{"id":"https://openalex.org/W4283709432","doi":"https://doi.org/10.1145/3503161.3548317","title":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation","display_name":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4283709432","doi":"https://doi.org/10.1145/3503161.3548317"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548317","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.12772","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101682289","display_name":"Jinxiang Liu","orcid":"https://orcid.org/0000-0003-2583-8881"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxiang Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089564180","display_name":"Jin Chen","orcid":"https://orcid.org/0000-0002-6497-4141"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Ju","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076097168","display_name":"Weidi Xie","orcid":"https://orcid.org/0000-0003-3804-2639"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100342828","display_name":"Ya Zhang","orcid":"https://orcid.org/0000-0002-5390-9053"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3742","last_page":"3753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.7344713807106018},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.705895721912384},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6924033164978027},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4956454038619995},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4910917282104492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48480024933815},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48331332206726074},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4713325500488281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3851749897003174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.329551637172699},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1692374050617218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344713807106018},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.705895721912384},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6924033164978027},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4956454038619995},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4910917282104492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48480024933815},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48331332206726074},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4713325500488281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3851749897003174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.329551637172699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1692374050617218},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548317","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.12772","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.12772","pdf_url":"https://arxiv.org/pdf/2206.12772","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.12772","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.12772","pdf_url":"https://arxiv.org/pdf/2206.12772","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W2106488367","https://openalex.org/W2145287260","https://openalex.org/W2164899449","https://openalex.org/W2295107390","https://openalex.org/W2470394683","https://openalex.org/W2796992393","https://openalex.org/W2799265169","https://openalex.org/W2890052321","https://openalex.org/W2931433835","https://openalex.org/W2936774411","https://openalex.org/W2962865004","https://openalex.org/W2962887041","https://openalex.org/W2962960500","https://openalex.org/W2962981304","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963680395","https://openalex.org/W2963775347","https://openalex.org/W2964015640","https://openalex.org/W2971680695","https://openalex.org/W2981816492","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2986131686","https://openalex.org/W2987936369","https://openalex.org/W2988200020","https://openalex.org/W3002552512","https://openalex.org/W3005680577","https://openalex.org/W3015371781","https://openalex.org/W3017343282","https://openalex.org/W3034658206","https://openalex.org/W3034930876","https://openalex.org/W3035060554","https://openalex.org/W3035333188","https://openalex.org/W3035524453","https://openalex.org/W3091905774","https://openalex.org/W3092603041","https://openalex.org/W3096431533","https://openalex.org/W3105352633","https://openalex.org/W3108367559","https://openalex.org/W3115772142","https://openalex.org/W3116298410","https://openalex.org/W3118120400","https://openalex.org/W3130662682","https://openalex.org/W3159481202","https://openalex.org/W3170088426","https://openalex.org/W3171007011","https://openalex.org/W3182657421","https://openalex.org/W4200436929","https://openalex.org/W4212774754","https://openalex.org/W4221161766","https://openalex.org/W4224925617","https://openalex.org/W4286421014","https://openalex.org/W4287373141","https://openalex.org/W4287392530","https://openalex.org/W4287592659","https://openalex.org/W4293665662","https://openalex.org/W4297808394","https://openalex.org/W4303467932","https://openalex.org/W4310255405","https://openalex.org/W4313056800","https://openalex.org/W6601630192"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W1983331834"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,44],"simple":[3],"yet":[4],"effective":[5],"self-supervised":[6,122],"framework":[7,141],"for":[8],"audio-visual":[9,51],"representation":[10],"learning,":[11],"to":[12,23,53,56,149,154],"localize":[13],"the":[14,30,50,67,73,79,131,139],"sound":[15,75,101,150],"source":[16,76],"in":[17,134],"videos.":[18],"To":[19],"understand":[20],"what":[21],"enables":[22],"learn":[24],"useful":[25],"representations,":[26,71],"we":[27,109],"systematically":[28],"investigate":[29],"effects":[31],"of":[32,40,69],"data":[33,41],"augmentations,":[34],"and":[35,106,114,152],"reveal":[36],"that":[37,92,146],"(1)":[38],"composition":[39],"augmentations":[42],"plays":[43],"critical":[45],"role,":[46],"i.e.":[47,72],"explicitly":[48],"encouraging":[49],"representations":[52,145],"be":[54],"invariant":[55],"various":[57],"transformations":[58],"(transformation":[59,87],"invariance);":[60],"(2)":[61],"enforcing":[62],"geometric":[63],"consistency":[64],"substantially":[65],"improves":[66],"quality":[68],"learned":[70],"detected":[74],"should":[77],"follow":[78],"same":[80],"transformation":[81],"applied":[82],"on":[83,99],"input":[84],"video":[85],"frames":[86],"equivariance).":[88],"Extensive":[89],"experiments":[90],"demonstrate":[91,124],"our":[93,121],"model":[94],"significantly":[95],"outperforms":[96],"previous":[97],"methods":[98],"two":[100],"localization":[102],"benchmarks,":[103],"namely,":[104],"Flickr-SoundNet":[105],"VGG-Sound.":[107],"Additionally,":[108],"also":[110],"evaluate":[111],"audio":[112,135],"retrieval":[113,116,126],"cross-modal":[115],"tasks.":[117],"In":[118],"both":[119],"cases,":[120],"models":[123],"superior":[125],"performances,":[127],"even":[128],"competitive":[129],"with":[130],"supervised":[132],"approach":[133],"retrieval.":[136],"This":[137],"reveals":[138],"proposed":[140],"learns":[142],"strong":[143],"multi-modal":[144],"are":[147],"beneficial":[148],"localisation":[151],"generalization":[153],"further":[155],"applications.":[156],"The":[157],"project":[158],"page":[159],"is":[160],"https://jinxiang-liu.github.io/SSL-TIE.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-06-30T00:00:00"}