{"id":"https://openalex.org/W4401169079","doi":"https://doi.org/10.1145/3674225.3674394","title":"Semi-AVS: Segmenting the Sounding Objects via Semi-supervised Learning","display_name":"Semi-AVS: Segmenting the Sounding Objects via Semi-supervised Learning","publication_year":2024,"publication_date":"2024-01-19","ids":{"openalex":"https://openalex.org/W4401169079","doi":"https://doi.org/10.1145/3674225.3674394"},"language":"en","primary_location":{"id":"doi:10.1145/3674225.3674394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674225.3674394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Power Electronics and Artificial Intelligence","raw_type":"proceedings-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":null,"display_name":"Chengcheng Li","orcid":"https://orcid.org/0009-0005-2324-3392"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengcheng Li","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, China"],"raw_orcid":"https://orcid.org/0009-0005-2324-3392","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057821256","display_name":"Zhengyi Liu","orcid":"https://orcid.org/0000-0003-3265-823X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyi Liu","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, China"],"raw_orcid":"https://orcid.org/0000-0003-3265-823X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112260820","display_name":"Wei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, China"],"raw_orcid":"https://orcid.org/0009-0004-1799-5443","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12373429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"939","last_page":"943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.9966999888420105,"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/depth-sounding","display_name":"Depth sounding","score":0.7751601934432983},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.7015067934989929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.697945773601532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6068584322929382},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4343807101249695},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4036423861980438},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.12095114588737488},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10217699408531189},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09166666865348816},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.06934869289398193}],"concepts":[{"id":"https://openalex.org/C55510283","wikidata":"https://www.wikidata.org/wiki/Q1382947","display_name":"Depth sounding","level":2,"score":0.7751601934432983},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.7015067934989929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697945773601532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068584322929382},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4343807101249695},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4036423861980438},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.12095114588737488},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10217699408531189},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09166666865348816},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.06934869289398193}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674225.3674394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674225.3674394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Power Electronics and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W3080686309","https://openalex.org/W3153906112","https://openalex.org/W3168916176","https://openalex.org/W3170088426","https://openalex.org/W3170264469","https://openalex.org/W3170630188","https://openalex.org/W3175515048","https://openalex.org/W3211993051","https://openalex.org/W3212022073","https://openalex.org/W4287684771","https://openalex.org/W4298326857","https://openalex.org/W4312815172","https://openalex.org/W4368754857","https://openalex.org/W4390874575","https://openalex.org/W4403386295","https://openalex.org/W6780718818","https://openalex.org/W6840058269","https://openalex.org/W6849149200"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2592395359","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Audio-visual":[0],"segmentation":[1,67],"(AVS)":[2],"is":[3,43,54,100,137],"a":[4,25,57,64,88,91],"complex":[5],"task":[6,125],"that":[7],"involves":[8],"accurately":[9],"segmenting":[10],"the":[11,15,21,33,47,73,76,80,85,107,114,117,127],"sounding":[12],"objects":[13],"from":[14],"visual":[16,30,108,118],"frames.":[17],"Existing":[18],"method":[19,121],"introduces":[20],"audio":[22,111,115],"semantics":[23],"and":[24,36,112,144],"regularization":[26],"loss":[27],"for":[28],"guiding":[29],"segmentation.":[31],"However,":[32],"one-shot":[34],"annotation":[35],"full-shot":[37],"prediction":[38],"fact":[39],"in":[40,56,87,106,122,140],"single-source":[41,123],"dataset":[42],"discarded":[44],"(i.e.,":[45],"only":[46],"ground":[48],"truth":[49],"of":[50,75],"first":[51,77],"sampled":[52],"frame":[53,78,109],"given":[55],"video).":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"propose":[63],"semi-supervised":[65,131],"audio-visual":[66,97,134],"framework":[68],"called":[69],"Semi-AVS,":[70],"to":[71,79,102],"propagate":[72],"mask":[74],"later":[81],"frames":[82,86],"since":[83],"all":[84],"video":[89],"share":[90],"same":[92],"sound":[93],"source.":[94],"Furthermore,":[95],"an":[96],"interaction":[98,135],"module":[99,136],"designed":[101],"both":[103],"locate":[104],"object":[105],"via":[110],"make":[113],"percept":[116],"context.":[119],"Our":[120],"AVS":[124,146],"outperforms":[126],"state-of-the-art":[128],"models":[129],"by":[130],"learning.":[132],"Meanwhile":[133],"also":[138],"verified":[139],"fully":[141],"supervised":[142],"multi-source":[143],"semantic":[145],"tasks.":[147]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}