{"id":"https://openalex.org/W4405354984","doi":"https://doi.org/10.1145/3696409.3700225","title":"Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning","display_name":"Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4405354984","doi":"https://doi.org/10.1145/3696409.3700225"},"language":"en","primary_location":{"id":"doi:10.1145/3696409.3700225","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700225","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 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3696409.3700225","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100756210","display_name":"Meng Shen","orcid":"https://orcid.org/0000-0003-2502-3500"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meng Shen","raw_affiliation_strings":["Nanyang Technological University, Singapore, SG",", , of ,"],"raw_orcid":"https://orcid.org/0000-0003-2502-3500","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":", , of ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006944766","display_name":"Yake Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yake Wei","raw_affiliation_strings":["Renmin University of China, Beijing, CN"],"raw_orcid":"https://orcid.org/0009-0008-8779-0637","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, CN","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019182457","display_name":"Jianxiong Yin","orcid":"https://orcid.org/0000-0003-4686-2768"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["GB","SG"],"is_corresponding":false,"raw_author_name":"Jianxiong (Terry) Yin","raw_affiliation_strings":["NVIDIA AI Tech Centre, Singapore, SG",", , of ,","Nanyang Technological University Singapore, SG"],"raw_orcid":"https://orcid.org/0000-0003-4686-2768","affiliations":[{"raw_affiliation_string":"NVIDIA AI Tech Centre, Singapore, SG","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":", , of ,","institution_ids":[]},{"raw_affiliation_string":"Nanyang Technological University Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009372982","display_name":"Deepu Rajan","orcid":"https://orcid.org/0000-0001-7788-8368"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Deepu Rajan","raw_affiliation_strings":["Nanyang Technological University, Singapore, SG",", , of ,"],"raw_orcid":"https://orcid.org/0000-0001-7788-8368","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":", , of ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670614","display_name":"Di Hu","orcid":"https://orcid.org/0000-0002-7118-6733"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Hu","raw_affiliation_strings":["Renmin University of China, Beijing, CN"],"raw_orcid":"https://orcid.org/0000-0002-7118-6733","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, CN","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077539496","display_name":"Simon See","orcid":"https://orcid.org/0000-0002-4958-9237"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon See","raw_affiliation_strings":["NVIDIA AI Tech Centre, Singapore, SG"],"raw_orcid":"https://orcid.org/0000-0002-4958-9237","affiliations":[{"raw_affiliation_string":"NVIDIA AI Tech Centre, Singapore, SG","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T10028","display_name":"Topic Modeling","score":0.9793999791145325,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9746000170707703,"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":0.7262760400772095},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.711600661277771},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6494566202163696},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5894463658332825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5827602744102478},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.565698504447937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5108749270439148},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4804239273071289},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45149677991867065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262760400772095},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.711600661277771},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6494566202163696},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5894463658332825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827602744102478},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.565698504447937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5108749270439148},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4804239273071289},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45149677991867065},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3696409.3700225","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700225","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 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.09126","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09126","pdf_url":"https://arxiv.org/pdf/2412.09126","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3696409.3700225","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700225","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 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2296448531","https://openalex.org/W2619383789","https://openalex.org/W2619697695","https://openalex.org/W2963155035","https://openalex.org/W2963341956","https://openalex.org/W2985076077","https://openalex.org/W3015371781","https://openalex.org/W3035524453","https://openalex.org/W3101345273","https://openalex.org/W3103649165","https://openalex.org/W3159481202","https://openalex.org/W3174894125","https://openalex.org/W3188030217","https://openalex.org/W3203711169","https://openalex.org/W3205626500","https://openalex.org/W4312677475","https://openalex.org/W4312775442","https://openalex.org/W4362598872","https://openalex.org/W4372266552","https://openalex.org/W4380993941","https://openalex.org/W4382237564","https://openalex.org/W4386071709"],"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":{"Training":[0],"multimodal":[1,67,152,174,187,192],"models":[2],"requires":[3],"a":[4,32,48,58,70,83,98],"large":[5],"amount":[6],"of":[7,42,104,172],"labeled":[8,28,50],"data.":[9,44],"Active":[10,89],"learning":[11],"(AL)":[12],"aim":[13],"to":[14,30,57,140],"reduce":[15],"labeling":[16],"costs.":[17],"Most":[18],"AL":[19,63,147],"methods":[20,64,148],"employ":[21],"warm-start":[22],"approaches,":[23],"which":[24],"rely":[25],"on":[26],"sufficient":[27],"data":[29,51,122,175,188],"train":[31],"well-calibrated":[33],"model":[34],"that":[35],"can":[36],"assess":[37],"the":[38,95,102,142,170],"uncertainty":[39],"and":[40,130],"diversity":[41],"unlabeled":[43],"However,":[45],"when":[46,109],"assembling":[47],"dataset,":[49],"are":[52],"often":[53,149],"scarce":[54],"initially,":[55],"leading":[56],"cold-start":[59],"problem.":[60],"Additionally,":[61],"most":[62],"seldom":[65],"address":[66,134],"data,":[68],"highlighting":[69],"research":[71,77],"gap":[72,120],"in":[73,151,177,185],"this":[74],"field.":[75],"Our":[76],"addresses":[78],"these":[79],"issues":[80],"by":[81],"developing":[82],"two-stage":[84],"method":[85],"for":[86],"Multi-Modal":[87],"Cold-Start":[88],"Learning":[90],"(MMCSAL).":[91],"Firstly,":[92],"we":[93,126,136,161],"observe":[94],"modality":[96,119,143],"gap,":[97],"significant":[99],"distance":[100],"between":[101,156],"centroids":[103],"representations":[105],"from":[106],"different":[107],"modalities,":[108],"only":[110],"using":[111],"cross-modal":[112,131,164],"pairing":[113],"information":[114],"as":[115,125],"self-supervision":[116],"signals.":[117],"This":[118],"affects":[121],"selection":[123],"process,":[124],"calculate":[127],"both":[128],"uni-modal":[129,138],"distances.":[132],"To":[133],"this,":[135],"introduce":[137],"prototypes":[139],"bridge":[141],"gap.":[144],"Secondly,":[145],"conventional":[146],"falter":[150],"scenarios":[153],"where":[154],"alignment":[155,165],"modalities":[157],"is":[158],"overlooked.":[159],"Therefore,":[160],"propose":[162],"enhancing":[163],"through":[166],"regularization,":[167],"thereby":[168],"improving":[169],"quality":[171],"selected":[173],"pairs":[176,189],"AL.":[178],"Finally,":[179],"our":[180],"experiments":[181],"demonstrate":[182],"MMCSAL's":[183],"efficacy":[184],"selecting":[186],"across":[190],"three":[191],"datasets.":[193]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2024-12-14T00:00:00"}