{"id":"https://openalex.org/W3209871323","doi":"https://doi.org/10.1109/tmm.2022.3229975","title":"Cross Modal Video Representations for Weakly Supervised Active Speaker Localization","display_name":"Cross Modal Video Representations for Weakly Supervised Active Speaker Localization","publication_year":2022,"publication_date":"2022-12-16","ids":{"openalex":"https://openalex.org/W3209871323","doi":"https://doi.org/10.1109/tmm.2022.3229975","mag":"3209871323"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3229975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3229975","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.04358","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103065972","display_name":"Rahul Sharma","orcid":"https://orcid.org/0000-0003-1697-3897"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Sharma","raw_affiliation_strings":["Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1697-3897","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[{"id":"https://openalex.org/I1342924430","display_name":"LAC+USC Medical Center","ror":"https://ror.org/04xzj3x20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1328359107","https://openalex.org/I1342924430"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["USC, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2845-1079","affiliations":[{"raw_affiliation_string":"USC, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1342924430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1052-6204","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1162,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.30278884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"25","issue":null,"first_page":"7825","last_page":"7836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.774033784866333},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6760854721069336},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5548315644264221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5543729066848755},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5527608394622803},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.46665334701538086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46500998735427856},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.46122628450393677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41525009274482727},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.21413415670394897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774033784866333},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6760854721069336},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5548315644264221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5543729066848755},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5527608394622803},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.46665334701538086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46500998735427856},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.46122628450393677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41525009274482727},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.21413415670394897},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tmm.2022.3229975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3229975","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2003.04358","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.04358","pdf_url":"https://arxiv.org/pdf/2003.04358","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3209871323","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.04358.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.04358","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.04358","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.04358","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.04358","pdf_url":"https://arxiv.org/pdf/2003.04358","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6600000262260437,"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":54,"referenced_works":["https://openalex.org/W1586079445","https://openalex.org/W2029590942","https://openalex.org/W2034214321","https://openalex.org/W2068678037","https://openalex.org/W2106488367","https://openalex.org/W2159505618","https://openalex.org/W2164899449","https://openalex.org/W2168996682","https://openalex.org/W2171819471","https://openalex.org/W2252355370","https://openalex.org/W2287407690","https://openalex.org/W2295107390","https://openalex.org/W2547701628","https://openalex.org/W2593116425","https://openalex.org/W2604260814","https://openalex.org/W2604379605","https://openalex.org/W2607037079","https://openalex.org/W2619697695","https://openalex.org/W2765793020","https://openalex.org/W2885307078","https://openalex.org/W2895249420","https://openalex.org/W2936299888","https://openalex.org/W2954458766","https://openalex.org/W2962858109","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963603913","https://openalex.org/W2963610932","https://openalex.org/W2963952323","https://openalex.org/W2970250044","https://openalex.org/W2971784756","https://openalex.org/W2981851635","https://openalex.org/W2991533779","https://openalex.org/W3015783745","https://openalex.org/W3016098309","https://openalex.org/W3034552680","https://openalex.org/W3034702511","https://openalex.org/W3035333188","https://openalex.org/W3035725370","https://openalex.org/W3093287838","https://openalex.org/W3106237638","https://openalex.org/W3116298410","https://openalex.org/W3118120400","https://openalex.org/W3118593445","https://openalex.org/W3119269912","https://openalex.org/W3119957342","https://openalex.org/W3153167542","https://openalex.org/W3201594678","https://openalex.org/W3203209821","https://openalex.org/W4312268709","https://openalex.org/W6683078286","https://openalex.org/W6684193366","https://openalex.org/W6782004394"],"related_works":["https://openalex.org/W3015734344","https://openalex.org/W2768817490","https://openalex.org/W3202022704","https://openalex.org/W2809767522","https://openalex.org/W3094123278","https://openalex.org/W3191488649","https://openalex.org/W3099638501","https://openalex.org/W3015356123","https://openalex.org/W3040260790","https://openalex.org/W2608612081","https://openalex.org/W3123226376","https://openalex.org/W3105099157","https://openalex.org/W3159929162","https://openalex.org/W3197567540","https://openalex.org/W2991487804","https://openalex.org/W2951804919","https://openalex.org/W3032892481","https://openalex.org/W2941492599","https://openalex.org/W2979157532","https://openalex.org/W3112385539"],"abstract_inverted_index":{"An":[0],"objective":[1],"understanding":[2],"of":[3,10,78,103,123,137,180,188,214],"media":[4,56,73],"depictions,":[5],"such":[6,20],"as":[7,21,159],"inclusive":[8],"portrayals":[9],"how":[11],"much":[12],"someone":[13,37],"is":[14,38,59,125],"heard":[15],"and":[16,24,35,40,69,75,151,206,210],"seen":[17],"on":[18,192],"screen":[19],"in":[22,54,72,106,119,141,222],"film":[23],"television,":[25],"requires":[26],"the":[27,49,55,66,76,100,107,111,135,146,178,186,189,212,215],"machines":[28],"to":[29,65,99,224],"discern":[30],"automatically":[31,46],"who,":[32],"when,":[33],"how,":[34],"where":[36],"talking,":[39],"not.":[41],"Speaker":[42],"activity":[43],"can":[44],"be":[45],"discerned":[47],"from":[48,155],"rich":[50],"multimodal":[51],"information":[52,97],"present":[53,85,129],"content.":[57,143],"This":[58],"however":[60],"a":[61,86,104,130,160],"challenging":[62],"problem":[63],"due":[64],"vast":[67],"variety":[68],"contextual":[70],"variability":[71],"content,":[74],"lack":[77],"labeled":[79],"data.":[80],"In":[81],"this":[82],"work,":[83],"we":[84,128,171],"cross-modal":[87,148,216],"neural":[88],"network":[89],"for":[90,113,116,134,162,177,218],"learning":[91],"visual":[92,108,120,149],"representations,":[93,150],"which":[94,124],"have":[95],"implicit":[96],"pertaining":[98],"spatial":[101],"location":[102],"speaker":[105,182,199],"frames.":[109],"Avoiding":[110],"need":[112],"manual":[114,168],"annotations":[115],"active":[117,139,181,198,220],"speakers":[118,140,221],"frames,":[121],"acquiring":[122],"very":[126],"expensive,":[127],"weakly":[131],"supervised":[132,226],"system":[133,191],"task":[136,179],"localizing":[138,219],"movie":[142,156],"We":[144,184],"use":[145],"learned":[147],"provide":[152],"weak":[153],"supervision":[154],"subtitles":[157],"acting":[158],"proxy":[161],"voice":[163],"activity,":[164],"thus":[165],"requiring":[166],"no":[167],"annotations.":[169],"Furthermore,":[170],"propose":[172],"an":[173],"audio-assisted":[174],"post-processing":[175],"formulation":[176],"detection.":[183],"evaluate":[185],"performance":[187],"proposed":[190],"three":[193],"benchmark":[194],"datasets:":[195],"i)":[196],"AVA":[197],"dataset,":[200,205],"ii)":[201],"Visual":[202],"person":[203],"clustering":[204],"iii)":[207],"Columbia":[208],"datset,":[209],"demonstrate":[211],"effectiveness":[213],"embeddings":[217],"comparison":[223],"fully":[225],"systems.":[227]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}