{"id":"https://openalex.org/W3090229599","doi":"https://doi.org/10.1109/icra40945.2020.9197566","title":"Self-Supervised Learning for Alignment of Objects and Sound","display_name":"Self-Supervised Learning for Alignment of Objects and Sound","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3090229599","doi":"https://doi.org/10.1109/icra40945.2020.9197566","mag":"3090229599"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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":"https://openalex.org/A5101470788","display_name":"Xinzhu Liu","orcid":"https://orcid.org/0000-0002-6447-2926"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinzhu Liu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455486","display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0000-0001-7854-4866"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Liu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833400","display_name":"Di Guo","orcid":"https://orcid.org/0000-0002-9816-0103"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Guo","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076806162","display_name":"Haibo Min","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Min","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101470788"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.54496379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1588","last_page":"1594"},"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":0.9991999864578247,"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":0.9962000250816345,"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":0.7696232795715332},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.702094554901123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6819288730621338},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6338872909545898},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6264320015907288},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.612576961517334},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5540056228637695},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5520511269569397},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5508357882499695},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5117533206939697},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.49914097785949707},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4255024194717407},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4175565242767334},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4054883122444153},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3106606900691986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2204538881778717},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09862574934959412},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09145405888557434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696232795715332},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.702094554901123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819288730621338},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6338872909545898},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6264320015907288},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.612576961517334},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5540056228637695},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5520511269569397},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5508357882499695},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5117533206939697},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.49914097785949707},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4255024194717407},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4175565242767334},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4054883122444153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3106606900691986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2204538881778717},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09862574934959412},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09145405888557434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W186036538","https://openalex.org/W639708223","https://openalex.org/W1560213421","https://openalex.org/W1901129140","https://openalex.org/W1971168548","https://openalex.org/W1983306266","https://openalex.org/W1991139021","https://openalex.org/W2106016262","https://openalex.org/W2127851351","https://openalex.org/W2144282867","https://openalex.org/W2150415460","https://openalex.org/W2221409856","https://openalex.org/W2271701291","https://openalex.org/W2413091727","https://openalex.org/W2460742184","https://openalex.org/W2561787614","https://openalex.org/W2566088759","https://openalex.org/W2593116425","https://openalex.org/W2613718673","https://openalex.org/W2660943524","https://openalex.org/W2772736377","https://openalex.org/W2901937360","https://openalex.org/W2962699416","https://openalex.org/W2962865004","https://openalex.org/W2962866211","https://openalex.org/W2962960500","https://openalex.org/W2963218389","https://openalex.org/W2964171275","https://openalex.org/W2965559681","https://openalex.org/W2966917182","https://openalex.org/W2968054085","https://openalex.org/W2988200020","https://openalex.org/W3007098864","https://openalex.org/W3105684258","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6607619696","https://openalex.org/W6620707391","https://openalex.org/W6750591037"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W1508899372","https://openalex.org/W2077498359","https://openalex.org/W1608003482","https://openalex.org/W2903040254","https://openalex.org/W2074134755","https://openalex.org/W4226449293","https://openalex.org/W2129566906","https://openalex.org/W2117408192"],"abstract_inverted_index":{"The":[0],"sound":[1,43,59,79,108],"source":[2,44],"separation":[3,45,60],"problem":[4],"has":[5],"many":[6],"useful":[7],"applications":[8],"in":[9,102],"the":[10,42,55,71,74,86,96,99,103],"field":[11],"of":[12,38,98,105],"robotics,":[13],"such":[14],"as":[15],"human-robot":[16],"interaction,":[17],"scene":[18],"understanding,":[19],"etc.":[20],"However,":[21],"it":[22],"remains":[23],"a":[24],"very":[25],"challenging":[26],"problem.":[27],"In":[28],"this":[29,92],"paper,":[30],"we":[31],"utilize":[32],"both":[33,85],"visual":[34],"and":[35,58,77,88,94,107],"audio":[36],"information":[37],"videos":[39],"to":[40,53,68],"perform":[41],"task.":[46],"A":[47],"self-supervised":[48],"learning":[49],"framework":[50],"is":[51,66],"proposed":[52,100],"implement":[54],"object":[56,106],"detection":[57],"modules":[61],"simultaneously.":[62],"Such":[63],"an":[64],"approach":[65,93],"designed":[67],"better":[69],"find":[70],"alignment":[72],"between":[73],"detected":[75],"objects":[76],"separated":[78],"components.":[80],"Our":[81],"experiments,":[82],"conducted":[83],"on":[84],"synthetic":[87],"real":[89],"datasets,":[90],"validate":[91],"demonstrate":[95],"effectiveness":[97],"model":[101],"task":[104],"alignment.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
