{"id":"https://openalex.org/W4406859274","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849046","title":"Multi-Modal Video Summarization Based on Two-Stage Fusion of Audio, Visual, and Recognized Text Information","display_name":"Multi-Modal Video Summarization Based on Two-Stage Fusion of Audio, Visual, and Recognized Text Information","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859274","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849046"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081898726","display_name":"Zekun Yang","orcid":"https://orcid.org/0000-0003-3518-8229"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zekun Yang","raw_affiliation_strings":["Nagoya University,Information Technology Center,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101936543","display_name":"Jiajun He","orcid":"https://orcid.org/0009-0006-6489-5220"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiajun He","raw_affiliation_strings":["Nagoya University,Graduate School of Information Science,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Information Science,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Information Technology Center,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9305999875068665,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9199469685554504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7600557804107666},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6463503241539001},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.642902672290802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49466511607170105},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.475897878408432},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4506058692932129},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4298252463340759},{"id":"https://openalex.org/keywords/information-fusion","display_name":"Information fusion","score":0.4191470444202423},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3307763934135437},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3232797384262085},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08309957385063171}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9199469685554504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600557804107666},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6463503241539001},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.642902672290802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49466511607170105},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.475897878408432},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4506058692932129},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4298252463340759},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.4191470444202423},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3307763934135437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3232797384262085},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08309957385063171},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2953104586","https://openalex.org/W2962934715","https://openalex.org/W3034999214","https://openalex.org/W3100439847","https://openalex.org/W3104210310","https://openalex.org/W3211495814","https://openalex.org/W4224925623","https://openalex.org/W4319438344","https://openalex.org/W4385245566","https://openalex.org/W4385574343","https://openalex.org/W4385767852","https://openalex.org/W4385822642","https://openalex.org/W4385822729","https://openalex.org/W4386071467","https://openalex.org/W4386076133","https://openalex.org/W4391021742","https://openalex.org/W4392904444","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6682631176","https://openalex.org/W6755559483","https://openalex.org/W6769627184","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6802077771","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6853555250","https://openalex.org/W6857062747","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W2355579697","https://openalex.org/W4360871138","https://openalex.org/W3208972923"],"abstract_inverted_index":{"Multi-modal":[0],"video":[1,23,34,49,54,83],"summarization":[2,50],"task":[3],"provides":[4],"a":[5,46,104],"text":[6,27,37,109],"summary":[7,21,134],"by":[8,65,74],"combining":[9],"information":[10,81,130],"from":[11,22],"different":[12,93],"kinds":[13],"of":[14,76],"inputs.":[15],"Previous":[16],"methods":[17],"usually":[18],"generate":[19,108,132],"the":[20,39,98,113,137],"and":[24,35,55,79,86,97],"ground":[25],"truth":[26],"inputs,":[28,57],"but":[29],"seldom":[30],"study":[31],"how":[32],"audio,":[33],"ASR":[36,71],"influence":[38],"results.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"introduce":[45],"novel":[47],"multi-modal":[48],"approach":[51],"that":[52,117,127],"leverages":[53],"audio":[56,80,129],"along":[58],"with":[59],"speech-recognized":[60],"text.":[61],"Our":[62],"method":[63,119],"initiates":[64],"conducting":[66],"speech":[67],"recognition":[68],"using":[69,82],"whisper":[70],"model,":[72],"followed":[73],"representation":[75],"visual,":[77],"textual,":[78],"transformer,":[84],"BART,":[85],"whisper,":[87],"respectively.":[88],"Subsequently,":[89],"two-stage":[90],"fusion":[91],"between":[92],"modalities":[94],"is":[95,124],"applied,":[96],"fused":[99],"features":[100],"are":[101],"fed":[102],"into":[103],"BART":[105],"decoder":[106],"to":[107],"summaries.":[110],"Experiments":[111],"on":[112],"how2":[114],"dataset":[115],"show":[116],"our":[118],"outperforms":[120],"previous":[121],"baselines.":[122],"It":[123],"also":[125],"revealed":[126],"incorporating":[128],"helps":[131],"better":[133],"even":[135],"if":[136],"texts":[138],"contain":[139],"certain":[140],"errors.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}