乐胖代购免代理版

{"id":"https://openalex.org/W4312639100","doi":"https://doi.org/10.1109/cvpr52688.2022.00806","title":"Balanced Multimodal Learning via On-the-fly Gradient Modulation","display_name":"Balanced Multimodal Learning via On-the-fly Gradient Modulation","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4312639100","doi":"https://doi.org/10.1109/cvpr52688.2022.00806"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.00806","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2203.15332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027985085","display_name":"Xiaokang Peng","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":"Xiaokang Peng","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006944766","display_name":"Yake Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yake Wei","raw_affiliation_strings":["Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016619434","display_name":"Andong Deng","orcid":"https://orcid.org/0000-0002-5606-4463"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andong Deng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391437","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0001-9457-263X"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai","institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I4210100255"]}]},{"author_position":"last","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":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing","institution_ids":["https://openalex.org/I78988378"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.162,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.999831,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8228","last_page":"8237"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9979,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9979,"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":0.9977,"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/T11309","display_name":"Music and Audio Processing","score":0.9952,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/modalities","display_name":"Modalities","score":0.6709212},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6405915},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5974166},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47101605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80632895},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6709212},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6405915},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5974166},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5725531},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5604401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50719357},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47704834},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47101605},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4333617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41003147},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.00806","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15332","pdf_url":"http://arxiv.org/pdf/2203.15332","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15332","pdf_url":"http://arxiv.org/pdf/2203.15332","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":44,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W189596042","https://openalex.org/W1933349210","https://openalex.org/W2030931454","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2474638510","https://openalex.org/W2507009361","https://openalex.org/W2619697695","https://openalex.org/W2619947201","https://openalex.org/W2753474648","https://openalex.org/W2760103357","https://openalex.org/W2768267830","https://openalex.org/W2890052321","https://openalex.org/W2895368507","https://openalex.org/W2962915600","https://openalex.org/W2963177640","https://openalex.org/W2964109005","https://openalex.org/W2967308614","https://openalex.org/W2970490659","https://openalex.org/W2971680695","https://openalex.org/W2977259558","https://openalex.org/W2982619606","https://openalex.org/W2990152177","https://openalex.org/W2990408345","https://openalex.org/W2990503944","https://openalex.org/W3002552512","https://openalex.org/W3005957673","https://openalex.org/W3015371781","https://openalex.org/W3015707499","https://openalex.org/W3025520547","https://openalex.org/W3034556939","https://openalex.org/W3034658206","https://openalex.org/W3035333188","https://openalex.org/W3105983073","https://openalex.org/W3170349722","https://openalex.org/W3174889475","https://openalex.org/W3175514052","https://openalex.org/W3176157254","https://openalex.org/W3196591432","https://openalex.org/W3206166878","https://openalex.org/W4256554223","https://openalex.org/W4287550992","https://openalex.org/W4293665662"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4320153225","https://openalex.org/W4307407935","https://openalex.org/W4293261942","https://openalex.org/W4224266612","https://openalex.org/W3125968744","https://openalex.org/W2383394264","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W203959209"],"abstract_inverted_index":{"Multimodal":[0],"learning":[1,114],"helps":[2],"to":[3,18,97,126],"comprehensively":[4],"understand":[5],"the":[6,34,100,107,113],"world,":[7],"by":[8,68,132],"integrating":[9],"different":[10,147],"senses.":[11],"Accordingly,":[12],"multiple":[13],"input":[14],"modalities":[15],"are":[16,28],"expected":[17],"boost":[19,156],"model":[20,36],"performance,":[21],"but":[22],"we":[23,45,92,138],"actually":[24],"find":[25],"that":[26,48,121],"they":[27],"not":[29],"fully":[30],"exploited":[31],"even":[32],"when":[33],"multimodal":[35,50,148,158],"outperforms":[37],"its":[38,162],"uni-modal":[39,65],"counterpart.":[40],"Specifically,":[41],"in":[42,53,72,77,82],"this":[43,89,151],"paper":[44],"point":[46],"out":[47],"existing":[49,157],"discriminative":[51],"models,":[52],"which":[54,160],"uniform":[55],"objective":[56],"is":[57,124,169],"designed":[58],"for":[59],"all":[60],"modalities,":[61],"could":[62],"remain":[63],"under-optimized":[64],"representations,":[66],"caused":[67,131],"another":[69],"dominated":[70],"modality":[71],"some":[73],"scenarios,":[74],"e.g.,":[75],"sound":[76],"blowing":[78],"wind":[79],"event,":[80,85],"vision":[81],"drawing":[83],"picture":[84],"etc.":[86],"To":[87],"alleviate":[88],"optimization":[90,101],"imbalance,":[91],"propose":[93],"on-the-fly":[94],"gradient":[95,133],"modulation":[96],"adaptively":[98],"control":[99],"of":[102,109],"each":[103],"modality,":[104],"via":[105],"monitoring":[106],"discrepancy":[108],"their":[110],"contribution":[111],"towards":[112],"objective.":[115],"Further,":[116],"an":[117],"extra":[118],"Gaussian":[119],"noise":[120],"changes":[122],"dynamically":[123],"introduced":[125],"avoid":[127],"possible":[128],"generalization":[129],"drop":[130],"modulation.":[134],"As":[135],"a":[136],"result,":[137],"achieve":[139],"considerable":[140],"improvement":[141],"over":[142],"common":[143],"fusion":[144],"methods":[145],"on":[146],"tasks,":[149],"and":[150,164],"simple":[152],"strategy":[153],"can":[154],"also":[155],"methods,":[159],"illustrates":[161],"efficacy":[163],"versatility.":[165],"The":[166],"source":[167],"code":[168],"available":[170],"at":[171],"https://github.com/GeWu-Lab/OGM-GE_CVPR2022.":[172]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4312639100","counts_by_year":[{"year":2024,"cited_by_count":62},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":7}],"updated_date":"2024-12-30T09:59:17.924388","created_date":"2023-01-05"}