{"id":"https://openalex.org/W4385477794","doi":"https://doi.org/10.1109/icasspw59220.2023.10192578","title":"Role of Audio In Video Summarization","display_name":"Role of Audio In Video Summarization","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385477794","doi":"https://doi.org/10.1109/icasspw59220.2023.10192578"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10192578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10192578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5033044122","display_name":"Ibrahim Shoer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim Shoer","raw_affiliation_strings":["Koç University,KUIS-AI Laboratory Multimedia, Vision and Graphics Group College of Engineering,Istanbul,Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Koç University,KUIS-AI Laboratory Multimedia, Vision and Graphics Group College of Engineering,Istanbul,Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005515553","display_name":"Berkay K\u00f6pr\u00fc","orcid":"https://orcid.org/0000-0003-2238-137X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berkay K\u00f6pr\u00fc","raw_affiliation_strings":["Koç University,KUIS-AI Laboratory Multimedia, Vision and Graphics Group College of Engineering,Istanbul,Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Koç University,KUIS-AI Laboratory Multimedia, Vision and Graphics Group College of Engineering,Istanbul,Turkey","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064993025","display_name":"Engin Erzin","orcid":"https://orcid.org/0000-0002-2715-2368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Engin Erzin","raw_affiliation_strings":["Koç University,KUIS-AI Laboratory Multimedia, Vision and Graphics Group College of Engineering,Istanbul,Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Koç University,KUIS-AI Laboratory Multimedia, Vision and Graphics Group College of Engineering,Istanbul,Turkey","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9585999846458435,"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":0.9647213220596313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8442273736000061},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6012099385261536},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5168285965919495},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4412821829319},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4273887872695923},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.4150004982948303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3992561399936676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34766343235969543}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9647213220596313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8442273736000061},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6012099385261536},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5168285965919495},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4412821829319},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4273887872695923},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4150004982948303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3992561399936676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34766343235969543},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10192578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10192578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1924343884","https://openalex.org/W2097117768","https://openalex.org/W2120645068","https://openalex.org/W2742409927","https://openalex.org/W2781922022","https://openalex.org/W2964158702","https://openalex.org/W2964167369","https://openalex.org/W2980888549","https://openalex.org/W3036601975","https://openalex.org/W3162472557","https://openalex.org/W3209983272","https://openalex.org/W3210314917","https://openalex.org/W3210592264","https://openalex.org/W4220861526","https://openalex.org/W4287173589","https://openalex.org/W6640109428","https://openalex.org/W6780218876","https://openalex.org/W6795952400"],"related_works":["https://openalex.org/W2793113313","https://openalex.org/W2308250245","https://openalex.org/W2735661856","https://openalex.org/W2312215770","https://openalex.org/W1991604670","https://openalex.org/W2000926173","https://openalex.org/W2086044694","https://openalex.org/W1532127741","https://openalex.org/W4310991386","https://openalex.org/W2994713541"],"abstract_inverted_index":{"Video":[0],"summarization":[1,20,64,103],"attracts":[2],"attention":[3],"for":[4,26,118,152],"efficient":[5],"video":[6,19,53,63,102,121,125,156],"representation,":[7],"retrieval,":[8],"and":[9,14,75,94,114,129,138,154],"browsing":[10],"to":[11,91],"ease":[12],"volume":[13],"traffic":[15],"surge":[16],"problems.":[17],"Although":[18],"mostly":[21],"uses":[22],"the":[23,28,41,52,96,101,108,119,148],"visual":[24],"channel":[25,43],"compaction,":[27],"benefits":[29],"of":[30,48,69,98],"audio-visual":[31,49,62,70,86,120,134,155],"modeling":[32],"appeared":[33],"in":[34,51,100],"recent":[35],"literature.":[36],"The":[37],"information":[38,71],"coming":[39],"from":[40],"audio":[42,99],"can":[44],"be":[45],"a":[46,60,81,143],"result":[47],"correlation":[50,88],"content.":[54],"In":[55],"this":[56],"study,":[57],"we":[58,79],"propose":[59],"new":[61,82],"framework":[65],"integrating":[66],"four":[67],"ways":[68],"fusion":[72],"with":[73],"GRU-based":[74],"attention-based":[76],"networks.":[77],"Furthermore,":[78,123],"investigate":[80],"explainability":[83],"methodology":[84],"using":[85],"canonical":[87],"analysis":[89],"(CCA)":[90],"better":[92],"understand":[93],"explain":[95],"role":[97],"task.":[104],"Experimental":[105],"evaluations":[106],"on":[107,127,133],"TVSum":[109,128],"dataset":[110],"attain":[111],"F1":[112],"score":[113,116],"Kendall-tau":[115],"improvements":[117],"summarization.":[122,157],"splitting":[124],"content":[126],"COGNIMUSE":[130],"datasets":[131],"based":[132],"CCA":[135],"as":[136],"positively":[137,149],"negatively":[139],"correlated":[140,150],"videos":[141,151],"yields":[142],"strong":[144],"performance":[145],"improvement":[146],"over":[147],"audio-only":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}