u0131\u00e7","raw_affiliation_strings":["Izmir Katip Celebi University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Izmir Katip Celebi University, Turkey","institution_ids":["https://openalex.org/I250383648"]}]},{"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":["University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":13,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9087,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88212224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2838","last_page":"2842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.994700014591217,"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":0.994700014591217,"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":0.9911999702453613,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9847999811172485,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8878454566001892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7902207970619202},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.768984317779541},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.557295024394989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4209624230861664},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3535890579223633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2486979365348816},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07061466574668884}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8878454566001892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902207970619202},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.768984317779541},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.557295024394989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4209624230861664},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3535890579223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2486979365348816},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07061466574668884}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-914","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11208480520002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8857457899","display_name":null,"funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2619383789","https://openalex.org/W2619947201","https://openalex.org/W2773514261","https://openalex.org/W2905139236","https://openalex.org/W2936774411","https://openalex.org/W2963524571","https://openalex.org/W3015591594","https://openalex.org/W3034815696","https://openalex.org/W3094502228","https://openalex.org/W3097791920","https://openalex.org/W3174906557","https://openalex.org/W3185739472","https://openalex.org/W3186781156","https://openalex.org/W3189036352","https://openalex.org/W3197621271","https://openalex.org/W3210279979","https://openalex.org/W4221152061","https://openalex.org/W4221157007","https://openalex.org/W4224871700","https://openalex.org/W4226174231","https://openalex.org/W4280567182","https://openalex.org/W4295190891","https://openalex.org/W4297841792","https://openalex.org/W4303578640","https://openalex.org/W4305008490","https://openalex.org/W4312463400","https://openalex.org/W4312898271","https://openalex.org/W4361865887","https://openalex.org/W4382202741","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4320016117","https://openalex.org/W4307856881","https://openalex.org/W2901467237","https://openalex.org/W2547835662","https://openalex.org/W3183824823","https://openalex.org/W3008515501","https://openalex.org/W2923366293","https://openalex.org/W2905654560","https://openalex.org/W2519434724","https://openalex.org/W2596543464"],"abstract_inverted_index":{"Audio":[0],"captioning":[1,75,111],"aims":[2],"to":[3,18,49,63,77],"generate":[4],"text":[5],"descriptions":[6],"of":[7,46,53],"audio":[8,28,41,74,92,110],"clips.In":[9],"the":[10,51,69,98,102,108],"real":[11],"world,":[12],"many":[13],"objects":[14],"produce":[15],"similar":[16],"sounds.How":[17],"accurately":[19],"recognize":[20],"ambiguous":[21,54],"sounds":[22],"is":[23],"a":[24],"major":[25],"challenge":[26],"for":[27],"captioning.In":[29],"this":[30],"work,":[31],"inspired":[32],"by":[33],"inherent":[34],"human":[35],"multimodal":[36],"perception,":[37],"we":[38,57,83],"propose":[39,84],"visuallyaware":[40],"captioning,":[42],"which":[43],"makes":[44],"use":[45],"visual":[47,61,70,94],"information":[48,100],"help":[50],"description":[52],"sounding":[55],"objects.Specifically,":[56],"introduce":[58],"an":[59,73,85],"off-the-shelf":[60],"encoder":[62],"extract":[64],"video":[65],"features":[66,71],"and":[67,93,96],"incorporate":[68],"into":[72],"system.Furthermore,":[76],"better":[78],"exploit":[79],"complementary":[80],"audio-visual":[81,86],"contexts,":[82],"attention":[87],"mechanism":[88],"that":[89,114],"adaptively":[90],"integrates":[91],"context":[95],"removes":[97],"redundant":[99],"in":[101],"latent":[103],"space.Experimental":[104],"results":[105,120],"on":[106,121],"AudioCaps,":[107],"largest":[109],"dataset,":[112],"show":[113],"our":[115],"proposed":[116],"method":[117],"achieves":[118],"state-of-theart":[119],"machine":[122],"translation":[123],"metrics.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
