{"id":"https://openalex.org/W4372260201","doi":"https://doi.org/10.1109/icassp49357.2023.10097072","title":"CM-CS: Cross-Modal Common-Specific Feature Learning For Audio-Visual Video Parsing","display_name":"CM-CS: Cross-Modal Common-Specific Feature Learning For Audio-Visual Video Parsing","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260201","doi":"https://doi.org/10.1109/icassp49357.2023.10097072"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100452324","display_name":"Hongbo Chen","orcid":"https://orcid.org/0000-0002-0432-2176"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Chen","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China","Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078385469","display_name":"Dongchen Zhu","orcid":"https://orcid.org/0000-0002-1579-3942"},"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":"Dongchen Zhu","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","University of Chinese Academy of Sciences, Beijing, China","Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459828","display_name":"Guanghui Zhang","orcid":"https://orcid.org/0000-0003-0432-7329"},"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":"Guanghui Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","University of Chinese Academy of Sciences, Beijing, China","Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027543595","display_name":"Wenjun Shi","orcid":"https://orcid.org/0000-0002-9826-8034"},"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":"Wenjun Shi","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","University of Chinese Academy of Sciences, Beijing, China","Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403837","display_name":"Xiaolin Zhang","orcid":"https://orcid.org/0000-0003-3307-9838"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]},{"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":"Xiaolin Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China","Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035418350","display_name":"Jiamao Li","orcid":"https://orcid.org/0000-0002-7478-4544"},"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":"Jiamao Li","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","University of Chinese Academy of Sciences, Beijing, China","Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5614,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66798264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9965999722480774,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.995199978351593,"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":0.9940000176429749,"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":0.791075587272644},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7341684699058533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6193662881851196},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6145049333572388},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.600450336933136},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5364903211593628},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4957467019557953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4483644664287567},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4355129897594452},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.42563390731811523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38243016600608826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791075587272644},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7341684699058533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6193662881851196},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6145049333572388},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.600450336933136},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5364903211593628},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4957467019557953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4483644664287567},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4355129897594452},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.42563390731811523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38243016600608826},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2931433835","https://openalex.org/W2963155035","https://openalex.org/W3034519219","https://openalex.org/W3093051361","https://openalex.org/W3118120400","https://openalex.org/W3175335326","https://openalex.org/W3175514052","https://openalex.org/W3214328324","https://openalex.org/W4221163935","https://openalex.org/W4385245566","https://openalex.org/W6804185262"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"The":[0,82,102],"weakly-supervised":[1],"audio-visual":[2,113],"video":[3],"parsing":[4],"(AVVP)":[5],"task":[6],"aims":[7,84],"to":[8,30,41,72,85,98,123,155],"parse":[9],"duration":[10],"and":[11,33,79,108,129,148],"categories":[12],"of":[13,53,127,138],"each":[14],"snippet":[15],"when":[16],"only":[17],"the":[18,45,51,74,95,125,145],"video-level":[19,158],"event":[20,35],"labels":[21],"are":[22],"provided.":[23],"Most":[24],"methods":[25],"either":[26],"leverage":[27],"attention":[28],"mechanisms":[29],"explore":[31],"cross-modal":[32,66],"cross-video":[34],"semantics":[36],"or":[37],"alleviate":[38],"label":[39],"noise":[40],"improve":[42],"performance.":[43],"However,":[44],"distributional":[46],"modality":[47],"discrepancy":[48],"caused":[49],"by":[50],"heterogeneity":[52],"signals":[54],"remains":[55],"a":[56,64,120,135],"significant":[57],"challenge.":[58],"To":[59],"this":[60],"end,":[61],"we":[62,118],"propose":[63],"novel":[65],"common-specific":[67],"feature":[68],"learning":[69,126],"method":[70,104,140],"(cm-CS)":[71],"map":[73],"modal":[75],"features":[76],"into":[77],"modality-common":[78],"modality-specific":[80],"subspaces.":[81],"former":[83],"capture":[86,99],"similar":[87],"high-level":[88],"scene":[89],"cue":[90],"across":[91,109,131],"different":[92],"modalities,":[93,112,114],"while":[94],"later":[96],"attempts":[97],"specific":[100],"cue.":[101],"proposed":[103],"is":[105],"applied":[106],"among":[107],"in-visual":[110],"2D-3D":[111],"respectively.":[115],"In":[116],"addition,":[117],"design":[119],"training":[121],"strategy":[122],"strengthen":[124],"similarity":[128],"differences":[130],"modalities.":[132],"Experiments":[133],"show":[134],"large":[136],"improvement":[137],"our":[139],"against":[141],"existing":[142],"works":[143],"on":[144],"Look,":[146],"Listen,":[147],"Parse":[149],"(LLP)":[150],"dataset":[151],"(e.g.":[152],"from":[153],"58.9%":[154],"62.9%":[156],"in":[157],"visual":[159],"metric).":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
