{"id":"https://openalex.org/W4292387239","doi":"https://doi.org/10.1109/tmm.2022.3200282","title":"Self-Supervised Fine-Grained Cycle-Separation Network (FSCN) for Visual-Audio Separation","display_name":"Self-Supervised Fine-Grained Cycle-Separation Network (FSCN) for Visual-Audio Separation","publication_year":2022,"publication_date":"2022-08-19","ids":{"openalex":"https://openalex.org/W4292387239","doi":"https://doi.org/10.1109/tmm.2022.3200282"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3200282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3200282","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":["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/A5068950059","display_name":"Yanli Ji","orcid":"https://orcid.org/0000-0001-9122-6141"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanli Ji","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-9122-6141","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622671","display_name":"Shuo Ma","orcid":"https://orcid.org/0000-0002-8324-0506"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Ma","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-3123","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-2924-946X","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8484,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70521402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"25","issue":null,"first_page":"5864","last_page":"5876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9970999956130981,"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/spectrogram","display_name":"Spectrogram","score":0.9125598669052124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7926064729690552},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7376307249069214},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6906012296676636},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6460387706756592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5263082981109619},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5155208110809326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5057272911071777},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4891715347766876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4338662028312683},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.28416943550109863},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2474118173122406},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17469841241836548},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11533713340759277},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.0951647162437439}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9125598669052124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926064729690552},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7376307249069214},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6906012296676636},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6460387706756592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5263082981109619},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5155208110809326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5057272911071777},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4891715347766876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4338662028312683},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.28416943550109863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2474118173122406},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17469841241836548},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11533713340759277},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0951647162437439}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3200282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3200282","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1901129140","https://openalex.org/W1971168548","https://openalex.org/W1976178451","https://openalex.org/W2000761799","https://openalex.org/W2020107464","https://openalex.org/W2098950531","https://openalex.org/W2120847449","https://openalex.org/W2127851351","https://openalex.org/W2143169494","https://openalex.org/W2150415460","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2407685581","https://openalex.org/W2408744528","https://openalex.org/W2460742184","https://openalex.org/W2587994092","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2625041691","https://openalex.org/W2796992393","https://openalex.org/W2889380691","https://openalex.org/W2890052321","https://openalex.org/W2900292050","https://openalex.org/W2903268680","https://openalex.org/W2904140938","https://openalex.org/W2915658286","https://openalex.org/W2951237705","https://openalex.org/W2962856082","https://openalex.org/W2962865004","https://openalex.org/W2963082324","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963887950","https://openalex.org/W2964171275","https://openalex.org/W2969104083","https://openalex.org/W2969987364","https://openalex.org/W2972767900","https://openalex.org/W2981816492","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2988200020","https://openalex.org/W3015371781","https://openalex.org/W3017343282","https://openalex.org/W3023371261","https://openalex.org/W3024979138","https://openalex.org/W3096780661","https://openalex.org/W3105352633","https://openalex.org/W3108367559","https://openalex.org/W3118120400","https://openalex.org/W3118548710","https://openalex.org/W3121016465","https://openalex.org/W3135222947","https://openalex.org/W3169318522","https://openalex.org/W4288083516","https://openalex.org/W4289665794","https://openalex.org/W6639824700","https://openalex.org/W6714030504","https://openalex.org/W6750591037","https://openalex.org/W6752791795","https://openalex.org/W6783539077"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2898606530","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"abstract_inverted_index":{"Audio":[0],"mixture":[1,29],"separation":[2,43,54,87,108],"is":[3,55,65,83,102],"still":[4],"challenging":[5],"due":[6],"to":[7,40,85,104],"heavy":[8],"overlaps":[9],"and":[10,91,99,126,138,148],"interactions.":[11],"To":[12],"correctly":[13],"separate":[14],"audio":[15,28,45,74,100,144],"mixtures,":[16],"we":[17,35],"propose":[18],"a":[19,37,52,58,80],"novel":[20],"self-supervised":[21,42],"Fine-grained":[22],"Cycle-Separation":[23],"Network":[24],"(FCSN)":[25],"for":[26,142],"vision-guided":[27],"separation.":[30],"In":[31],"the":[32,62,72,77,92,106,110,135,140],"proposed":[33,84],"approach,":[34],"design":[36],"two-stage":[38],"procedure":[39],"perform":[41],"on":[44,119],"mixtures.":[46],"Using":[47],"visual":[48],"information":[49],"as":[50],"guidance,":[51],"primary-stage":[53],"realized":[56],"via":[57],"U-net":[59],"network,":[60],"then":[61],"residual":[63,93,111],"spectrogram":[64,112],"calculated":[66],"by":[67],"removing":[68],"separated":[69,89],"spectrograms":[70],"from":[71],"original":[73],"mixture.":[75],"At":[76],"second-stage":[78],"separation,":[79],"cycle-separation":[81],"module":[82],"refine":[86],"using":[88],"results":[90,129],"spectrogram.":[94],"Self-supervision":[95],"learning":[96],"between":[97],"vision":[98],"modalities":[101],"presented":[103],"push":[105],"cycle":[107],"until":[109],"becomes":[113],"empty.":[114],"Extensive":[115],"experiments":[116],"are":[117],"evaluated":[118],"three":[120],"large-scale":[121],"datasets,":[122],"MUSIC":[123],"(MUSIC-21),":[124],"AudioSet,":[125],"VGGSound.":[127],"Experiment":[128],"certify":[130],"that":[131],"our":[132],"approach":[133],"outperforms":[134],"state-of-the-art":[136],"approaches,":[137],"demonstrate":[139],"effectiveness":[141],"separating":[143],"mixtures":[145],"with":[146],"overlap":[147],"interaction.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}