{"id":"https://openalex.org/W4408354411","doi":"https://doi.org/10.1109/icassp49660.2025.10888241","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","display_name":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354411","doi":"https://doi.org/10.1109/icassp49660.2025.10888241"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5003708446","display_name":"Kyeongha Rho","orcid":"https://orcid.org/0009-0001-6487-5418"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyeongha Rho","raw_affiliation_strings":["KAIST,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035071807","display_name":"Hyeongkeun Lee","orcid":"https://orcid.org/0000-0003-2152-3639"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeongkeun Lee","raw_affiliation_strings":["KAIST,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115926489","display_name":"Valentio Iverson","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Valentio Iverson","raw_affiliation_strings":["University of Waterloo,Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["KAIST,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003708446"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":7.6696,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97210278,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9944999814033508,"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":0.9315999746322632,"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":0.9437435865402222},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.778516948223114},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6621772050857544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5579628944396973},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3426600694656372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32431691884994507},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1812838315963745}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9437435865402222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778516948223114},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6621772050857544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5579628944396973},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3426600694656372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32431691884994507},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1812838315963745}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2506483933","https://openalex.org/W2949376505","https://openalex.org/W3094550259","https://openalex.org/W4226442948","https://openalex.org/W4307323391","https://openalex.org/W4372266552","https://openalex.org/W4372340819","https://openalex.org/W4382202741","https://openalex.org/W4385822505","https://openalex.org/W4386348132","https://openalex.org/W4392902953","https://openalex.org/W4392904001","https://openalex.org/W4400033239","https://openalex.org/W4402112401","https://openalex.org/W4402112418","https://openalex.org/W4402670194","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6682962330","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6798955355","https://openalex.org/W6811156277","https://openalex.org/W6848208918","https://openalex.org/W6854866820","https://openalex.org/W6861444294"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Automated":[0],"audio":[1,11,33,64,67,83],"captioning":[2,23,56,68],"is":[3,125,144],"a":[4,50],"task":[5],"that":[6,58,100,119],"generates":[7],"textual":[8],"descriptions":[9],"for":[10],"content,":[12],"and":[13,34,84],"recent":[14],"studies":[15],"have":[16],"explored":[17],"using":[18,104],"visual":[19,35,61,85],"information":[20,62],"to":[21,30,65,77],"enhance":[22],"quality.":[24],"However,":[25],"current":[26],"methods":[27,131],"often":[28],"fail":[29],"effectively":[31,59],"fuse":[32],"data,":[36],"missing":[37],"important":[38],"semantic":[39,90],"cues":[40],"from":[41],"each":[42,120],"modality.":[43],"To":[44],"address":[45],"this,":[46],"we":[47,93],"introduce":[48],"LAVCap,":[49],"large":[51,139],"language":[52],"model":[53],"(LLM)-based":[54],"audio-visual":[55,102],"framework":[57,124],"integrates":[60],"with":[63,111],"improve":[66],"performance.":[69],"LAVCap":[70,127],"employs":[71],"an":[72,95,105],"optimal":[73,96,106,113],"transport-based":[74],"alignment":[75],"loss":[76],"bridge":[78],"the":[79,112,133],"modality":[80],"gap":[81],"between":[82],"features,":[86],"enabling":[87],"more":[88],"effective":[89],"extraction.":[91],"Additionally,":[92],"propose":[94],"transport":[97,107],"attention":[98],"module":[99],"enhances":[101],"fusion":[103],"assignment":[108],"map.":[109],"Combined":[110],"training":[114],"strategy,":[115],"experimental":[116],"results":[117],"demonstrate":[118],"component":[121],"of":[122],"our":[123],"effective.":[126],"outperforms":[128],"existing":[129],"state-of-the-art":[130],"on":[132,138],"AudioCaps":[134],"dataset,":[135],"without":[136],"relying":[137],"datasets":[140],"or":[141],"post-processing.":[142],"Code":[143],"available":[145],"at":[146],"https://github.com/NAVER-INTEL-Co-Lab/gaudi-lavcap.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
