{"id":"https://openalex.org/W4226206782","doi":"https://doi.org/10.1145/3503161.3547869","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","display_name":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4226206782","doi":"https://doi.org/10.1145/3503161.3547869"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547869","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":["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/A5052798964","display_name":"Jiashuo Yu","orcid":"https://orcid.org/0000-0002-3094-6687"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashuo Yu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060790908","display_name":"Ying Cheng","orcid":"https://orcid.org/0000-0002-9103-6126"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Cheng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626035","display_name":"Rui-Wei Zhao","orcid":"https://orcid.org/0000-0002-8498-5761"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui-Wei Zhao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860531","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-6648-953X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6241","last_page":"6249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.996999979019165,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8184069395065308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7002952694892883},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6844180822372437},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6383323669433594},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5768744349479675},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5660295486450195},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5281969308853149},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.515173077583313},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3721049427986145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184069395065308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7002952694892883},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6844180822372437},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6383323669433594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5768744349479675},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5660295486450195},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5281969308853149},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.515173077583313},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3721049427986145},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547869","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3227695070","display_name":null,"funder_award_id":"No. 62172101, No. 61976057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6158060843","display_name":null,"funder_award_id":"No. 21511101000, No. 21511100602","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2146958953","https://openalex.org/W2183341477","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2736596806","https://openalex.org/W2962709777","https://openalex.org/W2962865004","https://openalex.org/W2962907723","https://openalex.org/W2962960500","https://openalex.org/W2963022469","https://openalex.org/W2963155035","https://openalex.org/W2963610932","https://openalex.org/W2964109005","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3015925607","https://openalex.org/W3021321555","https://openalex.org/W3035413240","https://openalex.org/W3048939150","https://openalex.org/W3099638501","https://openalex.org/W3118120400","https://openalex.org/W3175335326","https://openalex.org/W3175514052"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W4249847449","https://openalex.org/W2142145894","https://openalex.org/W2952780262","https://openalex.org/W4206776094","https://openalex.org/W3150439626","https://openalex.org/W3154920669","https://openalex.org/W3121197456","https://openalex.org/W2060887160","https://openalex.org/W2368367751"],"abstract_inverted_index":{"Recognizing":[0],"and":[1,19,108,126,142],"localizing":[2],"events":[3,14,59],"in":[4,17,60],"videos":[5,37],"is":[6,25,101],"a":[7,39,68,104,122,127],"fundamental":[8],"task":[9],"for":[10,27,75],"video":[11,145],"understanding.":[12],"Since":[13],"may":[15],"occur":[16],"auditory":[18],"visual":[20],"modalities,":[21],"multimodal":[22],"detailed":[23],"perception":[24],"essential":[26],"complete":[28],"scene":[29],"comprehension.":[30],"Most":[31],"previous":[32],"works":[33],"attempted":[34],"to":[35,57,131],"analyze":[36],"from":[38],"holistic":[40],"perspective.":[41],"However,":[42],"they":[43],"do":[44],"not":[45],"consider":[46],"semantic":[47,117],"information":[48],"at":[49],"multiple":[50],"scales,":[51],"which":[52,120],"makes":[53],"the":[54,82,149],"model":[55],"difficult":[56],"localize":[58],"different":[61],"lengths.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,79],"present":[67],"Multimodal":[69],"Pyramid":[70],"Attentional":[71],"Network":[72],"(MM-Pyramid":[73],")":[74],"event":[76,140],"localization.":[77],"Specifically,":[78],"first":[80],"propose":[81],"attentive":[83],"feature":[84],"pyramid":[85,91,96,133],"module.":[86],"This":[87],"module":[88],"captures":[89],"temporal":[90],"features":[92,134],"via":[93],"several":[94],"stacking":[95],"units,":[97],"each":[98],"of":[99,103,151],"them":[100],"composed":[102],"fixed-size":[105],"attention":[106,124],"block":[107,125,130],"dilated":[109],"convolution":[110],"block.":[111],"We":[112],"also":[113],"design":[114],"an":[115],"adaptive":[116],"fusion":[118,129],"module,":[119],"leverages":[121],"unit-level":[123],"selective":[128],"integrate":[132],"interactively.":[135],"Extensive":[136],"experiments":[137],"on":[138],"audio-visual":[139,144],"localization":[141],"weakly-supervised":[143],"parsing":[146],"tasks":[147],"verify":[148],"effectiveness":[150],"our":[152],"approach.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}