{"id":"https://openalex.org/W7130339596","doi":"https://doi.org/10.1109/tencon66050.2025.11375402","title":"Action-Aligned Video Pairing for Video Augmentation","display_name":"Action-Aligned Video Pairing for Video Augmentation","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W7130339596","doi":"https://doi.org/10.1109/tencon66050.2025.11375402"},"language":null,"primary_location":{"id":"doi:10.1109/tencon66050.2025.11375402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon66050.2025.11375402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2025 - 2025 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072934751","display_name":"Randy Cahya Wihandika","orcid":"https://orcid.org/0000-0001-8696-5687"},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Cahya Wihandika","raw_affiliation_strings":["Graduate School of Science and Technology, Kumamoto University,Kumamoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, Kumamoto University,Kumamoto,Japan","institution_ids":["https://openalex.org/I96036126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018027076","display_name":"Israel Mendon\u00e7a","orcid":"https://orcid.org/0000-0001-6819-4305"},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Israel Mendon\u00e7a","raw_affiliation_strings":["Kumamoto University,Faculty of Advanced Science and Technology,Kumamoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kumamoto University,Faculty of Advanced Science and Technology,Kumamoto,Japan","institution_ids":["https://openalex.org/I96036126"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010583900","display_name":"Masayoshi Aritsugi","orcid":"https://orcid.org/0000-0003-0861-849X"},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayoshi Aritsugi","raw_affiliation_strings":["Kumamoto University,Faculty of Advanced Science and Technology,Kumamoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kumamoto University,Faculty of Advanced Science and Technology,Kumamoto,Japan","institution_ids":["https://openalex.org/I96036126"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96036126"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64167867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1003","last_page":"1007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9635000228881836,"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":0.9635000228881836,"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":0.006099999882280827,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004999999888241291,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5414000153541565},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.46129998564720154},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.385699987411499},{"id":"https://openalex.org/keywords/pairing","display_name":"Pairing","score":0.3815000057220459},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.37229999899864197},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.36410000920295715},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.34439998865127563},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.329800009727478},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3237999975681305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982000112533569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5882999897003174},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5414000153541565},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5343999862670898},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.46129998564720154},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.3815000057220459},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.37229999899864197},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.34439998865127563},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.32359999418258667},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.29820001125335693},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C143184774","wikidata":"https://www.wikidata.org/wiki/Q3020846","display_name":"Deblocking filter","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2741999924182892},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.26190000772476196},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon66050.2025.11375402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon66050.2025.11375402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2025 - 2025 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W1522734439","https://openalex.org/W1861492603","https://openalex.org/W2016053056","https://openalex.org/W2126579184","https://openalex.org/W2963524571","https://openalex.org/W2992308087","https://openalex.org/W3089800122","https://openalex.org/W4309770473","https://openalex.org/W4312264488","https://openalex.org/W4312319992","https://openalex.org/W4312655706","https://openalex.org/W4389160174","https://openalex.org/W4390872963","https://openalex.org/W4396742831","https://openalex.org/W4404893151","https://openalex.org/W4415797934"],"related_works":[],"abstract_inverted_index":{"Video":[0],"augmentation":[1,17,56],"is":[2,146],"an":[3],"effective":[4,111],"strategy":[5,18,57],"for":[6],"improving":[7],"the":[8,30,43,71,91,132],"performance":[9],"of":[10,73,93],"action":[11],"recognition":[12],"models.":[13],"A":[14],"recent":[15],"video":[16,28,44,55,62],"addresses":[19],"scene":[20],"bias":[21],"by":[22,118],"mixing":[23,45],"human":[24],"regions":[25],"from":[26,32],"one":[27],"with":[29],"background":[31],"another.":[33],"However,":[34],"this":[35,86],"often":[36],"produces":[37,59],"artifacts":[38,95],"due":[39],"to":[40,69,84,88,109,124],"limitations":[41],"in":[42],"process,":[46],"which":[47,107],"degrade":[48],"training":[49],"quality.":[50],"This":[51],"study":[52],"proposes":[53],"a":[54,120],"that":[58,139],"compatible":[60],"action-scene":[61],"pairs":[63],"rather":[64],"than":[65],"choosing":[66],"them":[67],"randomly,":[68],"improve":[70,125],"quality":[72],"mixed":[74],"videos.":[75,100],"To":[76],"achieve":[77],"this,":[78],"two":[79],"compatibility":[80],"metrics":[81],"are":[82,115],"introduced":[83],"guide":[85],"selection":[87],"significantly":[89],"reduce":[90],"occurrence":[92],"visual":[94],"and":[96,135],"generate":[97],"higher-quality":[98],"augmented":[99],"Our":[101],"method":[102],"improves":[103,142],"alignment":[104],"between":[105],"actions":[106],"leads":[108],"more":[110],"augmentation.":[112],"The":[113],"performances":[114],"further":[116],"enhanced":[117],"applying":[119],"temporal":[121],"morphological":[122],"operation":[123],"object":[126],"detection":[127],"consistency.":[128],"Experimental":[129],"results":[130],"on":[131],"UCF101,":[133],"HMDB51,":[134],"Kinetics-100":[136],"datasets":[137],"show":[138],"our":[140],"approach":[141],"classification":[143],"performance.":[144],"Code":[145],"available":[147],"at":[148],"https://github.com/rendicahya/video-action-alignment.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-19T00:00:00"}