{"id":"https://openalex.org/W3035177583","doi":"https://doi.org/10.1109/icme46284.2020.9102921","title":"End-To-End Deep Multimodal Clustering","display_name":"End-To-End Deep Multimodal Clustering","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3035177583","doi":"https://doi.org/10.1109/icme46284.2020.9102921","mag":"3035177583"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","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/A5006269113","display_name":"Xianchao Zhang","orcid":"https://orcid.org/0000-0002-0180-3740"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianchao Zhang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059299970","display_name":"Jie Mu","orcid":"https://orcid.org/0009-0009-1958-5110"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Mu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030649664","display_name":"Linlin Zong","orcid":"https://orcid.org/0000-0002-1116-1016"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin Zong","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079763362","display_name":"Xiaochun Yang","orcid":"https://orcid.org/0000-0002-6184-4771"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Yang","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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":0.9973999857902527,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9955000281333923,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8674534559249878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7414937615394592},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6842831373214722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6462720632553101},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5805796384811401},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5395440459251404},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5250603556632996},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.43315961956977844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.427989661693573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4057384431362152},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38491395115852356},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33650436997413635}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8674534559249878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414937615394592},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6842831373214722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6462720632553101},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5805796384811401},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5395440459251404},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5250603556632996},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.43315961956977844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.427989661693573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4057384431362152},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38491395115852356},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33650436997413635},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme46284.2020.9102921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","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":27,"referenced_works":["https://openalex.org/W881606563","https://openalex.org/W1883346539","https://openalex.org/W1907775068","https://openalex.org/W2013029404","https://openalex.org/W2107034620","https://openalex.org/W2142109962","https://openalex.org/W2162833336","https://openalex.org/W2197707282","https://openalex.org/W2398118205","https://openalex.org/W2405459681","https://openalex.org/W2605146283","https://openalex.org/W2737186053","https://openalex.org/W2741943936","https://openalex.org/W2797653144","https://openalex.org/W2919115771","https://openalex.org/W2962852342","https://openalex.org/W2963365397","https://openalex.org/W2964074409","https://openalex.org/W2965624713","https://openalex.org/W2982619606","https://openalex.org/W6623954603","https://openalex.org/W6639103823","https://openalex.org/W6684050148","https://openalex.org/W6685380521","https://openalex.org/W6736441558","https://openalex.org/W6744043827","https://openalex.org/W7075742223"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W2669956259","https://openalex.org/W4224266612","https://openalex.org/W4249005693","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964"],"abstract_inverted_index":{"Deep":[0,52],"multimodal":[1,66],"clustering":[2,93,105,117,128],"is":[3],"challenging,":[4],"since":[5],"it":[6],"needs":[7],"to":[8,76],"learn":[9],"appropriate":[10],"features":[11,72,88],"for":[12],"different":[13,90],"modalities":[14,91],"and":[15,65,96],"find":[16],"correct":[17],"clusters":[18],"by":[19,79,92,100,125],"using":[20],"consistency":[21],"among":[22],"the":[23,28,33,40,43,70,111,126],"modalities.":[24],"Existing":[25],"methods":[26],"treat":[27],"two":[29],"problems":[30],"separately,":[31],"nevertheless,":[32],"optimization":[34,41,61],"of":[35,42,62,73,89],"one":[36],"does":[37],"not":[38],"guarantee":[39],"other.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"an":[50],"end-to-end":[51],"Multimodal":[53],"Clustering":[54],"(DMMC)":[55],"framework,":[56],"which":[57],"achieves":[58,121],"a":[59,101],"joint":[60],"feature":[63,99],"learning":[64],"clustering.":[67],"We":[68],"encourage":[69],"learned":[71],"each":[74],"modality":[75],"be":[77,108],"cluster-oriented":[78],"autoencoder":[80],"with":[81,115],"Frobenius":[82],"norm":[83],"loss.":[84,103],"Then,":[85],"DMMC":[86],"integrates":[87],"integration":[94],"layer":[95],"learns":[97],"consensus":[98,102,112],"The":[104],"result":[106],"can":[107],"discovered":[109],"in":[110],"feature.":[113],"Compared":[114],"existing":[116],"methods,":[118],"our":[119],"framework":[120],"superior":[122],"performances":[123],"measured":[124],"standard":[127],"evaluation":[129],"metrics.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}