{"id":"https://openalex.org/W4313123347","doi":"https://doi.org/10.1007/978-3-031-19836-6_22","title":"Audio\u2013Visual Segmentation","display_name":"Audio\u2013Visual Segmentation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4313123347","doi":"https://doi.org/10.1007/978-3-031-19836-6_22"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-19836-6_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-19836-6_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5047303316","display_name":"Jinxing Zhou","orcid":"https://orcid.org/0000-0001-6402-7593"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxing Zhou","raw_affiliation_strings":["Hefei University of Technology, Hefei, China","SenseTime Research, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"SenseTime Research, Hangzhou, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021424","display_name":"Jianyuan Wang","orcid":"https://orcid.org/0000-0002-6467-4018"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Jianyuan Wang","raw_affiliation_strings":["Australian National University, Canberra, Australia","SenseTime Research, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"SenseTime Research, Hangzhou, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612301","display_name":"Jiayi Zhang","orcid":"https://orcid.org/0000-0003-2434-4329"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Jiayi Zhang","raw_affiliation_strings":["Australian National University, Canberra, Australia","Beihang University, Beijing, China","SenseTime Research, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"SenseTime Research, Hangzhou, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079927298","display_name":"Weixuan Sun","orcid":"https://orcid.org/0000-0002-5409-1097"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Weixuan Sun","raw_affiliation_strings":["Australian National University, Canberra, Australia","SenseTime Research, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"SenseTime Research, Hangzhou, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630815","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-8516-0913"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Australian National University, Canberra, Australia","Beihang University, Beijing, China","SenseTime Research, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"SenseTime Research, Hangzhou, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040617006","display_name":"Stan Birchfield","orcid":"https://orcid.org/0000-0001-7366-2441"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stan Birchfield","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014554970","display_name":"Lingpeng Kong","orcid":"https://orcid.org/0000-0002-9033-2724"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Lingpeng Kong","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China","The University of Hong Kong, Pok Fu Lam, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066621365","display_name":"Yiran Zhong","orcid":"https://orcid.org/0000-0003-1404-3610"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiran Zhong","raw_affiliation_strings":["SenseTime Research, Hangzhou, China","Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hangzhou, China","institution_ids":["https://openalex.org/I4210128910"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":122,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"386","last_page":"403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8896637558937073},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7064875364303589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.692497968673706},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6373132467269897},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.611272931098938},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5400198101997375},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5060967803001404},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4971647560596466},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4547649025917053},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45364853739738464},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09307345747947693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8896637558937073},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7064875364303589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.692497968673706},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6373132467269897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.611272931098938},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5400198101997375},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5060967803001404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4971647560596466},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4547649025917053},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45364853739738464},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09307345747947693},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-19836-6_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-19836-6_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1981276685","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2412782625","https://openalex.org/W2422305492","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2910628332","https://openalex.org/W2931433835","https://openalex.org/W2962699416","https://openalex.org/W2962858109","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963091558","https://openalex.org/W2963115079","https://openalex.org/W2963150697","https://openalex.org/W2963218389","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2988200020","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3015371781","https://openalex.org/W3015925607","https://openalex.org/W3021321555","https://openalex.org/W3048939150","https://openalex.org/W3092603041","https://openalex.org/W3093287838","https://openalex.org/W3099638501","https://openalex.org/W3108367559","https://openalex.org/W3110606395","https://openalex.org/W3116298410","https://openalex.org/W3118120400","https://openalex.org/W3118366136","https://openalex.org/W3138516171","https://openalex.org/W3170088426","https://openalex.org/W3170630188","https://openalex.org/W3175335326","https://openalex.org/W3175514052","https://openalex.org/W3175515048","https://openalex.org/W4226206782","https://openalex.org/W4310895557","https://openalex.org/W6604044515","https://openalex.org/W6634721143"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2271369634","https://openalex.org/W2130974462","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W2028665553","https://openalex.org/W2086519370"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}