{"id":"https://openalex.org/W4415539049","doi":"https://doi.org/10.1145/3746027.3755561","title":"Retaining Temporal Semantics and Relation Topologies for Continual Weakly-Supervised Audio-Visual Video Parsing","display_name":"Retaining Temporal Semantics and Relation Topologies for Continual Weakly-Supervised Audio-Visual Video Parsing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539049","doi":"https://doi.org/10.1145/3746027.3755561"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755561","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5101420580","display_name":"Jie Fu","orcid":"https://orcid.org/0000-0002-3877-7814"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Fu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3877-7814","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingkun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"563","last_page":"572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9976000189781189,"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/parsing","display_name":"Parsing","score":0.7682999968528748},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6664999723434448},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6171000003814697},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5300999879837036},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5067999958992004},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4050999879837036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896999716758728},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7682999968528748},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601000189781189},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45829999446868896},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.27469998598098755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755561","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1010114375","display_name":null,"funder_award_id":"62402240, 62325206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5428277042","display_name":null,"funder_award_id":"BK20240645","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2554616628","https://openalex.org/W2560647685","https://openalex.org/W2786446225","https://openalex.org/W2948734064","https://openalex.org/W2963140444","https://openalex.org/W2964048876","https://openalex.org/W2964189064","https://openalex.org/W2985144848","https://openalex.org/W3004127093","https://openalex.org/W3035342403","https://openalex.org/W3094953068","https://openalex.org/W3113584014","https://openalex.org/W3157898411","https://openalex.org/W3162322471","https://openalex.org/W3168149265","https://openalex.org/W4225484930","https://openalex.org/W4226206782","https://openalex.org/W4312447529","https://openalex.org/W4312849014","https://openalex.org/W4390873486","https://openalex.org/W4390873759","https://openalex.org/W4392251991"],"related_works":[],"abstract_inverted_index":{"To":[0,61,172],"achieve":[1],"audio":[2],"and":[3,93,143,183,210,237],"visual":[4],"action":[5,32,117,206],"detections":[6],"in":[7,102,221],"a":[8,16,68,153],"given":[9],"video":[10,21,110],"accompanying":[11],"with":[12,106],"only":[13],"video-level":[14,115],"labels,":[15],"group":[17],"of":[18,81,119,137,148,156,240],"weakly-supervised":[19,92],"audio-visual":[20,109],"parsing":[22],"methods":[23,47],"have":[24],"been":[25],"explored.":[26],"Throughout":[27],"their":[28],"training":[29],"processes,":[30],"the":[31,63,79,85,91,107,169,174,177,193,211,235],"categories":[33,83],"are":[34,99,190],"typically":[35],"assumed":[36],"to":[37,52,90,130,167,196,201],"be":[38,50],"static,":[39],"which":[40,158],"is":[41,122,159],"not":[42,49],"always":[43],"satisfied.":[44],"Consequently,":[45],"these":[46],"can":[48],"employed":[51],"handle":[53],"dynamic":[54],"scenarios":[55],"involving":[56],"continuously":[57],"growing":[58],"novel":[59,69],"classes.":[60],"alleviate":[62],"above":[64],"issue,":[65],"we":[66],"introduce":[67],"Continual":[70],"Weakly-Supervised":[71],"Audio-Visual":[72],"Video":[73],"Parsing":[74],"(C-WSAVVP)":[75],"task,":[76,112],"where":[77,113,192],"maintaining":[78],"knowledge":[80],"historic":[82],"remains":[84],"eternal":[86],"topic.":[87],"Distinctly,":[88],"owing":[89],"multi-modal":[94],"characteristics,":[95],"two":[96],"core":[97],"challenges":[98],"more":[100,132,203],"obvious":[101],"C-WSAVVP:":[103],"(1)":[104],"Compared":[105],"continual":[108,225],"classification":[111],"distilling":[114],"coarse":[116],"semantic":[118,135,170,199,216],"trimmed":[120],"videos":[121,139],"sufficient":[123],"for":[124,161,208],"mitigating":[125],"catastrophic":[126],"forgetting,":[127],"C-WSAVVP":[128],"has":[129],"retain":[131],"fine-grained":[133],"temporal":[134,205],"information":[136],"untrimmed":[138],"containing":[140],"both":[141,222],"actions":[142,150,220],"backgrounds.":[144],"(2)":[145],"The":[146],"semantics":[147],"different":[149,219],"generally":[151],"exhibit":[152],"certain":[154],"degree":[155],"correlation,":[157],"beneficial":[160],"understanding":[162],"related":[163],"actions,":[164],"but":[165],"how":[166],"maintain":[168],"correlations?":[171],"address":[173],"specific":[175],"challenges,":[176],"Semantic":[178],"Prototype-based":[179],"Action":[180],"Refinement":[181],"(SPAR)":[182],"Inter-Class":[184],"Relation":[185],"Topology":[186],"Preservation":[187],"(IRTP)":[188],"modules":[189],"explored,":[191],"former":[194],"devotes":[195],"utilizing":[197],"various":[198],"prototypes":[200],"refine":[202],"reliable":[204],"intervals":[207],"distillation":[209],"latter":[212],"focuses":[213],"on":[214,229],"retaining":[215],"correlations":[217],"between":[218],"modalities":[223],"during":[224],"learning.":[226],"Comprehensive":[227],"experiments":[228],"our":[230,241],"reconstructed":[231],"C-LLP":[232],"dataset":[233],"demonstrate":[234],"effectiveness":[236],"generalization":[238],"capability":[239],"proposed":[242],"method.":[243]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}