{"id":"https://openalex.org/W4401991256","doi":"https://doi.org/10.1109/icmew63481.2024.10645477","title":"Self-Supervised Learning via Multi-Transformation Classification for Action Recognition","display_name":"Self-Supervised Learning via Multi-Transformation Classification for Action Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401991256","doi":"https://doi.org/10.1109/icmew63481.2024.10645477"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew63481.2024.10645477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5001193118","display_name":"Duc-Quang Vu","orcid":"https://orcid.org/0000-0001-5458-3713"},"institutions":[{"id":"https://openalex.org/I4210115718","display_name":"Thai Nguyen University","ror":"https://ror.org/02128gy91","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210115718"]},{"id":"https://openalex.org/I4387154701","display_name":"Thai Nguyen University Of Education","ror":"https://ror.org/044deqz63","country_code":null,"type":"education","lineage":["https://openalex.org/I4387154701"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duc-Quang Vu","raw_affiliation_strings":["Thai Nguyen University of Education,Dept. of CSIS,Thai Nguyen,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thai Nguyen University of Education,Dept. of CSIS,Thai Nguyen,Vietnam","institution_ids":["https://openalex.org/I4210115718","https://openalex.org/I4387154701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023725893","display_name":"Ngan Le","orcid":"https://orcid.org/0000-0003-2571-0511"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ngan Le","raw_affiliation_strings":["University of Arkansas,Dept. of CSCE,Fayetteville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas,Dept. of CSCE,Fayetteville,USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029325015","display_name":"Jia\u2010Ching Wang","orcid":"https://orcid.org/0000-0003-0024-6732"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Ching Wang","raw_affiliation_strings":["National Central University,Dept. of CSIE,Taoyuan,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Central University,Dept. of CSIE,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.7599098682403564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.605481743812561},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5770620107650757},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5464455485343933},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49309250712394714},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48427242040634155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38706251978874207},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.08949041366577148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599098682403564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.605481743812561},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5770620107650757},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5464455485343933},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49309250712394714},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48427242040634155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38706251978874207},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.08949041366577148},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":1,"locations":[{"id":"doi:10.1109/icmew63481.2024.10645477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew63481.2024.10645477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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":37,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2326925005","https://openalex.org/W2487442924","https://openalex.org/W2550462002","https://openalex.org/W2615413256","https://openalex.org/W2798271879","https://openalex.org/W2851061873","https://openalex.org/W2888101838","https://openalex.org/W2902671786","https://openalex.org/W2948242301","https://openalex.org/W2962824366","https://openalex.org/W2962931121","https://openalex.org/W2962934715","https://openalex.org/W2963524571","https://openalex.org/W2963631366","https://openalex.org/W2963814513","https://openalex.org/W2964037671","https://openalex.org/W2980927909","https://openalex.org/W2981385151","https://openalex.org/W2981862717","https://openalex.org/W2982198876","https://openalex.org/W3010874390","https://openalex.org/W3015213852","https://openalex.org/W3099025572","https://openalex.org/W3108655343","https://openalex.org/W3186221976","https://openalex.org/W4206215724","https://openalex.org/W4206488443","https://openalex.org/W4297697565","https://openalex.org/W4312575985","https://openalex.org/W4375868819","https://openalex.org/W4387448039","https://openalex.org/W4390535256","https://openalex.org/W6738465933","https://openalex.org/W6752941011"],"related_works":["https://openalex.org/W2353644209","https://openalex.org/W2961085424","https://openalex.org/W2593663830","https://openalex.org/W2348743188","https://openalex.org/W2902317490","https://openalex.org/W2463239216","https://openalex.org/W4387423451","https://openalex.org/W2025460258","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Self-supervised":[0,42],"tasks":[1,15,135],"have":[2,152,173],"been":[3],"utilized":[4,113],"to":[5,37,61,103,114,124,143],"build":[6],"useful":[7],"representations":[8],"that":[9,175],"can":[10],"be":[11],"used":[12],"in":[13,72,133,147],"downstream":[14,149],"when":[16],"the":[17,34,56,62,68,107,126,130,137,148,154],"annotation":[18],"is":[19,70],"unavailable.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"introduce":[25],"a":[26,73],"self-supervised":[27,74,182],"video":[28,69,99,104],"representation":[29,58,66],"learning":[30,43],"method":[31],"based":[32],"on":[33,44,156],"multi-transformation":[35],"classification":[36],"efficiently":[38],"classify":[39,125],"human":[40,145],"actions.":[41],"various":[45],"transformations":[46,80,100],"not":[47],"only":[48],"provides":[49],"richer":[50],"contextual":[51],"information":[52],"but":[53],"also":[54],"enables":[55],"visual":[57],"more":[59],"robust":[60],"transforms.":[63],"The":[64,170],"spatio-temporal":[65],"of":[67],"learned":[71,131],"manner":[75],"by":[76],"classifying":[77],"seven":[78,97],"different":[79,98],"i.e.":[81],"rotation,":[82],"clip":[83],"inversion,":[84],"permutation,":[85],"split,":[86],"join":[87],"transformation,":[88],"color":[89],"switch,":[90],"frame":[91],"replacement,":[92],"and":[93,119,140,158,164],"noise":[94],"addition.":[95],"First,":[96],"are":[101,112,122],"applied":[102],"clips.":[105],"Then":[106],"3D":[108,165],"convolutional":[109],"neural":[110],"networks":[111],"extract":[115],"features":[116,121],"for":[117],"clips":[118],"these":[120],"processed":[123],"pseudo-labels.":[127],"We":[128,151],"use":[129],"models":[132,139],"pretext":[134],"as":[136,167],"pre-trained":[138],"fine-tune":[141],"them":[142],"recognize":[144],"actions":[146],"task.":[150],"conducted":[153],"experiments":[155],"UCF101":[157],"HMDB51":[159],"datasets":[160],"together":[161],"with":[162],"C3D":[163],"Resnet-18":[166],"backbone":[168],"networks.":[169],"experimental":[171],"results":[172],"shown":[174],"our":[176],"proposed":[177],"framework":[178],"outperformed":[179],"other":[180],"SOTA":[181],"action":[183],"recognition":[184],"approaches.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}