{"id":"https://openalex.org/W2153738600","doi":"https://doi.org/10.1109/mmsp.2006.285298","title":"Audio-Visual Feature Extraction for Semi-Automatic Annotation of Meetings","display_name":"Audio-Visual Feature Extraction for Semi-Automatic Annotation of Meetings","publication_year":2006,"publication_date":"2006-10-01","ids":{"openalex":"https://openalex.org/W2153738600","doi":"https://doi.org/10.1109/mmsp.2006.285298","mag":"2153738600"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2006.285298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5109865320","display_name":"Mari\u00e1n K\u00e9pesi","orcid":null},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marian Kepesi","raw_affiliation_strings":["SPSC Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"SPSC Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049148493","display_name":"Michael Neffe","orcid":null},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Neffe","raw_affiliation_strings":["SPSC Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"SPSC Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012795098","display_name":"Tuan Van Pham","orcid":"https://orcid.org/0000-0002-9225-0191"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Tuan Van Pham","raw_affiliation_strings":["SPSC Laboratory, Graz University of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"SPSC Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032685725","display_name":"Michael Grabner","orcid":"https://orcid.org/0000-0002-5220-721X"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Grabner","raw_affiliation_strings":["Inst. for Computer Graphics and Vision, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Inst. for Computer Graphics and Vision, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060290606","display_name":"Helmut Gr\u00e4bner","orcid":"https://orcid.org/0000-0003-1377-2686"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Helmut Grabner","raw_affiliation_strings":["Inst. for Computer Graphics and Vision, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Inst. for Computer Graphics and Vision, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016491652","display_name":"Andreas Juffinger","orcid":null},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andreas Juffinger","raw_affiliation_strings":["Inst. for Theoretical Computer Science, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Inst. for Theoretical Computer Science, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":1,"citation_normalized_percentile":{"value":0.200597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":61,"max":68},"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"211"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988,"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":0.9988,"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/T12031","display_name":"Speech and dialogue systems","score":0.9982,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9978,"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/identification","display_name":"Identification","score":0.59447193},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.52832144},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4529466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84286594},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8290349},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6804336},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5960454},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.59447193},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.52832144},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4529466},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42690623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42515418},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4246634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3888721},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35527998},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2006.285298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":19,"referenced_works":["https://openalex.org/W1491761707","https://openalex.org/W1492341426","https://openalex.org/W1986408226","https://openalex.org/W2008732477","https://openalex.org/W2102722370","https://openalex.org/W2103876808","https://openalex.org/W2120478181","https://openalex.org/W2151103935","https://openalex.org/W2164010719","https://openalex.org/W2164598857","https://openalex.org/W2170865122","https://openalex.org/W2295262250","https://openalex.org/W2400267228","https://openalex.org/W2972843502","https://openalex.org/W2986815505","https://openalex.org/W319228038","https://openalex.org/W4230607658","https://openalex.org/W79946180","https://openalex.org/W8547393"],"related_works":["https://openalex.org/W4301143707","https://openalex.org/W2952745240","https://openalex.org/W2625833328","https://openalex.org/W2392921965","https://openalex.org/W2377979023","https://openalex.org/W2361861616","https://openalex.org/W2358755282","https://openalex.org/W2263699433","https://openalex.org/W2218034408","https://openalex.org/W2185469136"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"the":[5,26,32,45,76,87,93,119,124],"building":[6],"blocks":[7],"of":[8,19,31,44,65],"our":[9],"semi-automatic":[10],"annotation":[11,18,99],"tool":[12],"which":[13],"supports":[14],"multi-modal":[15],"and":[16,29,42,53,63,67,73,86,121],"multi-level":[17],"meetings.":[20,109],"The":[21,38,98,110],"main":[22],"focus":[23],"is":[24],"on":[25],"proper":[27],"design":[28],"functionality":[30],"modules":[33],"for":[34],"recognizing":[35],"meeting":[36],"actions.":[37],"key":[39],"features,":[40],"identity":[41],"position":[43],"speakers,":[46],"are":[47,83,90,101],"provided":[48],"by":[49,95],"different":[50],"modalities":[51],"(audio":[52],"video).":[54],"Three":[55],"audio":[56],"algorithms":[57,70],"(voice":[58],"activity":[59],"detection,":[60],"speaker":[61],"identification":[62],"direction":[64],"arrival)":[66],"three":[68],"video":[69],"(detection,":[71],"tracking":[72],"identification)":[74],"form":[75],"low-level":[77],"feature":[78],"extraction":[79],"components.":[80],"Low-level":[81],"features":[82],"automatically":[84],"merged":[85],"recognized":[88],"actions":[89,125],"proposed":[91],"to":[92,106],"user":[94,111],"visualizing":[96],"them.":[97],"labels":[100],"related":[102],"but":[103],"not":[104],"limited":[105],"events":[107],"during":[108],"can":[112],"finally":[113],"confirm":[114],"or":[115],"if":[116],"necessary,":[117],"modify":[118],"suggestion,":[120],"then":[122],"store":[123],"into":[126],"a":[127],"database":[128]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2153738600","counts_by_year":[],"updated_date":"2024-12-12T07:03:49.077101","created_date":"2016-06-24"}