{"id":"https://openalex.org/W4387967986","doi":"https://doi.org/10.1145/3581783.3612468","title":"Intra- and Inter-Modal Curriculum for Multimodal Learning","display_name":"Intra- and Inter-Modal Curriculum for Multimodal Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967986","doi":"https://doi.org/10.1145/3581783.3612468"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612468","doi":"https://doi.org/10.1145/3581783.3612468","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612468","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612468","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612468","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101273536","display_name":"Yuwei Zhou","orcid":"https://orcid.org/0000-0001-9582-7331","observed_orcids":["https://orcid.org/0000-0001-9582-7331","https://orcid.org/0009-0003-6503-1780"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9582-7331","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Yue Wang","orcid":"https://orcid.org/0000-0002-0351-2939","observed_orcids":["https://orcid.org/0000-0002-0351-2939","https://orcid.org/0000-0001-9448-7689"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0351-2939","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420416","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-0943-2286","observed_orcids":["https://orcid.org/0000-0002-0943-2286","https://orcid.org/0000-0002-1724-8649"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0943-2286","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028258340","display_name":"Xuguang Duan","orcid":"https://orcid.org/0000-0001-9108-9618","observed_orcids":["https://orcid.org/0000-0001-9108-9618"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Duan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9108-9618","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290","observed_orcids":["https://orcid.org/0000-0003-2236-9290"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2236-9290","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.7899,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94154527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3724","last_page":"3735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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":9.999999747378752e-05,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/multimodal-learning","display_name":"multimodal learning","score":0.9629999995231628},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.953000009059906},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.859000027179718},{"id":"https://openalex.org/keywords/teacher-model","display_name":"teacher model","score":0.5659999847412109},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.8889999985694885},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.8059999942779541},{"id":"https://openalex.org/keywords/visual-entailment","display_name":"visual entailment","score":0.984000027179718},{"id":"https://openalex.org/keywords/multimodal-classification","display_name":"multimodal classification","score":0.9319999814033508}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7590827941894531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560241222381592},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7526975870132446},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6485567688941956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.619004487991333},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5708163976669312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5457058548927307},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.48836490511894226},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4419592320919037},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4164447784423828},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3205344080924988},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07215708494186401},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612468","doi":"https://doi.org/10.1145/3581783.3612468","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612468","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612468","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612468","doi":"https://doi.org/10.1145/3581783.3612468","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612468","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612468","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8278999924659729,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G119957897","display_name":null,"funder_award_id":"62102222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1527691513","display_name":null,"funder_award_id":"62250008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1950392669","display_name":null,"funder_award_id":"BNR2023RC01003","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G3022012397","display_name":null,"funder_award_id":"BNR2023TD03006","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G3720940119","display_name":null,"funder_award_id":"2020AAA0106300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G567712599","display_name":null,"funder_award_id":"No. BNR2023RC01003, BNR2023TD03006","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G6440740121","display_name":null,"funder_award_id":"No. 62250008, 62222209, 62102222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6655011991","display_name":null,"funder_award_id":"No. 2020AAA0106300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8567821897","display_name":null,"funder_award_id":"62222209","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"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":"https://ror.org/02tcm9e24"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387967986.pdf","grobid_xml":"https://content.openalex.org/works/W4387967986.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1572469720","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W1924770834","https://openalex.org/W1933349210","https://openalex.org/W2030931454","https://openalex.org/W2060727197","https://openalex.org/W2085291930","https://openalex.org/W2102660061","https://openalex.org/W2132984949","https://openalex.org/W2151096985","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2294370754","https://openalex.org/W2296073425","https://openalex.org/W2409879278","https://openalex.org/W2465534249","https://openalex.org/W2493109494","https://openalex.org/W2560730294","https://openalex.org/W2561238782","https://openalex.org/W2587372848","https://openalex.org/W2613000335","https://openalex.org/W2619383789","https://openalex.org/W2619947201","https://openalex.org/W2620998106","https://openalex.org/W2727285023","https://openalex.org/W2739879705","https://openalex.org/W2745461083","https://openalex.org/W2765874585","https://openalex.org/W2767290858","https://openalex.org/W2771951981","https://openalex.org/W2787017828","https://openalex.org/W2883409523","https://openalex.org/W2899335602","https://openalex.org/W2907386696","https://openalex.org/W2908510526","https://openalex.org/W2912371042","https://openalex.org/W2937328183","https://openalex.org/W2946165673","https://openalex.org/W2948972794","https://openalex.org/W2953084091","https://openalex.org/W2964121744","https://openalex.org/W2965591307","https://openalex.org/W2978017171","https://openalex.org/W2998081612","https://openalex.org/W2999905431","https://openalex.org/W3004413500","https://openalex.org/W3015371781","https://openalex.org/W3023989664","https://openalex.org/W3034368386","https://openalex.org/W3035333188","https://openalex.org/W3098748824","https://openalex.org/W3107906842","https://openalex.org/W3123742938","https://openalex.org/W3134648203","https://openalex.org/W3142849873","https://openalex.org/W3176157254","https://openalex.org/W3176292403","https://openalex.org/W3180718533","https://openalex.org/W3196591432","https://openalex.org/W4292542951","https://openalex.org/W4312639100"],"related_works":["https://openalex.org/W6891885701","https://openalex.org/W7203758236","https://openalex.org/W4400434986","https://openalex.org/W6979364855","https://openalex.org/W4414739275","https://openalex.org/W7138982927","https://openalex.org/W4399151460","https://openalex.org/W4415795759","https://openalex.org/W4403924124","https://openalex.org/W4402832821"],"abstract_inverted_index":{"Multimodal":[0],"learning":[1,35],"has":[2,25],"been":[3,26],"widely":[4],"studied":[5],"and":[6,16,109,120,166,173,203,219],"applied":[7],"due":[8],"to":[9,38,51,66,136,164,213,223],"its":[10,17,190],"improvement":[11,222],"over":[12,47],"previous":[13],"unimodal":[14,39,82],"tasks":[15,91,196],"effectiveness":[18],"on":[19,62,73,81,194],"emerging":[20],"multimodal":[21,34,124,198,224],"challenges.":[22],"However,":[23],"it":[24],"reported":[27],"that":[28,207],"modal":[29,93],"encoders":[30],"are":[31,45],"under-optimized":[32,216],"in":[33,36],"contrast":[37],"learning,":[40],"especially":[41],"when":[42],"some":[43],"modalities":[44],"dominant":[46],"others.":[48],"Existing":[49],"solutions":[50],"this":[52],"problem":[53,218],"suffer":[54],"from":[55,170,186],"two":[56],"limitations:":[57],"i)":[58],"they":[59],"merely":[60],"focus":[61],"inter-modal":[63,156],"balance,":[64],"failing":[65],"consider":[67],"the":[68,90,127,142,147,151,155,168,187,215],"influence":[69],"of":[70,179],"intra-modal":[71,128],"data":[72,118,148],"each":[74],"modality;":[75],"ii)":[76],"their":[77],"implementations":[78],"heavily":[79],"rely":[80],"performances":[83],"or":[84,189],"losses,":[85],"thus":[86],"being":[87],"suboptimal":[88],"for":[89,123],"requiring":[92],"interactions":[94],"(e.g.,":[95],"visual":[96,200,204],"question":[97,201],"answering).":[98],"To":[99],"tackle":[100,214],"these":[101],"limitations,":[102],"we":[103,130,158],"propose":[104],"I2MCL,":[105],"a":[106,132,160,182],"generic":[107],"Intra-":[108],"Inter-Modal":[110],"Curriculum":[111],"Learning":[112],"framework":[113],"which":[114,145],"simultaneously":[115],"considers":[116],"both":[117],"difficulty":[119,143],"modality":[121,183,217],"balance":[122],"learning.":[125,225],"In":[126,154],"curriculum,":[129,157],"adopt":[131],"pretrained":[133],"teacher":[134],"model":[135],"obtain":[137],"knowledge":[138],"distillation":[139,171],"loss":[140,172,175],"as":[141],"measurer,":[144],"determines":[146],"weights":[149],"within":[150],"corresponding":[152],"modality.":[153],"utilize":[159],"Pareto":[161],"optimization":[162],"strategy":[163],"measure":[165],"compare":[167],"gradients":[169],"task":[174,188],"across":[176],"modalities,":[177],"capable":[178],"determining":[180],"whether":[181],"should":[184],"learn":[185],"teacher.":[191],"Empirical":[192],"experiments":[193],"various":[195],"including":[197],"classification,":[199],"answering":[202],"entailment":[205],"demonstrate":[206],"our":[208],"proposed":[209],"I2MCL":[210],"is":[211],"able":[212],"bring":[220],"consistent":[221]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-28T00:00:00"}