{"id":"https://openalex.org/W4304092370","doi":"https://doi.org/10.1145/3503161.3548263","title":"C <sup>3</sup> CMR: Cross-Modality Cross-Instance Contrastive Learning for Cross-Media Retrieval","display_name":"C <sup>3</sup> CMR: Cross-Modality Cross-Instance Contrastive Learning for Cross-Media Retrieval","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092370","doi":"https://doi.org/10.1145/3503161.3548263"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548263","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548263","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5100610651","display_name":"Junsheng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junsheng Wang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032269269","display_name":"Tiantian Gong","orcid":"https://orcid.org/0000-0001-8142-3782"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiantian Gong","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101581937","display_name":"Zhixiong Zeng","orcid":"https://orcid.org/0000-0002-3822-1074"},"institutions":[{"id":"https://openalex.org/I4210092230","display_name":"Beijing Shijingshan Hospital","ror":"https://ror.org/00g87gv13","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210092230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixiong Zeng","raw_affiliation_strings":["Independent Researcher, Bejing, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Bejing, China","institution_ids":["https://openalex.org/I4210092230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081724365","display_name":"Changchang Sun","orcid":"https://orcid.org/0000-0003-3685-1205"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changchang Sun","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100610651"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.6622,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78276059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4300","last_page":"4308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.984000027179718,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.794808030128479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.749433696269989},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6737509965896606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6675319075584412},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5716379284858704},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5448600649833679},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.51800137758255},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.49602827429771423},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46032702922821045},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4364214837551117},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.415410578250885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4025150537490845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.390725314617157}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.794808030128479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.749433696269989},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6737509965896606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675319075584412},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5716379284858704},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5448600649833679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.51800137758255},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49602827429771423},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46032702922821045},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4364214837551117},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.415410578250885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4025150537490845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.390725314617157},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548263","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548263","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1686810756","https://openalex.org/W1964073652","https://openalex.org/W2007972815","https://openalex.org/W2013535308","https://openalex.org/W2211092169","https://openalex.org/W2605649771","https://openalex.org/W2741163476","https://openalex.org/W2765440071","https://openalex.org/W2896457183","https://openalex.org/W2954672622","https://openalex.org/W2963526065","https://openalex.org/W2964081303","https://openalex.org/W2964216321","https://openalex.org/W2967957126","https://openalex.org/W3035524453","https://openalex.org/W3046614818","https://openalex.org/W3135367836","https://openalex.org/W3155366680","https://openalex.org/W3173223111","https://openalex.org/W3175300676","https://openalex.org/W3176463841","https://openalex.org/W3196056489","https://openalex.org/W3206019042","https://openalex.org/W4214648142","https://openalex.org/W4251657561","https://openalex.org/W4255556797","https://openalex.org/W4256361765"],"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":{"Cross-modal":[0],"retrieval":[1,29,194],"is":[2,30],"an":[3],"essential":[4],"area":[5],"of":[6,112,129,186],"representation":[7],"learning,":[8],"which":[9,66],"aims":[10],"to":[11,31,59,95,107,125,148,168],"retrieve":[12],"instances":[13],"with":[14],"the":[15,33,98,103,109,113,130,149,164,170,184],"same":[16],"semantics":[17],"from":[18],"different":[19,37],"modalities.":[20],"In":[21,134],"real":[22],"implementation,":[23],"a":[24,83,119],"key":[25],"challenge":[26],"for":[27,48,89],"cross-modal":[28,193],"narrow":[32],"heterogeneity":[34],"gap":[35],"between":[36],"modalities":[38],"and":[39,42,55,63,69,139,158],"obtain":[40],"modality-invariant":[41],"discriminative":[43,72,110],"features.":[44,73,115],"Typically,":[45],"existing":[46],"approaches":[47],"this":[49,79,135],"task":[50],"mainly":[51],"learn":[52,71],"inter-modal":[53,121,140],"invariance":[54,141],"focus":[56],"on":[57,178],"how":[58],"combine":[60],"pair-level":[61],"loss":[62],"class-level":[64],"loss,":[65],"cannot":[67],"effectively":[68],"adequately":[70],"To":[74],"address":[75],"these":[76],"issues,":[77],"in":[78],"paper,":[80],"we":[81,101,117,162],"propose":[82,163],"novel":[84],"Cross-Modality":[85],"Cross-Instance":[86],"Contrastive":[87],"Learning":[88],"Cross-Media":[90],"Retrieval":[91],"(C3CMR)":[92],"method.":[93],"Specifically,":[94],"fully":[96],"employ":[97],"intra-modal":[99,104],"similarities,":[100],"introduce":[102],"contrastive":[105,122,166],"learning":[106,123,167],"enhance":[108],"power":[111],"unimodal":[114],"Besides,":[116],"design":[118],"supervised":[120],"scheme":[124],"take":[126],"full":[127],"advantage":[128],"label":[131],"semantic":[132,152],"associations.":[133],"way,":[136],"cross-semantic":[137],"associations":[138],"can":[142],"be":[143],"further":[144],"learned.":[145],"Moreover,":[146],"pertaining":[147],"local":[150],"suboptimal":[151],"similarity":[153],"by":[154],"only":[155],"mining":[156],"pairwise":[157],"triplewise":[159],"sample":[160],"relationships,":[161],"cross-instance":[165],"mine":[169],"similarities":[171],"among":[172],"multiple":[173],"instances.":[174],"Comprehensive":[175],"experimental":[176],"results":[177],"four":[179],"widely-used":[180],"benchmark":[181],"datasets":[182],"demonstrate":[183],"superiority":[185],"our":[187],"proposed":[188],"method":[189],"over":[190],"several":[191],"state-of-the-art":[192],"methods.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}