{"id":"https://openalex.org/W3193376721","doi":"https://doi.org/10.1145/3475722.3482791","title":"STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification","display_name":"STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3193376721","doi":"https://doi.org/10.1145/3475722.3482791","mag":"3193376721"},"language":"en","primary_location":{"id":"doi:10.1145/3475722.3482791","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3475722.3482791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.08362","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029167948","display_name":"Hasib Zunair","orcid":"https://orcid.org/0000-0002-5984-1731"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hasib Zunair","raw_affiliation_strings":["Concordia University, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039349647","display_name":"Yan Gobeil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Gobeil","raw_affiliation_strings":["D\u00e9cathlon, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D\u00e9cathlon, Montreal, QC, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089703583","display_name":"Samuel Mercier","orcid":"https://orcid.org/0000-0003-4912-8665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Mercier","raw_affiliation_strings":["D\u00e9cathlon, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D\u00e9cathlon, Montreal, QC, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Abdessamad Ben Hamza","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdessamad Ben Hamza","raw_affiliation_strings":["Concordia University, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8172563314437866},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7357304692268372},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6699770092964172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6485476493835449},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6481262445449829},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6369668245315552},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5531220436096191},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5401135683059692},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5114918947219849},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4500097930431366},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.44435542821884155},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.3968072831630707},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.29210638999938965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172563314437866},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7357304692268372},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6699770092964172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6485476493835449},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6481262445449829},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6369668245315552},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5531220436096191},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5401135683059692},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5114918947219849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4500097930431366},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.44435542821884155},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3968072831630707},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29210638999938965},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3475722.3482791","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3475722.3482791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.08362","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.08362","pdf_url":"https://arxiv.org/pdf/2108.08362","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3193376721","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2108.08362.pdf","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2108.08362","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.08362","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.08362","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.08362","pdf_url":"https://arxiv.org/pdf/2108.08362","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3193376721.pdf","grobid_xml":"https://content.openalex.org/works/W3193376721.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1500351990","https://openalex.org/W2048679005","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2111316763","https://openalex.org/W2136504847","https://openalex.org/W2149933564","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2943152387","https://openalex.org/W2955425717","https://openalex.org/W2963170156","https://openalex.org/W2963207607","https://openalex.org/W2963942586","https://openalex.org/W2964121744","https://openalex.org/W2982707468","https://openalex.org/W3035160371","https://openalex.org/W3099570996","https://openalex.org/W3103031651"],"related_works":["https://openalex.org/W3206707760","https://openalex.org/W2048120744","https://openalex.org/W3208365968","https://openalex.org/W2801728680","https://openalex.org/W3086580107","https://openalex.org/W3022146783","https://openalex.org/W3041610550","https://openalex.org/W2080848539","https://openalex.org/W3028227066","https://openalex.org/W3168921237","https://openalex.org/W3098250197","https://openalex.org/W3161622534","https://openalex.org/W3044331088","https://openalex.org/W3094784946","https://openalex.org/W3099025572","https://openalex.org/W2106981652","https://openalex.org/W3034453888","https://openalex.org/W3161583375","https://openalex.org/W2899992091","https://openalex.org/W3134565489"],"abstract_inverted_index":{"Semi-supervised":[0],"learning":[1,84,183],"(SSL)":[2],"has":[3],"proven":[4],"to":[5,13,22,46,125,142,177],"be":[6],"effective":[7],"at":[8,41],"leveraging":[9,161],"large-scale":[10],"unlabeled":[11,38,57,102,162],"data":[12,19,40,58,65,104],"mitigate":[14],"the":[15,122,135,144],"dependency":[16],"on":[17,37,105,114],"labeled":[18],"in":[20,59,172],"order":[21],"learn":[23],"better":[24],"models":[25],"for":[26,52,97,216],"visual":[27,169,209],"recognition":[28],"and":[29,64,85,117,155,196],"classification":[30,119,174,187,210],"tasks.":[31],"However,":[32],"recent":[33],"SSL":[34,79],"methods":[35],"rely":[36],"image":[39,103,129],"a":[42,91,106,147],"scale":[43,107],"of":[44,61,108,137,149,208],"billions":[45],"work":[47],"well.":[48],"This":[49],"becomes":[50],"infeasible":[51],"tasks":[53,98],"with":[54,87],"relatively":[55],"fewer":[56],"terms":[60],"runtime,":[62],"memory":[63],"acquisition.":[66],"To":[67],"address":[68],"this":[69],"issue,":[70],"we":[71],"propose":[72],"noisy":[73,88],"semi-supervised":[74],"transfer":[75,83,182],"learning,":[76],"an":[77,128],"efficient":[78],"approach":[80],"that":[81,99,159,203],"integrates":[82],"self-training":[86],"student":[89],"into":[90],"single":[92],"framework,":[93],"which":[94],"is":[95,124],"tailored":[96],"can":[100],"leverage":[101],"thousands.":[109],"We":[110,200],"evaluate":[111],"our":[112,164,204],"method":[113,205],"both":[115],"binary":[116],"multi-class":[118,173],"tasks,":[120],"where":[121],"objective":[123],"identify":[126,143],"whether":[127],"displays":[130],"people":[131],"practicing":[132],"sports":[133],"or":[134],"type":[136],"sport,":[138],"as":[139,141],"well":[140],"pose":[145],"from":[146],"pool":[148],"popular":[150],"yoga":[151],"poses.":[152],"Extensive":[153],"experiments":[154],"ablation":[156],"studies":[157],"demonstrate":[158],"by":[160],"data,":[163],"proposed":[165],"framework":[166],"significantly":[167],"improves":[168,186],"classification,":[170],"especially":[171],"settings":[175],"compared":[176],"state-of-the-art":[178],"methods.":[179],"Moreover,":[180],"incorporating":[181],"not":[184],"only":[185],"performance,":[188],"but":[189],"also":[190,201],"requires":[191],"6x":[192],"less":[193,198],"compute":[194],"time":[195],"5x":[197],"memory.":[199],"show":[202],"boosts":[206],"robustness":[207],"models,":[211],"even":[212],"without":[213],"specifically":[214],"optimizing":[215],"adversarial":[217],"robustness.":[218]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}