{"id":"https://openalex.org/W4388193335","doi":"https://doi.org/10.1145/3581783.3612511","title":"Class-level Structural Relation Modeling and Smoothing for Visual Representation Learning","display_name":"Class-level Structural Relation Modeling and Smoothing for Visual Representation Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388193335","doi":"https://doi.org/10.1145/3581783.3612511"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612511","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5088964139","display_name":"Zitan Chen","orcid":"https://orcid.org/0009-0004-8422-4032"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zitan Chen","raw_affiliation_strings":["Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079754643","display_name":"Zhuang Qi","orcid":"https://orcid.org/0000-0003-3433-7413"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang Qi","raw_affiliation_strings":["Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019267021","display_name":"Xiao Cao","orcid":"https://orcid.org/0000-0001-9704-9633"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiao Cao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029698374","display_name":"Xiangxian Li","orcid":"https://orcid.org/0000-0001-6638-2361"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxian Li","raw_affiliation_strings":["Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101536417","display_name":"Xiangxu Meng","orcid":"https://orcid.org/0000-0001-7290-5659"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":["Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100629169","display_name":"Lei Meng","orcid":"https://orcid.org/0000-0002-0273-5946"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Meng","raw_affiliation_strings":["Shandong University & Shandong Research Institute of Industrial Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University & Shandong Research Institute of Industrial Technology, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5088964139"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":1.7457,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8785886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2964","last_page":"2972"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9954000115394592,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9721999764442444,"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":0.6952754259109497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6253670454025269},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5755923986434937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5666542053222656},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4321930408477783},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4293830990791321},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.349279522895813},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.336092472076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952754259109497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6253670454025269},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5755923986434937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5666542053222656},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4321930408477783},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4293830990791321},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.349279522895813},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.336092472076416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612511","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3486015038","display_name":null,"funder_award_id":"62006141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2007972815","https://openalex.org/W2112796928","https://openalex.org/W2526198870","https://openalex.org/W2552639984","https://openalex.org/W2951323451","https://openalex.org/W2966628364","https://openalex.org/W2981794866","https://openalex.org/W2998508940","https://openalex.org/W3092995403","https://openalex.org/W3109754877","https://openalex.org/W3110214837","https://openalex.org/W3172133997","https://openalex.org/W3176659256","https://openalex.org/W4214753187","https://openalex.org/W4226224676","https://openalex.org/W4283804319","https://openalex.org/W4296121252","https://openalex.org/W4312297142","https://openalex.org/W4313151233","https://openalex.org/W4317829628","https://openalex.org/W4321354006","https://openalex.org/W4362714795","https://openalex.org/W4386076209","https://openalex.org/W6600103761","https://openalex.org/W6600601450","https://openalex.org/W6601013545","https://openalex.org/W6601523666","https://openalex.org/W6825417173"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W4226363941","https://openalex.org/W4285218279","https://openalex.org/W4386136067","https://openalex.org/W4286858940"],"abstract_inverted_index":{"Representation":[0,92,107,188],"learning":[1,22,223,236],"for":[2,90,164,220,238],"images":[3],"has":[4],"been":[5,247],"advanced":[6],"by":[7],"recent":[8],"progress":[9],"in":[10,152],"more":[11],"complex":[12],"neural":[13],"models":[14,32,237],"such":[15,24],"as":[16,25],"the":[17,26,36,42,61,64,97,116,128,138,149,153,165,202,209,214],"Vision":[18],"Transformers":[19],"and":[20,46,88,104,119,123,134,156,185,224,244],"new":[21],"theories":[23],"structural":[27,65],"causal":[28],"models.":[29],"However,":[30],"these":[31],"mainly":[33],"rely":[34],"on":[35],"classification":[37],"loss":[38],"to":[39,110,126,147,181,200,208],"implicitly":[40],"regularize":[41],"class-level":[43,161],"data":[44,68,150],"distributions,":[45],"they":[47],"may":[48,70],"face":[49],"difficulties":[50],"when":[51],"handling":[52],"classes":[53],"with":[54,178,196,231],"diverse":[55],"visual":[56,132,206,234],"patterns.":[57],"We":[58],"argue":[59],"that":[60,226],"incorporation":[62],"of":[63,115,130,160,216],"information":[66],"between":[67],"samples":[69],"improve":[71],"this":[72,76,78],"situation.":[73],"To":[74],"achieve":[75],"goal,":[77],"paper":[79],"presents":[80],"a":[81,112,144,192],"framework":[82],"termed":[83],"Class-level":[84,98,139],"Structural":[85],"Relation":[86,99,140],"Modeling":[87],"Smoothing":[89],"Visual":[91],"Learning":[93,108,189],"(CSRMS),":[94],"which":[95],"includes":[96],"Modelling,":[100],"Class-aware":[101,168],"Graph":[102,169],"Sampling,":[103],"Relational":[105,186],"Graph-Guided":[106,187],"modules":[109],"model":[111],"relational":[113],"graph":[114,193],"entire":[117],"dataset":[118],"perform":[120],"class-aware":[121],"smoothing":[122,198],"regularization":[124],"operations":[125,199],"alleviate":[127],"issue":[129],"intra-class":[131],"diversity":[133],"inter-class":[135],"similarity.":[136],"Specifically,":[137],"Modelling":[141],"module":[142,171,190],"uses":[143],"clustering":[145],"algorithm":[146],"learn":[148],"distributions":[151],"feature":[154],"space":[155],"identify":[157],"three":[158,179],"types":[159],"sample":[162,182],"relations":[163],"training":[166,174],"set;":[167],"Sampling":[170],"extends":[172],"typical":[173],"batch":[175],"construction":[176],"process":[177],"strategies":[180],"dataset-level":[183],"sub-graphs;":[184],"employs":[191],"convolution":[194],"network":[195],"knowledge-guided":[197],"ease":[201],"projection":[203],"from":[204],"different":[205],"patterns":[207],"same":[210],"class.":[211],"Experiments":[212],"demonstrate":[213],"effectiveness":[215],"structured":[217],"knowledge":[218],"modelling":[219],"enhanced":[221],"representation":[222,235],"show":[225],"CSRMS":[227],"can":[228],"be":[229],"incorporated":[230],"any":[232],"state-of-the-art":[233],"performance":[239],"gains.":[240],"The":[241],"source":[242],"codes":[243],"demos":[245],"have":[246],"released":[248],"at":[249],"https://github.com/czt117/CSRMS.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}