{"id":"https://openalex.org/W4402916063","doi":"https://doi.org/10.1109/icip51287.2024.10647522","title":"Improving Self-Supervised Vision Transformers for Visual Control","display_name":"Improving Self-Supervised Vision Transformers for Visual Control","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402916063","doi":"https://doi.org/10.1109/icip51287.2024.10647522"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647522","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647522","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 Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","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/A5065362742","display_name":"Wonil Song","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonil Song","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073320959","display_name":"Kwanghoon Sohn","orcid":"https://orcid.org/0000-0002-3715-0331"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanghoon Sohn","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037006973","display_name":"Dongbo Min","orcid":"https://orcid.org/0000-0003-4825-5240"},"institutions":[{"id":"https://openalex.org/I4210132203","display_name":"Ewha Womans University Medical Center","ror":"https://ror.org/03exgrk66","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I138925566","https://openalex.org/I4210132203"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongbo Min","raw_affiliation_strings":["Ewha Womans University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ewha Womans University","institution_ids":["https://openalex.org/I4210132203"]}]}],"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":0.13157843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1302","last_page":"1308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9258000254631042,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9258000254631042,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9039999842643738,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.6653642654418945},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.583223283290863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.571459949016571},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5005030632019043},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1860562264919281},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.14336341619491577},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08380559086799622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653642654418945},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.583223283290863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.571459949016571},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5005030632019043},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1860562264919281},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.14336341619491577},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08380559086799622}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647522","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647522","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 Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2150468603","https://openalex.org/W2761873684","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2787666871","https://openalex.org/W2842511635","https://openalex.org/W2899663614","https://openalex.org/W2920362155","https://openalex.org/W2944828972","https://openalex.org/W2952867909","https://openalex.org/W3005173720","https://openalex.org/W3005680577","https://openalex.org/W3015437096","https://openalex.org/W3021708257","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3094502228","https://openalex.org/W3115293622","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3164024107","https://openalex.org/W3166052165","https://openalex.org/W3170863103","https://openalex.org/W3170874841","https://openalex.org/W3175558129","https://openalex.org/W3186672455","https://openalex.org/W4224314580","https://openalex.org/W4226167593","https://openalex.org/W4287667696","https://openalex.org/W4287724327","https://openalex.org/W4287811291","https://openalex.org/W4297808394","https://openalex.org/W4298857966","https://openalex.org/W4312446817","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6739901393","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6755977528","https://openalex.org/W6760405395","https://openalex.org/W6762573206","https://openalex.org/W6773738434","https://openalex.org/W6774314701","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6779326418","https://openalex.org/W6780226713","https://openalex.org/W6780470247","https://openalex.org/W6782858274","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6795475546","https://openalex.org/W6796367035","https://openalex.org/W6796761347","https://openalex.org/W6799458897","https://openalex.org/W6810655313","https://openalex.org/W6810968573"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Despite":[0],"the":[1,17,35,38,56,91,135,156,167,171],"tremendous":[2],"success":[3],"of":[4,13,19,37,59,122,184],"vision":[5,15],"transformer":[6],"(ViT)":[7],"architectures":[8],"in":[9,41,78,94,181,187],"a":[10,46,60],"broad":[11],"range":[12],"computer":[14,95],"tasks,":[16],"potential":[18],"ViT":[20,39,62,136,175],"for":[21,51,85],"vision-based":[22],"deep":[23],"reinforcement":[24],"learning":[25,53,132],"(RL)":[26],"has":[27],"not":[28],"been":[29],"fully":[30],"explored":[31],"yet.":[32],"To":[33,75],"improve":[34],"performance":[36,180],"model":[40],"visual":[42,113],"RL,":[43],"we":[44,97,164],"propose":[45],"simple":[47],"yet":[48],"effective":[49],"approach":[50,129,169],"self-supervised":[52,108],"by":[54],"utilizing":[55],"structural":[57],"capability":[58],"single":[61],"model,":[63],"which":[64,88],"can":[65],"learn":[66,112,141],"multiple,":[67],"distinct":[68],"representations":[69,144],"through":[70,126],"extra":[71,100,124],"learnable":[72],"token":[73,83,93],"embeddings.":[74],"this":[76],"end,":[77],"addition":[79],"to":[80,90,105,111,134,140,148],"an":[81],"RL":[82,86,149],"used":[84],"input,":[87],"corresponds":[89],"classification":[92],"vision,":[96],"introduce":[98],"additional":[99,131],"tokens":[101,125],"that":[102,145,166,173],"are":[103,146],"tailored":[104],"two":[106],"auxiliary":[107],"tasks":[109,186],"specialized":[110],"and":[114,161],"environmental":[115],"dynamics":[116],"representations.":[117],"By":[118],"interacting":[119],"with":[120],"embeddings":[121],"these":[123],"self-attention,":[127],"our":[128],"provides":[130],"signals":[133],"encoder,":[137],"enabling":[138],"it":[139],"more":[142],"comprehensive":[143],"beneficial":[147],"tasks.":[150],"In":[151],"experiments":[152],"on":[153],"benchmarks":[154],"including":[155],"DeepMind":[157],"Control":[158],"Suite":[159],"(DMControl)":[160],"Atari":[162],"games,":[163],"demonstrate":[165],"proposed":[168],"outperforms":[170],"baselines":[172],"utilize":[174],"encoders,":[176],"particularly":[177],"achieving":[178],"state-of-the-art":[179],"4":[182],"out":[183],"5":[185],"DMControl.":[188]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}