{"id":"https://openalex.org/W1988419820","doi":"https://doi.org/10.1145/2324796.2324799","title":"Beyond audio and video retrieval","display_name":"Beyond audio and video retrieval","publication_year":2012,"publication_date":"2012-06-05","ids":{"openalex":"https://openalex.org/W1988419820","doi":"https://doi.org/10.1145/2324796.2324799","mag":"1988419820"},"language":"en","primary_location":{"id":"doi:10.1145/2324796.2324799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","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/A5110183841","display_name":"Duo Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Duo Ding","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086192353","display_name":"Shourabh Rawat","orcid":"https://orcid.org/0009-0000-0160-3741"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shourabh Rawat","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008492426","display_name":"Peter Schulam","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Franz Schulam","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034672538","display_name":"Susanne Burger","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susanne Burger","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066182035","display_name":"Ehsan Younessian","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ehsan Younessian","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505813","display_name":"Lei Bao","orcid":"https://orcid.org/0000-0003-4764-8560"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Bao","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086047097","display_name":"Michael G. Christel","orcid":"https://orcid.org/0000-0002-2660-2515"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael G. Christel","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107836252","display_name":"Alexander G. Hauptmann","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Hauptmann","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5110183841"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":8.6047,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98152966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9900000095367432,"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":0.8965247869491577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8769630193710327},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.7398688793182373},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5768599510192871},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5474477410316467},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5397544503211975},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5359249114990234},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.49161773920059204},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45871761441230774},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4403374195098877},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35970190167427063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3366250991821289},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3150906264781952}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8965247869491577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769630193710327},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.7398688793182373},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5768599510192871},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5474477410316467},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5397544503211975},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5359249114990234},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.49161773920059204},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45871761441230774},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4403374195098877},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35970190167427063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3366250991821289},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3150906264781952},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2324796.2324799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G2979156668","display_name":null,"funder_award_id":"IIS-0917072CCF-1019104","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G6874514035","display_name":null,"funder_award_id":"IIS-0917072CCF-1019104","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W11313625","https://openalex.org/W105852416","https://openalex.org/W1664028424","https://openalex.org/W1983408706","https://openalex.org/W2019273110","https://openalex.org/W2028582118","https://openalex.org/W2062875547","https://openalex.org/W2094998392","https://openalex.org/W2129286681","https://openalex.org/W2133273100","https://openalex.org/W2155003238","https://openalex.org/W2181909559","https://openalex.org/W2531621976","https://openalex.org/W2534300396","https://openalex.org/W6679740967"],"related_works":["https://openalex.org/W2377059580","https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W4200355488","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W127000293","https://openalex.org/W4390942716"],"abstract_inverted_index":{"Given":[0],"the":[1,11,53,96,165,196],"deluge":[2],"of":[3,28,55,67,89,152,163,215,219],"multimedia":[4],"content":[5],"that":[6,32,128],"is":[7,14],"becoming":[8],"available":[9],"over":[10],"Internet,":[12],"it":[13],"increasingly":[15],"important":[16,97],"to":[17,20,103,132,189],"be":[18,130],"able":[19,131],"effectively":[21],"examine":[22],"and":[23,48,51,78,108,117,143,173,181,208,212],"organize":[24],"these":[25],"large":[26,150],"stores":[27],"information":[29,98],"in":[30,99],"ways":[31],"go":[33],"beyond":[34],"browsing":[35],"or":[36,147],"collaborative":[37],"filtering.":[38],"In":[39,156],"this":[40,121,157],"paper":[41],"we":[42,159],"review":[43],"previous":[44],"work":[45],"on":[46,195],"audio":[47],"video":[49,73,101,114],"processing,":[50],"define":[52],"task":[54],"Topic-Oriented":[56],"Multimedia":[57],"Summarization":[58],"(TOMS)":[59],"using":[60],"natural":[61,90,185],"language":[62,91,186],"generation:":[63],"given":[64,179],"a":[65,72,81,87,100,104,113,123,149,178,183,191,216],"set":[66],"automatically":[68,85],"extracted":[69,197],"features":[70,172,176],"from":[71,177],"(such":[74],"as":[75,122],"visual":[76,170],"concepts":[77],"ASR":[79,174],"transcripts)":[80],"TOMS":[82,166,210],"system":[83,188],"will":[84,129],"generate":[86],"paragraph":[88],"(\"a":[92],"recounting\"),":[93],"which":[94],"summarizes":[95],"belonging":[102],"certain":[105],"topic":[106],"area,":[107],"provides":[109],"explanations":[110],"for":[111,205],"why":[112],"was":[115],"matched":[116],"retrieved.":[118],"We":[119,168,199],"see":[120],"first":[124],"step":[125],"towards":[126],"systems":[127],"discriminate":[133],"visually":[134],"similar,":[135],"but":[136],"semantically":[137],"different":[138],"videos,":[139],"compare":[140],"two":[141],"videos":[142,153],"provide":[144],"textual":[145,192],"output":[146],"summarize":[148],"number":[151],"at":[154],"once.":[155],"paper,":[158],"introduce":[160],"our":[161,220],"approach":[162],"solving":[164],"problem.":[167],"extract":[169],"concept":[171],"transcription":[175],"video,":[180],"develop":[182],"template-based":[184],"generation":[187],"produce":[190],"recounting":[193],"based":[194],"features.":[198],"also":[200],"propose":[201],"possible":[202],"experimental":[203],"designs":[204],"continuously":[206],"evaluating":[207],"improving":[209],"systems,":[211],"present":[213],"results":[214],"pilot":[217],"evaluation":[218],"initial":[221],"system.":[222]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
