{"id":"https://openalex.org/W4416150673","doi":"https://doi.org/10.1109/iccv51701.2025.01189","title":"Learning to Generalize Without Bias for Open-Vocabulary Action Recognition","display_name":"Learning to Generalize Without Bias for Open-Vocabulary Action Recognition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416150673","doi":"https://doi.org/10.1109/iccv51701.2025.01189"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","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/2502.20158","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102317329","display_name":"Yating Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yating Yu","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013382259","display_name":"Congqi Cao","orcid":"https://orcid.org/0000-0002-0217-9791"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congqi Cao","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376931","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0002-2125-1074"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101590880","display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-3839-2965"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37931355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12800","last_page":"12810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.7652000188827515,"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":0.7652000188827515,"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":0.18019999563694,"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/T12290","display_name":"Human Motion and Animation","score":0.007499999832361937,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/debiasing","display_name":"Debiasing","score":0.8245000243186951},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6462000012397766},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5735999941825867},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5375999808311462},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5338000059127808},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4677000045776367},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.44440001249313354},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4302999973297119}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.8245000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195000052452087},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6462000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5735999941825867},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5375999808311462},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4977000057697296},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.20158","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20158","pdf_url":"https://arxiv.org/pdf/2502.20158","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.20158","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.20158","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.20158","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20158","pdf_url":"https://arxiv.org/pdf/2502.20158","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G327371728","display_name":null,"funder_award_id":"62376217,62273347,62301434","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Leveraging":[0],"the":[1,31,124,133,138,146],"effective":[2],"visual-text":[3],"alignment":[4],"and":[5,88,162],"static":[6,32,44,67,135],"generalizability":[7],"from":[8],"CLIP,":[9,35],"recent":[10],"video":[11,37,105,139],"learners":[12,38,106],"adopt":[13],"CLIP":[14,127],"initialization":[15],"with":[16,66],"further":[17,142],"regularization":[18,128,175],"or":[19],"recombination":[20],"for":[21,69,178],"generalization":[22,158],"in":[23,91,187],"open-vocabulary":[24,180],"action":[25,71,181],"recognition":[26,182],"in-context.":[27],"However,":[28],"due":[29],"to":[30,40,51,84,107,110,149,159],"bias":[33,136],"of":[34,77,126,137],"such":[36],"tend":[39],"overfit":[41],"on":[42],"shortcut":[43],"features,":[45],"thereby":[46],"compromising":[47],"their":[48],"generalizability,":[49],"especially":[50],"novel":[52,63,164],"out-of-context":[53,163,188],"actions.":[54],"To":[55],"address":[56],"this":[57],"issue,":[58],"we":[59],"introduce":[60],"Open-MeDe,":[61],"a":[62,74,81,92,98,118],"Meta-optimization":[64],"framework":[65],"Debiasing":[68],"Open-vocabulary":[70],"recognition.":[72],"From":[73],"fresh":[75],"perspective":[76],"generalization,":[78],"Open-MeDe":[79,96,170],"adopts":[80],"meta-learning":[82],"approach":[83],"improve":[85],"known-to-open":[86],"generalizing":[87],"image-to-video":[89],"debiasing":[90],"cost-effective":[93],"manner.":[94],"Specifically,":[95],"introduces":[97],"cross-batch":[99],"meta-optimization":[100],"scheme":[101],"that":[102,154,169],"explicitly":[103],"encourages":[104],"quickly":[108],"generalize":[109],"arbitrary":[111],"subsequent":[112],"data":[113],"via":[114],"virtual":[115],"evaluation,":[116],"steering":[117],"smoother":[119],"optimization":[120,130,147],"landscape.":[121],"In":[122],"effect,":[123],"free":[125],"during":[129],"implicitly":[131],"mitigates":[132],"inherent":[134],"meta-learner.":[140],"We":[141],"apply":[143],"self-ensemble":[144],"over":[145],"trajectory":[148],"obtain":[150],"generic":[151],"optimal":[152],"parameters":[153],"can":[155],"achieve":[156],"robust":[157],"both":[160],"in-context":[161,179],"data.":[165],"Extensive":[166],"evaluations":[167],"show":[168],"not":[171],"only":[172],"surpasses":[173],"state-of-the-art":[174],"methods":[176],"tailored":[177],"but":[183],"also":[184],"substantially":[185],"excels":[186],"scenarios.Code":[189],"is":[190],"released":[191],"at":[192],"https://github.com/Mia-YatingYu/Open-MeDe.":[193]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}