{"id":"https://openalex.org/W4403780618","doi":"https://doi.org/10.1145/3664647.3680697","title":"Detached and Interactive Multimodal Learning","display_name":"Detached and Interactive Multimodal Learning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780618","doi":"https://doi.org/10.1145/3664647.3680697"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680697","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680697","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3680697","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028335984","display_name":"Yunfeng Fan","orcid":"https://orcid.org/0000-0002-2277-5355"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yunfeng Fan","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2277-5355","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063181504","display_name":"Wenchao Xu","orcid":"https://orcid.org/0000-0003-0983-387X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenchao Xu","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-0983-387X","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027119797","display_name":"Haozhao Wang","orcid":"https://orcid.org/0000-0002-7591-5315"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhao Wang","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-7591-5315","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108149924","display_name":"Junhong Liu","orcid":"https://orcid.org/0009-0002-5332-1855"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhong Liu","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5332-1855","affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043464306","display_name":"Song Guo","orcid":"https://orcid.org/0000-0001-9831-2202"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Song Guo","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9831-2202","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5470","last_page":"5478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9966999888420105,"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":0.9966999888420105,"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":0.920199990272522,"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/T12031","display_name":"Speech and dialogue systems","score":0.9193999767303467,"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/computer-science","display_name":"Computer science","score":0.7084174752235413},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.532004177570343},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39079979062080383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35889267921447754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084174752235413},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.532004177570343},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39079979062080383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35889267921447754}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680697","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680697","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-147134","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2024&rft.spage=&rft.aulast=Fan&rft.aufirst=Yunfeng&rft.atitle=Detached+and+Interactive+Multimodal+Learning&rft.title=","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3664647.3680697","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680697","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2948153973","https://openalex.org/W2964109005","https://openalex.org/W3035333188","https://openalex.org/W3035524453","https://openalex.org/W3153511633","https://openalex.org/W3166100196","https://openalex.org/W3174159092","https://openalex.org/W3196591432","https://openalex.org/W3206366488","https://openalex.org/W3214127792","https://openalex.org/W4212774754","https://openalex.org/W4234552385","https://openalex.org/W4285107355","https://openalex.org/W4312639100","https://openalex.org/W4312765682","https://openalex.org/W4312983485","https://openalex.org/W4313034431","https://openalex.org/W4313136445","https://openalex.org/W4372266552","https://openalex.org/W4386065563","https://openalex.org/W4386076642","https://openalex.org/W4386076681","https://openalex.org/W4387967986"],"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":{"Recently,":[0],"Multimodal":[1],"Learning":[2],"(MML)":[3],"has":[4],"gained":[5],"significant":[6],"interest":[7],"as":[8],"it":[9],"compensates":[10],"for":[11,130],"single-modality":[12],"limitations":[13],"through":[14],"comprehensive":[15],"complementary":[16,74,146],"information":[17,75,147],"within":[18],"multimodal":[19],"data.":[20],"However,":[21],"traditional":[22],"MML":[23,69],"methods":[24],"generally":[25],"use":[26],"the":[27,40,52,79,149,165],"joint":[28],"learning":[29,34,97],"framework":[30,70],"with":[31,95],"a":[32,66,105,110,116,138],"uniform":[33],"objective":[35],"that":[36,108],"can":[37],"lead":[38],"to":[39,59,72,122,128,143],"modality":[41,83,93],"competition":[42,88],"issue,":[43],"where":[44],"feedback":[45],"predominantly":[46],"comes":[47],"from":[48],"certain":[49],"modalities,":[50],"limiting":[51],"full":[53],"potential":[54],"of":[55,81,168],"others.":[56],"In":[57],"response":[58],"this":[60,62],"challenge,":[61],"paper":[63],"introduces":[64],"DI-MML,":[65],"novel":[67],"detached":[68],"designed":[71],"learn":[73],"across":[76],"modalities":[77],"under":[78],"premise":[80],"avoiding":[82],"competition.":[84],"Specifically,":[85],"DI-MML":[86],"addresses":[87],"by":[89],"separately":[90],"training":[91],"each":[92],"encoder":[94],"isolated":[96],"objectives.":[98],"It":[99],"further":[100],"encourages":[101],"cross-modal":[102],"interaction":[103],"via":[104],"shared":[106],"classifier":[107],"defines":[109],"common":[111],"feature":[112],"space":[113],"and":[114,160],"employing":[115],"dimension-decoupled":[117],"unidirectional":[118],"contrastive":[119],"(DUC)":[120],"loss":[121],"facilitate":[123],"modality-level":[124],"knowledge":[125],"transfer.":[126],"Additionally,":[127],"account":[129],"varying":[131],"reliability":[132],"in":[133],"sample":[134],"pairs,":[135],"we":[136],"devise":[137],"certainty-aware":[139],"logit":[140],"weighting":[141],"strategy":[142],"effectively":[144],"leverage":[145],"at":[148,176],"instance":[150],"level":[151],"during":[152],"inference.":[153],"Extensive":[154],"experiments":[155],"conducted":[156],"on":[157],"audio-visual,":[158],"flow-image,":[159],"front-rear":[161],"view":[162],"datasets":[163],"show":[164],"superior":[166],"performance":[167],"our":[169],"proposed":[170],"method.":[171],"The":[172],"code":[173],"is":[174],"released":[175],"https://github.com/fanyunfeng-bit/DI-MML.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}