{"id":"https://openalex.org/W3098984791","doi":"https://doi.org/10.1109/icassp39728.2021.9415065","title":"Audio-Visual Event Recognition Through the Lens of Adversary","display_name":"Audio-Visual Event Recognition Through the Lens of Adversary","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3098984791","doi":"https://doi.org/10.1109/icassp39728.2021.9415065","mag":"3098984791"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.07430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004697852","display_name":"Juncheng B Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juncheng B Li","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038055180","display_name":"Kaixin Ma","orcid":"https://orcid.org/0000-0001-7414-5673"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaixin Ma","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112694715","display_name":"Shuhui Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhui Qu","raw_affiliation_strings":["Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063149046","display_name":"Po-Yao Huang","orcid":"https://orcid.org/0000-0002-3319-5145"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Yao Huang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4606571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"616","last_page":"620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/adversarial-system","display_name":"Adversarial system","score":0.8147531747817993},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7997374534606934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7591390609741211},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.6192979216575623},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5770792365074158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5401351451873779},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47482141852378845},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47453534603118896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4031074047088623},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38222476840019226},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1273839771747589},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08081173896789551}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8147531747817993},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7997374534606934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591390609741211},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.6192979216575623},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5770792365074158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401351451873779},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47482141852378845},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47453534603118896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4031074047088623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38222476840019226},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1273839771747589},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08081173896789551},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.07430","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07430","pdf_url":"https://arxiv.org/pdf/2011.07430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},{"id":"mag:3098984791","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.07430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.07430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.07430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/djgp-zj39","is_oa":true,"landing_page_url":"https://doi.org/10.17023/djgp-zj39","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.07430","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07430","pdf_url":"https://arxiv.org/pdf/2011.07430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3098984791.pdf","grobid_xml":"https://content.openalex.org/works/W3098984791.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2676925568","https://openalex.org/W2791956393","https://openalex.org/W2808084195","https://openalex.org/W2936774411","https://openalex.org/W2942630857","https://openalex.org/W2947356958","https://openalex.org/W2963022469","https://openalex.org/W2963155035","https://openalex.org/W2963403868","https://openalex.org/W2963610932","https://openalex.org/W2963723765","https://openalex.org/W2964891022","https://openalex.org/W2972678295","https://openalex.org/W2973109987","https://openalex.org/W2980037812","https://openalex.org/W2984287396","https://openalex.org/W2986277087","https://openalex.org/W2990408345","https://openalex.org/W2994728585","https://openalex.org/W2995242814","https://openalex.org/W3016195076","https://openalex.org/W3027013152","https://openalex.org/W3091896612","https://openalex.org/W6739901393","https://openalex.org/W6749158954","https://openalex.org/W6761839128","https://openalex.org/W6763597408","https://openalex.org/W6767269270","https://openalex.org/W6770805772","https://openalex.org/W6771438384","https://openalex.org/W6884739491"],"related_works":["https://openalex.org/W3162819547","https://openalex.org/W3164364099","https://openalex.org/W3022473380","https://openalex.org/W3022223508","https://openalex.org/W2963638211","https://openalex.org/W2972362166","https://openalex.org/W2998243512","https://openalex.org/W2892852825","https://openalex.org/W3165385275","https://openalex.org/W2884614645","https://openalex.org/W3048753943","https://openalex.org/W2924785549","https://openalex.org/W2997093650","https://openalex.org/W3022151098","https://openalex.org/W2963208512","https://openalex.org/W2901958720","https://openalex.org/W2957199652","https://openalex.org/W3080490018","https://openalex.org/W3042380503","https://openalex.org/W2759471388"],"abstract_inverted_index":{"As":[0],"audio/visual":[1],"classification":[2],"models":[3,89],"are":[4,125],"widely":[5],"deployed":[6],"for":[7],"sensitive":[8],"tasks":[9],"like":[10],"content":[11],"filtering":[12],"at":[13],"scale,":[14],"it":[15],"is":[16,132],"critical":[17],"to":[18,30,36,64,85,112,120,127,138,161],"understand":[19],"their":[20],"robustness":[21,53,144],"along":[22],"with":[23],"improving":[24],"the":[25,40,65,75,114,133,140,148,152],"accuracy.":[26],"This":[27],"work":[28],"aims":[29],"study":[31],"several":[32],"key":[33],"questions":[34],"related":[35],"multimodal":[37,122],"learning":[38],"through":[39],"lens":[41],"of":[42,101,104],"adversarial":[43,76,83,102,118],"noises:":[44],"1)":[45],"The":[46],"trade-off":[47],"between":[48],"early/middle/late":[49],"fusion":[50,136],"affecting":[51],"its":[52],"and":[54,143,146],"accuracy":[55],"2)":[56],"How":[57,68],"does":[58,69],"different":[59,70,107],"frequency/time":[60],"domain":[61],"features":[62,150,154],"contribute":[63,73],"robustness?":[66],"3)":[67],"neural":[71,88,157],"modules":[72],"against":[74],"noise?":[77],"In":[78],"our":[79],"experiment,":[80],"we":[81,109,124],"construct":[82],"examples":[84],"attack":[86,97],"state-of-the-art":[87],"trained":[90],"on":[91],"Google":[92],"AudioSet.[1]1We":[93],"compare":[94],"how":[95],"much":[96],"potency":[98],"in":[99],"terms":[100],"perturbation":[103],"size":[105],"using":[106],"Lpnorms":[108],"would":[110],"need":[111],"\"deactivate\"":[113],"victim":[115],"model.":[116],"Using":[117],"noise":[119],"ablate":[121],"models,":[123],"able":[126],"provide":[128],"insights":[129],"into":[130],"what":[131],"best":[134],"potential":[135],"strategy":[137],"balance":[139],"model":[141,159],"parameters/accuracy":[142],"trade-off,":[145],"distinguish":[147],"robust":[149],"versus":[151],"non-robust":[153],"that":[155],"various":[156],"networks":[158],"tend":[160],"learn.":[162]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}