{"id":"https://openalex.org/W4404135833","doi":"https://doi.org/10.1145/3686540.3686547","title":"Exploring Event Misalignment Bias and Segment Focus Bias for Weakly-Supervised Audio-Visual Video Parsing","display_name":"Exploring Event Misalignment Bias and Segment Focus Bias for Weakly-Supervised Audio-Visual Video Parsing","publication_year":2024,"publication_date":"2024-05-29","ids":{"openalex":"https://openalex.org/W4404135833","doi":"https://doi.org/10.1145/3686540.3686547"},"language":"en","primary_location":{"id":"doi:10.1145/3686540.3686547","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686540.3686547","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 6th International Conference on Big-data Service and Intelligent Computation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1145/3686540.3686547","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114119790","display_name":"Mingchi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingchi Li","raw_affiliation_strings":["Shanghai Institute of Microsystem and Information Technology, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0003-4862-7910","affiliations":[{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Songrui Han","orcid":"https://orcid.org/0009-0007-9091-3231"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songrui Han","raw_affiliation_strings":["Shanghai Institute of Microsystem and Information Technology, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0007-9091-3231","affiliations":[{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101674147","display_name":"Xiaobing Yuan","orcid":"https://orcid.org/0000-0001-7602-7136"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Yuan","raw_affiliation_strings":["Shanghai Institute of Microsystem and Information Technology, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-7602-7136","affiliations":[{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114119790"],"corresponding_institution_ids":["https://openalex.org/I4210147322","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21385782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9926000237464905,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9915000200271606,"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":0.7831518054008484},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7753235101699829},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7533193826675415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5770254731178284},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5705841779708862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.531078040599823},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.46009984612464905},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42475542426109314},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.21609166264533997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831518054008484},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7753235101699829},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7533193826675415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770254731178284},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5705841779708862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.531078040599823},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.46009984612464905},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42475542426109314},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.21609166264533997},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3686540.3686547","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686540.3686547","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 6th International Conference on Big-data Service and Intelligent Computation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3686540.3686547","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686540.3686547","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 6th International Conference on Big-data Service and Intelligent Computation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6800000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2146958953","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2584992898","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2931433835","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963155035","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2971923036","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2988200020","https://openalex.org/W2989980422","https://openalex.org/W2990113535","https://openalex.org/W2990408345","https://openalex.org/W2997909293","https://openalex.org/W3017343282","https://openalex.org/W3095687795","https://openalex.org/W3175335326","https://openalex.org/W3175514052","https://openalex.org/W3214328324","https://openalex.org/W4226206782","https://openalex.org/W4287608901","https://openalex.org/W4304083155","https://openalex.org/W4312864739"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,51,67,216,239],"the":[4,14,23,41,103,114,144,192,211,235,240],"audio-visual":[5,20],"video":[6,38,72],"parsing":[7],"(AVVP)":[8],"task,":[9],"which":[10,111,141,173],"aims":[11],"to":[12,35,95,117,147,157,184,207],"predict":[13],"classes":[15],"of":[16,26,105,124,138,175,194,197],"audio,":[17],"visual":[18],"and":[19,22,71,74,189,224],"events":[21,28,107],"temporal":[24,58],"boundaries":[25,59],"multiple":[27],"in":[29,133],"a":[30,135,139,165],"given":[31],"video.":[32],"In":[33],"contrast":[34],"fully":[36,148],"supervised":[37],"understanding":[39],"tasks,":[40],"AVVP":[42,241],"task":[43],"is":[44,131,205],"more":[45],"difficult":[46],"since":[47],"it":[48,153],"relies":[49],"only":[50,134],"video-level":[52],"labels":[53],"during":[54],"training,":[55],"without":[56],"any":[57],"or":[60],"modal":[61],"annotations.":[62],"Prior":[63],"works":[64],"typically":[65],"focus":[66,126,156,203,215],"jointly":[68],"modeling":[69],"audio":[70],"data":[73],"extracting":[75],"information":[76,130,151],"from":[77],"cross-modal":[78,106,180,186],"segment-level":[79,120,125,150],"features":[80],"simultaneously.":[81],"Despite":[82],"their":[83],"initial":[84],"success,":[85],"we":[86,163],"argue":[87],"that":[88,229],"there":[89],"are":[90],"still":[91],"two":[92,176],"inherent":[93],"challenges":[94],"be":[96,109],"solved:":[97],"1)":[98,178],"Cross-modal":[99],"event":[100,129,181,195,220],"misalignment":[101,187],"bias:":[102,127],"occurrence":[104],"may":[108],"asynchronous,":[110],"can":[112],"hinder":[113],"model\u2019s":[115,145],"ability":[116,146],"correctly":[118],"utilize":[119,149],"information;":[121],"2)":[122,199],"Lack":[123],"rich":[128,219],"found":[132],"few":[136],"segments":[137,217],"video,":[140],"would":[142],"impede":[143],"if":[152],"assigns":[154],"equal":[155],"all":[158],"segments.":[159],"To":[160],"this":[161],"end,":[162],"propose":[164],"generic":[166],"framework":[167,232],"named":[168],"Cross-Modal":[169],"Re-calibrating":[170],"Network":[171],"(CMRN),":[172],"consists":[174],"parts:":[177],"A":[179],"alignment":[182],"module":[183,204],"eliminate":[185],"bias":[188,209],"thus":[190],"improve":[191],"consistency":[193],"representations":[196],"segments;":[198],"An":[200],"information-aware":[201],"segment":[202],"proposed":[206,231],"inject":[208],"into":[210],"model,":[212],"enabling":[213],"selectively":[214],"with":[218],"information.":[221],"Extensive":[222],"quantitative":[223],"qualitative":[225],"experimental":[226],"results":[227],"demonstrate":[228],"our":[230],"significantly":[233],"improves":[234],"previous":[236],"state-of-the-art":[237],"methods":[238],"task.":[242]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}