{"id":"https://openalex.org/W3202907041","doi":"https://doi.org/10.1109/tetc.2021.3115625","title":"SPACE: Finding Key-Speaker in Complex Multi-Person Scenes","display_name":"SPACE: Finding Key-Speaker in Complex Multi-Person Scenes","publication_year":2021,"publication_date":"2021-10-02","ids":{"openalex":"https://openalex.org/W3202907041","doi":"https://doi.org/10.1109/tetc.2021.3115625","mag":"3202907041"},"language":"en","primary_location":{"id":"doi:10.1109/tetc.2021.3115625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2021.3115625","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","raw_type":"journal-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/A5041479215","display_name":"Haoyu Zhao","orcid":"https://orcid.org/0000-0003-3832-6439"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Zhao","raw_affiliation_strings":["School of Information Engineering, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046155722","display_name":"Weidong Min","orcid":"https://orcid.org/0000-0003-2526-2181"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Min","raw_affiliation_strings":["School of Software, Nanchang University, Nanchang, China","Jiangxi Key Laboratory of Smart City, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]},{"raw_affiliation_string":"Jiangxi Key Laboratory of Smart City, Nanchang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101892617","display_name":"Jianqiang Xu","orcid":"https://orcid.org/0000-0002-4267-3639"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Xu","raw_affiliation_strings":["School of Information Engineering, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029896144","display_name":"Qing Han","orcid":null},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Han","raw_affiliation_strings":["School of Information Engineering, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642837","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-2948-805X"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Software, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101692199","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0003-0445-5603"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["School of Information Engineering, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019886356","display_name":"Ziyuan Yang","orcid":"https://orcid.org/0000-0002-0275-4098"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyuan Yang","raw_affiliation_strings":["School of Information Engineering, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006184401","display_name":"Linghua Zhou","orcid":"https://orcid.org/0000-0002-1536-1533"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghua Zhou","raw_affiliation_strings":["School of Information Engineering, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5041479215"],"corresponding_institution_ids":["https://openalex.org/I141649914"],"apc_list":null,"apc_paid":null,"fwci":0.7751,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7406327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":"3","first_page":"1645","last_page":"1656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983999729156494,"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":0.9965000152587891,"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":0.8557401895523071},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7691630125045776},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5624719858169556},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5204018354415894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5100744366645813},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4221588969230652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39209768176078796},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33534640073776245},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33132490515708923},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.12454256415367126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8557401895523071},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7691630125045776},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5624719858169556},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5204018354415894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5100744366645813},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4221588969230652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39209768176078796},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33534640073776245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33132490515708923},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.12454256415367126},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2021.3115625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2021.3115625","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1191276245","display_name":null,"funder_award_id":"62076117","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4034380999","display_name":null,"funder_award_id":"20161ACB20004","funder_id":"https://openalex.org/F4320322665","funder_display_name":"Natural Science Foundation of Jiangxi Province"},{"id":"https://openalex.org/G8102185992","display_name":null,"funder_award_id":"61762061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1906419545","https://openalex.org/W1964448421","https://openalex.org/W2015293542","https://openalex.org/W2029163572","https://openalex.org/W2033966334","https://openalex.org/W2040253108","https://openalex.org/W2064194796","https://openalex.org/W2067816745","https://openalex.org/W2081074144","https://openalex.org/W2085331248","https://openalex.org/W2114032116","https://openalex.org/W2118847468","https://openalex.org/W2123815913","https://openalex.org/W2135964285","https://openalex.org/W2137084491","https://openalex.org/W2144506857","https://openalex.org/W2147806277","https://openalex.org/W2411152591","https://openalex.org/W2466781280","https://openalex.org/W2515751428","https://openalex.org/W2550543432","https://openalex.org/W2559085405","https://openalex.org/W2606250917","https://openalex.org/W2749660340","https://openalex.org/W2754484231","https://openalex.org/W2759799350","https://openalex.org/W2768817490","https://openalex.org/W2781110478","https://openalex.org/W2788991015","https://openalex.org/W2798558457","https://openalex.org/W2798734012","https://openalex.org/W2810163051","https://openalex.org/W2962696180","https://openalex.org/W2963781481","https://openalex.org/W2963920562","https://openalex.org/W2986953233","https://openalex.org/W3003903817","https://openalex.org/W3015309989","https://openalex.org/W3034491120","https://openalex.org/W3100517161","https://openalex.org/W3104119587","https://openalex.org/W3105099157","https://openalex.org/W3119381934","https://openalex.org/W3121709906","https://openalex.org/W6637373629","https://openalex.org/W6675048546"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2161543916"],"abstract_inverted_index":{"Intelligent":[0],"image":[1,26],"processing":[2,27],"based":[3],"on":[4],"deep":[5],"learning":[6],"is":[7,15,52,98],"a":[8,62,161],"recently":[9],"emerging":[10],"artificial":[11],"Intelligence":[12],"method":[13,89,183],"which":[14],"critical":[16],"in":[17,39],"the":[18,31,35,76,86,143,150,154,181,186],"next":[19],"generation":[20],"computing":[21],"systems.":[22],"Key-speaker":[23],"detection":[24,46,65,159,188],"using":[25,105],"aims":[28],"to":[29,84,114,148,153,172],"find":[30,85,115,149],"speaker":[32,45],"who":[33],"plays":[34],"most":[36],"important":[37,118],"role":[38],"complex":[40],"multi-person":[41],"scenes.":[42],"However,":[43],"existing":[44,193],"methods":[47],"just":[48],"judge":[49],"whether":[50],"there":[51],"somebody":[53],"talking.":[54],"To":[55],"overcome":[56],"this":[57,59,146],"problem,":[58],"paper":[60],"proposes":[61],"novel":[63],"key-speaker":[64,158],"approach":[66,74],"named":[67],"Speaker":[68],"Pose-Attention":[69,125],"deteCtion":[70],"modEl":[71],"(SPACE).":[72],"This":[73],"extracts":[75],"space":[77],"information":[78],"and":[79,109,128,166],"analyze":[80],"people's":[81,135],"attention":[82,136],"gathering":[83],"key-speaker.":[87,151],"The":[88,95,120,132,138,176],"consists":[90,123],"of":[91,117,124,145,156],"two":[92],"main":[93],"parts.":[94],"first":[96],"part":[97,122],"our":[99],"proposed":[100,182],"Importance":[101],"Detection":[102],"Model":[103],"(IDM)":[104],"human":[106],"pose":[107],"estimation":[108],"an":[110],"effective":[111],"evaluation":[112],"strategy":[113],"candidates":[116],"speaker.":[119],"second":[121],"Graph":[126],"(PAG)":[127],"link":[129,139],"analysis":[130,140],"algorithm.":[131],"PAG":[133],"represents":[134],"graph.":[137],"algorithm":[141],"analyzes":[142],"connectivity":[144],"graph":[147],"Due":[152],"lack":[155],"available":[157],"datasets,":[160],"self-collected":[162],"dataset":[163],"containing":[164],"speech":[165],"meeting":[167],"scenes":[168],"has":[169],"been":[170],"built":[171],"estimate":[173],"SPACE":[174],"model.":[175],"experimental":[177],"results":[178],"show":[179],"that":[180],"can":[184],"obtain":[185],"best":[187],"accuracy":[189],"compared":[190],"with":[191],"other":[192],"methods.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}