{"id":"https://openalex.org/W7225246984","doi":"https://doi.org/10.3390/app162110920","title":"Action-Region Mixing: A Video Augmentation Approach for Reducing Scene Bias in Action Recognition","display_name":"Action-Region Mixing: A Video Augmentation Approach for Reducing Scene Bias in Action Recognition","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225246984","doi":"https://doi.org/10.3390/app162110920"},"language":"en","primary_location":{"id":"doi:10.3390/app162110920","doi":"https://doi.org/10.3390/app162110920","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162110920","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/app162110920","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139165869","display_name":"Asl\u0131 \u00c7elik","orcid":"https://orcid.org/0000-0003-1874-6743","observed_orcids":["https://orcid.org/0000-0003-1874-6743"]},"institutions":[{"id":"https://openalex.org/I51826884","display_name":"Kocaeli \u00dcniversitesi","ror":"https://ror.org/0411seq30","country_code":"TR","type":"education","lineage":["https://openalex.org/I51826884"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Asl\u0131 \u00c7elik","raw_affiliation_strings":["Department of Electronics and Communication Engineering, Kocaeli University, Kocaeli 41001, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-1874-6743","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, Kocaeli University, Kocaeli 41001, Turkey","institution_ids":["https://openalex.org/I51826884"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146468666","display_name":"T\u00fcrkay Yildirim","orcid":"https://orcid.org/0009-0004-0393-2097","observed_orcids":["https://orcid.org/0009-0004-0393-2097"]},"institutions":[{"id":"https://openalex.org/I51826884","display_name":"Kocaeli \u00dcniversitesi","ror":"https://ror.org/0411seq30","country_code":"TR","type":"education","lineage":["https://openalex.org/I51826884"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"T\u00fcrkay Y\u0131ld\u0131r\u0131m","raw_affiliation_strings":["Department of Electronics and Communication Engineering, Kocaeli University, Kocaeli 41001, Turkey"],"raw_orcid":"https://orcid.org/0009-0004-0393-2097","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, Kocaeli University, Kocaeli 41001, Turkey","institution_ids":["https://openalex.org/I51826884"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086588942","display_name":"O\u011fuzhan Urhan","orcid":"https://orcid.org/0000-0002-0352-1560","observed_orcids":["https://orcid.org/0000-0002-0352-1560"]},"institutions":[{"id":"https://openalex.org/I51826884","display_name":"Kocaeli \u00dcniversitesi","ror":"https://ror.org/0411seq30","country_code":"TR","type":"education","lineage":["https://openalex.org/I51826884"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"O\u011fuzhan Urhan","raw_affiliation_strings":["Department of Electronics and Communication Engineering, Kocaeli University, Kocaeli 41001, Turkey","EVSTEK Bilisim Teknolojileri A.S., KOU Teknopark, Kocaeli 41275, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-0352-1560","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, Kocaeli University, Kocaeli 41001, Turkey","institution_ids":["https://openalex.org/I51826884"]},{"raw_affiliation_string":"EVSTEK Bilisim Teknolojileri A.S., KOU Teknopark, Kocaeli 41275, Turkey","institution_ids":["https://openalex.org/I51826884"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5139165869"],"corresponding_institution_ids":["https://openalex.org/I51826884"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79476048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"21","first_page":"10920","last_page":"10920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9970999956130981,"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":0.9970999956130981,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.0003000000142492354,"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/video-action-recognition","display_name":"video action recognition","score":0.9679999947547913},{"id":"https://openalex.org/keywords/video-augmentation","display_name":"video augmentation","score":0.7580000162124634},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9539999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804099977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6953999996185303},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6040999889373779},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6010000109672546},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3937999904155731},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.38350000977516174},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/app162110920","doi":"https://doi.org/10.3390/app162110920","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162110920","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/app162110920","doi":"https://doi.org/10.3390/app162110920","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162110920","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2016053056","https://openalex.org/W2126579184","https://openalex.org/W2507009361","https://openalex.org/W2619082050","https://openalex.org/W2625366777","https://openalex.org/W2962934715","https://openalex.org/W2963150697","https://openalex.org/W2991727786","https://openalex.org/W2992308087","https://openalex.org/W3147387781","https://openalex.org/W4220710236","https://openalex.org/W4309770473","https://openalex.org/W4312264488","https://openalex.org/W4396681775","https://openalex.org/W4402727018","https://openalex.org/W4402754134","https://openalex.org/W4411472234","https://openalex.org/W4413145364","https://openalex.org/W4415798953","https://openalex.org/W7172399305"],"related_works":["https://openalex.org/W4309125512","https://openalex.org/W7130339596","https://openalex.org/W3111762767","https://openalex.org/W4411472234","https://openalex.org/W7124564048","https://openalex.org/W4312264488","https://openalex.org/W4392402474","https://openalex.org/W4366307892","https://openalex.org/W7163989705","https://openalex.org/W2394840239"],"abstract_inverted_index":{"Video":[0],"action":[1,105],"recognition":[2,136],"models":[3],"can":[4],"rely":[5,42],"heavily":[6],"on":[7,43,127,174],"recurring":[8],"scene":[9,34],"context":[10],"rather":[11],"than":[12],"action-relevant":[13,124],"cues,":[14],"limiting":[15],"their":[16],"generalization":[17],"to":[18,53,91,167],"background":[19,63,169],"changes.":[20],"foreground\u2013background":[21],"mixing":[22,39,157],"has":[23],"therefore":[24],"emerged":[25],"as":[26,158],"a":[27,76,84,159,164],"useful":[28],"augmentation":[29,80,147,161],"strategy":[30],"for":[31],"reducing":[32],"such":[33],"dependence.":[35],"However,":[36],"existing":[37],"semantic":[38,146],"approaches":[40],"typically":[41],"off-the-shelf":[44],"object":[45],"detectors":[46],"and":[47,50,111,129,142,171],"associated":[48],"preprocessing":[49],"postprocessing":[51],"pipelines":[52],"localize":[54],"action-related":[55,93],"regions,":[56],"while":[57,122],"bounding-box-based":[58,145],"representations":[59],"may":[60],"introduce":[61],"unrelated":[62],"content":[64],"into":[65],"the":[66,96,139,143,152],"mixed":[67],"samples.":[68],"To":[69],"address":[70],"these":[71],"limitations,":[72],"we":[73],"propose":[74],"ActionRegionMix,":[75],"prompt-guided,":[77],"action-aware":[78],"video":[79,160],"framework":[81],"that":[82,132],"leverages":[83],"mask-generating":[85],"Multimodal":[86],"Large":[87],"Language":[88],"Model":[89],"(MLLM)":[90],"extract":[92],"regions":[94,106],"at":[95],"pixel":[97],"level":[98],"in":[99],"an":[100],"open-vocabulary":[101],"manner.":[102],"The":[103],"extracted":[104],"are":[107],"transferred":[108],"across":[109],"videos":[110],"composited":[112],"with":[113],"backgrounds":[114],"from":[115],"other":[116],"training":[117],"samples,":[118],"introducing":[119],"contextual":[120],"variation":[121],"preserving":[123],"content.":[125],"Experiments":[126],"UCF101":[128],"HMDB51":[130],"show":[131],"ActionRegionMix":[133],"consistently":[134],"improves":[135],"performance":[137],"over":[138],"no-augmentation":[140],"baseline":[141],"compared":[144],"methods.":[148],"These":[149],"results":[150],"demonstrate":[151],"effectiveness":[153],"of":[154],"pixel-level":[155],"action-region":[156],"strategy,":[162],"offering":[163],"promising":[165],"approach":[166],"enhance":[168],"diversity":[170],"mitigate":[172],"reliance":[173],"scene-specific":[175],"cues.":[176]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}