{"id":"https://openalex.org/W2126392652","doi":"https://doi.org/10.1109/icme.2002.1035604","title":"Enhanced video browsing using automatically extracted audio excerpts","display_name":"Enhanced video browsing using automatically extracted audio excerpts","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2126392652","doi":"https://doi.org/10.1109/icme.2002.1035604","mag":"2126392652"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2002.1035604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","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/A5087467671","display_name":"Jonathan Foote","orcid":"https://orcid.org/0000-0003-4411-1362"},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Foote","raw_affiliation_strings":["FX Palo Alto Laboratory, Palo Alto, CA, USA","FX Palo Alto Lab., CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970"]},{"raw_affiliation_string":"FX Palo Alto Lab., CA, USA","institution_ids":["https://openalex.org/I26274970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069841532","display_name":"Matthew Cooper","orcid":"https://orcid.org/0000-0003-2395-8628"},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Cooper","raw_affiliation_strings":["FX Palo Alto Laboratory, CA, USA","FX Palo Alto Lab., CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, CA, USA","institution_ids":["https://openalex.org/I26274970"]},{"raw_affiliation_string":"FX Palo Alto Lab., CA, USA","institution_ids":["https://openalex.org/I26274970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058611482","display_name":"Lynn Wilcox","orcid":null},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Wilcox","raw_affiliation_strings":["FX Palo Alto Laboratory, Palo Alto, CA, USA","FX Palo Alto Lab., CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970"]},{"raw_affiliation_string":"FX Palo Alto Lab., CA, USA","institution_ids":["https://openalex.org/I26274970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2966,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5918175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"357","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8845786452293396},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6613622307777405},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.5086067914962769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5065149068832397},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47947797179222107},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4630088806152344},{"id":"https://openalex.org/keywords/video-capture","display_name":"Video capture","score":0.43981218338012695},{"id":"https://openalex.org/keywords/smacker-video","display_name":"Smacker video","score":0.4330100119113922},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4326813220977783},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.4070097506046295},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.40455156564712524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33386266231536865},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.2633434534072876},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.21542635560035706},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08908477425575256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8845786452293396},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6613622307777405},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.5086067914962769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5065149068832397},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47947797179222107},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4630088806152344},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.43981218338012695},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.4330100119113922},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4326813220977783},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4070097506046295},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.40455156564712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33386266231536865},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2633434534072876},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.21542635560035706},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08908477425575256},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2002.1035604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.5480","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.5480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.fxpal.com/people/foote/papers/icme02-1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W139898027","https://openalex.org/W1966663330","https://openalex.org/W2008611008","https://openalex.org/W2019276416","https://openalex.org/W2052006268","https://openalex.org/W2088193042","https://openalex.org/W2111331420","https://openalex.org/W2112006116","https://openalex.org/W2168249484","https://openalex.org/W2403632467","https://openalex.org/W4285719527","https://openalex.org/W6605678257","https://openalex.org/W6713425194"],"related_works":["https://openalex.org/W1972455458","https://openalex.org/W2033891286","https://openalex.org/W1659903366","https://openalex.org/W4249922618","https://openalex.org/W2139928945","https://openalex.org/W1734875414","https://openalex.org/W2205749934","https://openalex.org/W1861066240","https://openalex.org/W2369074649","https://openalex.org/W2289298825"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"method":[3],"for":[4,56],"rapidly":[5],"and":[6,53],"robustly":[7],"extracting":[8],"audio":[9,32,44],"excerpts":[10,33],"without":[11,62],"the":[12,36,41],"overhead":[13],"of":[14],"speech":[15],"recognition":[16],"or":[17,59,67],"speaker":[18],"segmentation.":[19],"An":[20],"immediate":[21],"application":[22],"is":[23],"to":[24],"automatically":[25],"augment":[26],"keyframe-based":[27],"video":[28,37,58,66],"summaries":[29],"with":[30,35,47],"informative":[31],"associated":[34],"segments":[38],"represented":[39],"by":[40],"keyframes.":[42],"Short":[43],"clips":[45],"combined":[46],"keyframes":[48],"comprise":[49],"an":[50],"extremely":[51],"lightweight":[52],"Web-browsable":[54],"interface":[55],"auditioning":[57],"similar":[60],"media,":[61],"using":[63],"bandwidth-intensive":[64],"streaming":[65],"audio.":[68]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
