{"id":"https://openalex.org/W2603497684","doi":null,"title":"Detecting Categories in News Video Using Acoustic, Speech, and Image Features.","display_name":"Detecting Categories in News Video Using Acoustic, Speech, and Image Features.","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2603497684","mag":"2603497684"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.1720","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.1720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~aberg/papers/trecvid06.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5062886906","display_name":"Slav Petrov","orcid":"https://orcid.org/0000-0002-5505-4861","observed_orcids":["https://orcid.org/0000-0002-5505-4861"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Slav Petrov","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110487910","display_name":"Arlo Faria","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arlo Faria","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013275072","display_name":"Pascal Michaillat","orcid":"https://orcid.org/0000-0003-2381-7470","observed_orcids":["https://orcid.org/0000-0003-2381-7470"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pascal Michaillat","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":"https://orcid.org/0000-0003-2381-7470","affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104361813","display_name":"Alexander C. Berg","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander C. Berg","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X","observed_orcids":["https://orcid.org/0000-0002-9925-905X"]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["SRI International","University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902","observed_orcids":["https://orcid.org/0000-0002-8881-1902","https://orcid.org/0009-0002-5983-2904"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Klein","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":"https://orcid.org/0000-0002-8881-1902","affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594573","display_name":"Jitendra Malik","orcid":"https://orcid.org/0000-0003-3695-1580","observed_orcids":["https://orcid.org/0000-0003-3695-1580"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jitendra Malik","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":"https://orcid.org/0000-0003-3695-1580","affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9666,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88817114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8852999806404114,"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":0.8852999806404114,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.07720000296831131,"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":0.013299999758601189,"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/acoustic-characteristics","display_name":"acoustic features","score":0.7110000252723694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7450000047683716},{"id":"https://openalex.org/keywords/imaging-features","display_name":"imaging features","score":0.8790000081062317},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.8510000109672546},{"id":"https://openalex.org/keywords/trecvid","display_name":"TRECVID","score":0.5130000114440918},{"id":"https://openalex.org/keywords/high-level-feature-extraction","display_name":"high-level feature extraction","score":0.7689999938011169},{"id":"https://openalex.org/keywords/shape-features","display_name":"shape features","score":0.7319999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794159471988678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6207221746444702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.502556324005127},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4646342098712921},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43513602018356323},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41808241605758667},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4157860577106476},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.412198543548584},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.352716326713562},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3459863066673279},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34199315309524536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.1720","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.1720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~aberg/papers/trecvid06.pdf","raw_type":"text"},{"id":"mag:2603497684","doi":null,"is_oa":false,"landing_page_url":"http://acberg.com/papers/trecvid06.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.6600000262260437,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1576520375","https://openalex.org/W1604792744","https://openalex.org/W1608381367","https://openalex.org/W2097560587","https://openalex.org/W2145295623","https://openalex.org/W2165828254","https://openalex.org/W2168002178","https://openalex.org/W2916567321"],"related_works":["https://openalex.org/W2606850727","https://openalex.org/W7098121367","https://openalex.org/W2905853508","https://openalex.org/W2142475372","https://openalex.org/W1614434287","https://openalex.org/W21165000","https://openalex.org/W2384148271","https://openalex.org/W2109788830","https://openalex.org/W2019594093","https://openalex.org/W2389996138"],"abstract_inverted_index":{"This":[0],"work":[1],"describes":[2],"systems":[3,55,65],"for":[4,43],"detecting":[5],"semantic":[6],"categories":[7],"present":[8,85],"in":[9,17,98],"news":[10],"video.":[11],"The":[12],"multimedia":[13],"data":[14],"was":[15,23,247],"processed":[16],"three":[18,81],"ways:":[19],"the":[20,47,62,69,76,80,89,99,107,123,193,203,228,249,273],"audio":[21,229],"signal":[22],"converted":[24],"to":[25,58],"a":[26,35,132,151,241],"sequence":[27],"of":[28,46,61,109,154,166,205,244],"acoustic":[29,158,175,208,224],"features,":[30,257],"automatic":[31],"speech":[32,112,126,156,173,190,195,222,256],"recognition":[33],"provided":[34,180,275],"word-level":[36],"transcription,":[37],"and":[38,53,74,104,113,157,174,182,246],"image":[39,114,142,236],"features":[40,143,176,191,214,225,237],"were":[41,56,218],"computed":[42],"selected":[44],"frames":[45],"video":[48,91],"signal.":[49,230],"Primary":[50],"acoustic,":[51,111],"speech,":[52],"vision":[54,124,251],"trained":[57,140,149,170,188,201],"discriminate":[59],"instances":[60],"categories.":[63],"Higher-level":[64],"exploited":[66],"correlations":[67],"among":[68],"categories,":[70],"incorporated":[71],"sequential":[72],"context,":[73],"combined":[75],"joint":[77],"evidence":[78],"from":[79,88,192,216,227,269],"information":[82],"sources.":[83],"We":[84,96],"experimental":[86],"results":[87],"TREC":[90],"retrieval":[92],"evaluation.":[93],"1.":[94],"OVERVIEW":[95],"participated":[97],"\u201dHigh-Level":[100],"Feature-Extraction":[101],"\u201d":[102],"task":[103],"focused":[105],"on":[106,131,141,150,164,171,189,202],"design":[108],"effective":[110,220],"features:":[115],"\u2022":[116,136,145,160,184,197],"ucb":[117,137,146,161,185,198],"1best:":[118],"For":[119],"each":[120],"category":[121,206],"choose":[122],"or":[125,223],"system":[127,232],"that":[128,260],"performed":[129],"best":[130,250],"held":[133],"out":[134],"set.":[135],"vision:":[138],"SVM":[139,148,163,187,200],"only.":[144],"fusion:":[147],"weighted":[152],"combination":[153],"image,":[155,172],"features.":[159],"concat:":[162],"top":[165],"SVMs":[167],"which":[168,233],"are":[169],"(uses":[177],"only":[178,235,252],"TRECVID":[179,274],"ASR":[181,268],"MT).":[183],"text:":[186],"SRI":[194,270],"recognizer.":[196],"sound:":[199],"outputs":[204],"specific":[207],"GMMs.":[209],"In":[210],"our":[211],"experiments,":[212],"shape":[213],"extracted":[215,226],"images":[217],"more":[219],"than":[221,272],"Our":[231],"used":[234],"(ucb":[238],"vision)":[239],"achieved":[240],"mean":[242],"AP":[243],"0.11":[245],"perhaps":[248],"system.":[253],"When":[254],"using":[255,267],"we":[258],"found":[259],"performance":[261],"can":[262],"be":[263],"greatly":[264],"improved":[265],"by":[266],"rather":[271],"ASR/MT.":[276],"2.":[277]},"counts_by_year":[],"updated_date":"2026-09-24T07:57:37.273135","created_date":"2017-04-07T00:00:00"}
