{"id":"https://openalex.org/W7108645570","doi":"https://doi.org/10.5281/zenodo.17811491","title":"Joint Object Detection and Sound Source Separation","display_name":"Joint Object Detection and Sound Source Separation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108645570","doi":"https://doi.org/10.5281/zenodo.17811491"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811491","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811491","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811491","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sunyoo Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunyoo Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yunjeong Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunjeong Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Doyeon Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doyeon Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Seoyoung Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seoyoung Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Eunyi Lyou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunyi Lyou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Seungju Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seungju Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Junhyug Noh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhyug Noh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Joonseok Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joonseok Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9889000058174133,"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":0.9889000058174133,"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":0.005100000184029341,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0008999999845400453,"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/joint","display_name":"Joint (building)","score":0.7775999903678894},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7753999829292297},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6545000076293945},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6535000205039978},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6362000107765198},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5648999810218811},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5555999875068665},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42559999227523804}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7775999903678894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771999835968018},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7753999829292297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6690999865531921},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6545000076293945},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6535000205039978},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5440999865531921},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42559999227523804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.3361000120639801},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C3018256011","wikidata":"https://www.wikidata.org/wiki/Q898987","display_name":"Separation method","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.25360000133514404},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811491","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811491","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811491","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811491","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,67,86],"propose":[1,68],"See2Hear":[2],"(S2H),":[3],"a":[4,69],"framework":[5],"that":[6,73,92,118],"jointly":[7],"learns":[8],"audio-visual":[9],"representations":[10],"for":[11,129],"object":[12,76,80,112],"detection":[13,30,113,123],"and":[14,31,106,124],"sound":[15],"source":[16,101],"separation":[17,32,102,125],"from":[18,78],"videos.":[19],"Existing":[20],"methods":[21],"do":[22],"not":[23],"fully":[24],"exploit":[25],"the":[26,29,79,96,104,119],"synergy":[27],"between":[28],"tasks,":[33],"often":[34],"relying":[35],"on":[36,103],"disjointly":[37],"pre-trained":[38],"visual":[39],"encoders.":[40],"In":[41],"this":[42,84],"paper,":[43],"S2H":[44],"integrates":[45],"both":[46,130],"tasks":[47],"in":[48,64,99],"an":[49],"end-to-end":[50],"trainable":[51],"unified":[52],"structure":[53],"using":[54],"transformer-based":[55],"architectures.":[56],"A":[57],"naive":[58],"combination":[59],"of":[60,122],"them,":[61],"however,":[62],"results":[63],"suboptimal":[65],"performance.":[66,114],"dynamic":[70],"filtering":[71],"mechanism":[72],"selects":[74],"relevant":[75],"queries":[77],"detector":[81],"to":[82,90],"resolve":[83],"issue.":[85],"conduct":[87],"extensive":[88],"experiments":[89],"verify":[91],"our":[93],"approach":[94],"achieves":[95],"state-of-the-art":[97],"performance":[98],"audio":[100],"MUSIC":[105],"MUSIC-21":[107],"datasets,":[108],"while":[109],"maintaining":[110],"competitive":[111],"Ablation":[115],"studies":[116],"confirm":[117],"joint":[120],"training":[121],"is":[126],"mutually":[127],"beneficial":[128],"tasks.":[131]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-12-05T00:00:00"}