{"id":"https://openalex.org/W4225296419","doi":"https://doi.org/10.1109/icassp43922.2022.9747641","title":"Mixed In Time And Modality: Curse Or Blessing\u0192 Cross-Instance Data Augmentation for Weakly Supervised Multimodal Temporal Fusion","display_name":"Mixed In Time And Modality: Curse Or Blessing\u0192 Cross-Instance Data Augmentation for Weakly Supervised Multimodal Temporal Fusion","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225296419","doi":"https://doi.org/10.1109/icassp43922.2022.9747641"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747641","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100311855","display_name":"Yonggang Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yonggang Zhu","raw_affiliation_strings":["Beijing University of Posts and Communications","Peking University"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Communications","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675045","display_name":"Chao Tian","orcid":"https://orcid.org/0000-0001-8752-6141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Tian","raw_affiliation_strings":["China Xi’an Satellite Control Center"],"affiliations":[{"raw_affiliation_string":"China Xi’an Satellite Control Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002774811","display_name":"Zhuqing Jiang","orcid":"https://orcid.org/0000-0001-6308-5708"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuqing Jiang","raw_affiliation_strings":["Beijing University of Posts and Communications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Communications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029278873","display_name":"Aidong Men","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aidong Men","raw_affiliation_strings":["Beijing University of Posts and Communications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Communications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379058","display_name":"Haiying Wang","orcid":"https://orcid.org/0000-0001-8358-9065"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiying Wang","raw_affiliation_strings":["Beijing University of Posts and Communications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Communications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069484115","display_name":"Qing-Chao Chen","orcid":"https://orcid.org/0000-0002-1216-5609"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingchao Chen","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100311855"],"corresponding_institution_ids":["https://openalex.org/I139759216","https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.2452,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.34913112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4538","last_page":"4542"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9876000285148621,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9825000166893005,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/blessing","display_name":"Blessing","score":0.7624826431274414},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6822116374969482},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.6452475786209106},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6316242218017578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5790078043937683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.573415994644165},{"id":"https://openalex.org/keywords/curse","display_name":"Curse","score":0.5231465101242065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3820948600769043},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08823558688163757},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07212027907371521}],"concepts":[{"id":"https://openalex.org/C2776195157","wikidata":"https://www.wikidata.org/wiki/Q626510","display_name":"Blessing","level":2,"score":0.7624826431274414},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6822116374969482},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.6452475786209106},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6316242218017578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5790078043937683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.573415994644165},{"id":"https://openalex.org/C2780273121","wikidata":"https://www.wikidata.org/wiki/Q109411","display_name":"Curse","level":2,"score":0.5231465101242065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3820948600769043},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08823558688163757},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07212027907371521},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747641","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2248498780","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2890052321","https://openalex.org/W2931433835","https://openalex.org/W2939574508","https://openalex.org/W2963610932","https://openalex.org/W2964109005","https://openalex.org/W2981905048","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3002552512","https://openalex.org/W3015371781","https://openalex.org/W3015925607","https://openalex.org/W3021321555","https://openalex.org/W3031418291","https://openalex.org/W3093287838","https://openalex.org/W3108367559","https://openalex.org/W3110606395","https://openalex.org/W3118120400","https://openalex.org/W3175514052","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6749633790","https://openalex.org/W6754048563","https://openalex.org/W6773226109","https://openalex.org/W6780746695","https://openalex.org/W6786949882"],"related_works":["https://openalex.org/W2005044196","https://openalex.org/W2313412377","https://openalex.org/W1485007142","https://openalex.org/W3133282625","https://openalex.org/W2314038984","https://openalex.org/W1911503363","https://openalex.org/W3165692504","https://openalex.org/W3180421702","https://openalex.org/W2313993255","https://openalex.org/W2413520594"],"abstract_inverted_index":{"In":[0],"multimodal":[1],"video":[2,82],"event":[3],"localization,":[4,46],"we":[5,37],"usually":[6],"leverage":[7],"feature":[8,41,98,105],"fusion":[9,42,99],"across":[10],"different":[11],"axes,":[12,19],"such":[13],"as":[14],"the":[15,25,61,80,95],"modality":[16],"and":[17,64,86,127],"temporal":[18],"for":[20,104],"better":[21],"context.":[22],"To":[23],"reduce":[24],"costs":[26],"of":[27,97,115],"detailed":[28],"annotations,":[29],"recent":[30],"solutions":[31],"explore":[32],"weakly":[33,44,120],"supervised":[34,45,68,121],"settings.":[35],"However,":[36],"observe":[38],"that":[39,109],"when":[40],"meets":[43],"problems":[47],"can":[48,93,112],"occur.":[49],"It":[50],"may":[51],"cause":[52],"\"feature":[53],"cross-interference\",":[54],"which":[55,92],"produces":[56],"a":[57,88],"smearing":[58],"effect":[59],"on":[60,79,118],"localization":[62,123],"result":[63],"can\u2019t":[65],"be":[66],"effectively":[67],"with":[69],"conventional":[70],"multiple":[71],"instance":[72],"learning":[73],"loss.":[74],"We":[75,107],"verify":[76],"it":[77],"quantitatively":[78],"audio-visual":[81,122],"parsing":[83],"(AVVP)":[84],"task,":[85],"propose":[87],"cross-instance":[89],"data-augmentation":[90],"framework,":[91],"preserve":[94],"benefits":[96],"while":[100],"providing":[101],"explicit":[102],"feedbacks":[103],"cross-interference.":[106],"show":[108],"our":[110],"method":[111],"enhance":[113],"performance":[114],"existing":[116],"models":[117],"two":[119],"tasks,":[124],"i.e.":[125],"AVVP":[126],"AVE.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}