{"id":"https://openalex.org/W4403791316","doi":"https://doi.org/10.1145/3664647.3681331","title":"Robust Variational Contrastive Learning for Partially View-unaligned Clustering","display_name":"Robust Variational Contrastive Learning for Partially View-unaligned Clustering","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791316","doi":"https://doi.org/10.1145/3664647.3681331"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681331","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101227506","display_name":"Changhao He","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changhao He","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015639955","display_name":"Hongyuan Zhu","orcid":"https://orcid.org/0000-0001-5177-8320"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongyuan Zhu","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082233466","display_name":"Peng Hu","orcid":"https://orcid.org/0000-0003-3868-3997"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Hu","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022800038","display_name":"Xi Peng","orcid":"https://orcid.org/0000-0002-5727-2790"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Peng","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101227506"],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":null,"apc_paid":null,"fwci":3.099,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93001098,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4167","last_page":"4176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9994999766349792,"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/T10057","display_name":"Face and Expression Recognition","score":0.9994999766349792,"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":0.9987000226974487,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7324851155281067},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6892557740211487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5368561744689941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324851155281067},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6892557740211487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5368561744689941}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681331","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2007972815","https://openalex.org/W2049633694","https://openalex.org/W2107034620","https://openalex.org/W2128532956","https://openalex.org/W2138118304","https://openalex.org/W2155904486","https://openalex.org/W2187089797","https://openalex.org/W2531563875","https://openalex.org/W2730106296","https://openalex.org/W2742098698","https://openalex.org/W2747329762","https://openalex.org/W2753064086","https://openalex.org/W2963697299","https://openalex.org/W2963764569","https://openalex.org/W2997707481","https://openalex.org/W3098802639","https://openalex.org/W3100993965","https://openalex.org/W3168316785","https://openalex.org/W3169978599","https://openalex.org/W3176694003","https://openalex.org/W4214876032","https://openalex.org/W4220873374","https://openalex.org/W4240935049","https://openalex.org/W4290713716","https://openalex.org/W4312973985","https://openalex.org/W4385318959","https://openalex.org/W4385764502","https://openalex.org/W4386071520","https://openalex.org/W4387968141","https://openalex.org/W4388692616","https://openalex.org/W4389319141","https://openalex.org/W4393147617","https://openalex.org/W4393160175","https://openalex.org/W4400524870"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Although":[0],"multi-view":[1],"learning":[2,67,151,221],"has":[3],"achieved":[4],"remarkable":[5],"progress":[6],"over":[7],"the":[8,43,63,122,126,129,135,159,169,181,195,219],"past":[9],"decades,":[10],"most":[11,130],"existing":[12],"methods":[13,58],"implicitly":[14],"assume":[15],"that":[16,213,230],"all":[17,71],"views":[18,29,65,79],"(or":[19],"modalities)":[20],"are":[21,59],"well-aligned.":[22],"In":[23],"practice,":[24],"however,":[25],"collecting":[26],"fully":[27,245],"aligned":[28,246],"is":[30,114,250],"challenging":[31],"due":[32],"to":[33,61,100,152,176],"complexities":[34],"and":[35,39,104,148,155,244],"discordances":[36],"in":[37,42,121,158,241],"time":[38],"space,":[40,124],"resulting":[41],"Partially":[44],"View-unaligned":[45],"Problem":[46],"(PVP),":[47],"such":[48],"as":[49,117],"audio-video":[50],"asynchrony":[51],"caused":[52],"by":[53,66,141,203],"network":[54],"congestion.":[55],"While":[56],"some":[57],"proposed":[60],"align":[62],"unaligned":[64],"view-invariant":[68],"representations,":[69,161],"almost":[70],"of":[72,197],"them":[73],"overlook":[74],"specific":[75,105,156,182],"information":[76,106],"across":[77],"different":[78],"for":[80],"complementarity,":[81],"limiting":[82],"performance":[83],"improvement.":[84],"To":[85,108],"address":[86],"these":[87],"problems,":[88],"we":[89,207],"propose":[90,208],"a":[91,118,167,209],"robust":[92,210],"framework,":[93],"dubbed":[94],"VariatIonal":[95],"ConTrAstive":[96],"Learning":[97],"(VITAL),":[98],"designed":[99],"learn":[101],"both":[102,242],"common":[103,132,154,170],"simultaneously.":[107],"be":[109,174],"specific,":[110],"each":[111],"data":[112],"sample":[113,186],"first":[115],"modeled":[116],"Gaussian":[119],"distribution":[120,160],"latent":[123],"where":[125],"mean":[127],"estimates":[128],"probable":[131],"information,":[133,188],"while":[134,180],"variance":[136],"indicates":[137],"view-specific":[138],"information.":[139],"Second,":[140],"using":[142],"variational":[143],"inference,":[144],"VITAL":[145,231],"conducts":[146],"intra-":[147],"inter-view":[149],"contrastive":[150,205,220],"preserve":[153],"semantics":[157],"thereby":[162,189],"achieving":[163],"comprehensive":[164],"perception.":[165],"As":[166],"result,":[168],"representation":[171,183],"(mean)":[172],"could":[173],"used":[175],"guide":[177],"category-level":[178],"realignment,":[179],"(variance)":[184],"complements":[185],"semantic":[187],"boosting":[190],"overall":[191],"performance.":[192],"Finally,":[193],"considering":[194],"abundance":[196],"False":[198],"Negative":[199],"Pairs":[200],"(FNPs)":[201],"generated":[202],"unsupervised":[204],"learning,":[206],"loss":[211],"function":[212],"seamlessly":[214],"incorporates":[215],"FNP":[216],"rectification":[217],"into":[218],"paradigm.":[222],"Empirical":[223],"evaluations":[224],"on":[225],"eight":[226],"benchmark":[227],"datasets":[228],"reveal":[229],"outperforms":[232],"ten":[233],"state-of-the-art":[234],"deep":[235],"clustering":[236],"baselines,":[237],"demonstrating":[238],"its":[239],"efficacy":[240],"partially":[243],"scenarios.":[247],"The":[248],"Code":[249],"available":[251],"at":[252],"https://github.com/He-Changhao/2024-MM-VITAL.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}