{"id":"https://openalex.org/W7130570102","doi":"https://doi.org/10.1109/ictc66702.2025.11388114","title":"Real-Time ViTPose Deployment via Progressive GPU Integration of DARK Post-Processing","display_name":"Real-Time ViTPose Deployment via Progressive GPU Integration of DARK Post-Processing","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130570102","doi":"https://doi.org/10.1109/ictc66702.2025.11388114"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","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/A5069647116","display_name":"Seon Ho Oh","orcid":"https://orcid.org/0000-0002-2927-7850"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seon Ho Oh","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Cyber Security Research Division,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Cyber Security Research Division,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100750091","display_name":"Sangwook Park","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangwook Park","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Cyber Security Research Division,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Cyber Security Research Division,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"459","last_page":"464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9447000026702881,"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":0.9447000026702881,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.007600000128149986,"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":0.0066999997943639755,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6908000111579895},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6657000184059143},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6456999778747559},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5507000088691711},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5214999914169312},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4878999888896942},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4537000060081482},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43389999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912999987602234},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6908000111579895},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6657000184059143},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6456999778747559},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4878999888896942},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4611999988555908},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4081999957561493},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3467000126838684},{"id":"https://openalex.org/C19527686","wikidata":"https://www.wikidata.org/wiki/Q1665453","display_name":"System integration","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","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":5,"referenced_works":["https://openalex.org/W2952122856","https://openalex.org/W3034742259","https://openalex.org/W3034750257","https://openalex.org/W3203925315","https://openalex.org/W4214508443"],"related_works":[],"abstract_inverted_index":{"Real-time":[0],"human":[1],"pose":[2],"estimation":[3],"for":[4,60,67],"multi-camera":[5],"systems":[6],"requires":[7],"near-millisecond":[8],"processing,":[9],"but":[10],"ViTPose":[11],"deployment":[12],"is":[13,27],"limited":[14],"by":[15,29],"CPU-based":[16,30],"post-processing":[17],"bottlenecks.":[18],"Traditional":[19],"implementations":[20],"create":[21],"hybrid":[22],"architectures":[23],"where":[24],"GPU-accelerated":[25],"inference":[26],"followed":[28],"DARK":[31,50,84],"post-processing,":[32],"leading":[33],"to":[34,52,94],"performance":[35,114],"degradation":[36,119],"and":[37,64],"GPU":[38,53,69],"underutilization.":[39],"This":[40],"paper":[41],"proposes":[42],"a":[43,78],"TensorRT":[44],"optimization":[45,80],"framework":[46],"that":[47],"systematically":[48],"migrates":[49],"operations":[51,85],"through":[54],"progressive":[55],"integration":[56,59,66],"strategies:":[57],"partial":[58],"balanced":[61],"workload":[62],"distribution":[63],"full":[65],"maximum":[68],"utilization.":[70],"Our":[71],"approach":[72],"treats":[73],"the":[74,121],"entire":[75],"pipeline":[76],"as":[77],"unified":[79],"target,":[81],"implementing":[82],"GPU-optimized":[83],"using":[86],"vectorized":[87],"CUDA":[88],"kernels.":[89],"Experimental":[90],"results":[91],"demonstrate":[92],"up":[93],"414.4%":[95],"improvement":[96],"over":[97],"PyTorch":[98],"baseline,":[99],"achieving":[100],"1909":[101],"queries":[102],"per":[103],"second":[104],"(QPS)":[105],"throughput":[106],"with":[107,116],"0.87ms":[108],"latency":[109],"while":[110],"maintaining":[111],"identical":[112],"AP":[113],"(76.9%)":[115],"no":[117],"accuracy":[118],"in":[120],"primary":[122],"evaluation":[123],"metric.":[124]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}