{"id":"https://openalex.org/W4387968253","doi":"https://doi.org/10.1145/3581783.3612412","title":"ScaleFlow: Efficient Deep Vision Pipeline with Closed-Loop Scale-Adaptive Inference","display_name":"ScaleFlow: Efficient Deep Vision Pipeline with Closed-Loop Scale-Adaptive Inference","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968253","doi":"https://doi.org/10.1145/3581783.3612412"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612412","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612412","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612412","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612412","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048432270","display_name":"Yuyang Leng","orcid":"https://orcid.org/0009-0008-9376-0880"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuyang Leng","raw_affiliation_strings":["George Mason University, Fairfax, VA, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054692652","display_name":"Renyuan Liu","orcid":"https://orcid.org/0000-0001-9710-6116"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renyuan Liu","raw_affiliation_strings":["George Mason University, Fairfax, VA, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063851331","display_name":"Hongpeng Guo","orcid":"https://orcid.org/0000-0002-2714-7550"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongpeng Guo","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065505890","display_name":"Songqing Chen","orcid":"https://orcid.org/0000-0003-4650-7125"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songqing Chen","raw_affiliation_strings":["George Mason University, Fairfax, VA, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102736697","display_name":"Shuochao Yao","orcid":"https://orcid.org/0000-0001-7446-1430"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuochao Yao","raw_affiliation_strings":["George Mason University, Fairfax, VA, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048432270"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.3582,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60569795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1698","last_page":"1706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955999851226807,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9937999844551086,"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/inference","display_name":"Inference","score":0.8261703252792358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7950561046600342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6028633117675781},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5074631571769714},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5004005432128906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48015302419662476},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.47561389207839966},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4408392608165741},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43700963258743286},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42089781165122986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30071812868118286},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.139691561460495}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8261703252792358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950561046600342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6028633117675781},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5074631571769714},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5004005432128906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48015302419662476},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.47561389207839966},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4408392608165741},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43700963258743286},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42089781165122986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30071812868118286},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.139691561460495},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612412","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612412","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612412","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612412","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612412","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612412","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3013630393","display_name":"Collaborative Research: CPS: Medium: Real-time Criticality-Aware Neural Networks for Mission-critical Cyber-Physical Systems","funder_award_id":"2038658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3092819423","display_name":null,"funder_award_id":"CNS-2038658, IIS-2107200","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6234211897","display_name":null,"funder_award_id":"IIS-2107200","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6866416028","display_name":"Collaborative Research: CNS Core: Small: From Capture to Consumption: System Challenges in Pervasive 360-Degree Video Sharing","funder_award_id":"2007153","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7323781115","display_name":"III: Medium: Collaborative Research: Principled Uncertainty Quantification in Deep Learning Models for Time Series Analysis","funder_award_id":"2107200","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8869176546","display_name":null,"funder_award_id":"CNS-2038658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968253.pdf","grobid_xml":"https://content.openalex.org/works/W4387968253.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1546509353","https://openalex.org/W1861492603","https://openalex.org/W2300242332","https://openalex.org/W2570343428","https://openalex.org/W2586654419","https://openalex.org/W2754395205","https://openalex.org/W2886904239","https://openalex.org/W2913507876","https://openalex.org/W2945261895","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963521844","https://openalex.org/W2963611739","https://openalex.org/W2964121718","https://openalex.org/W2983038091","https://openalex.org/W2989604896","https://openalex.org/W3034971973","https://openalex.org/W3046256272","https://openalex.org/W3046754651","https://openalex.org/W3092663126","https://openalex.org/W3098691969","https://openalex.org/W3191321386","https://openalex.org/W3194790201","https://openalex.org/W4289305285","https://openalex.org/W4311007713","https://openalex.org/W6779679448"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2097707447","https://openalex.org/W3109712509","https://openalex.org/W3013760193","https://openalex.org/W3162668736","https://openalex.org/W4366999913","https://openalex.org/W4281678247","https://openalex.org/W4381489698","https://openalex.org/W3014007418","https://openalex.org/W3131458535"],"abstract_inverted_index":{"Deep":[0],"visual":[1],"data":[2,118,144,157],"processing":[3,116],"is":[4],"underpinning":[5],"many":[6],"life-changing":[7],"applications,":[8],"such":[9],"as":[10],"auto-driving":[11],"and":[12,183,199],"smart":[13],"cities.":[14],"Improving":[15],"the":[16,28,45,50,54,63,82,86,146],"accuracy":[17,87,194],"while":[18,81],"minimizing":[19],"their":[20,32],"inference":[21,60,107,112],"time":[22,113],"under":[23],"constrained":[24],"resources":[25],"has":[26,38],"been":[27,39,162],"primary":[29],"pursuit":[30],"for":[31,49,58],"practical":[33],"adoptions.":[34],"Existing":[35],"research":[36],"thus":[37],"devoted":[40],"to":[41,75,139,164,179],"either":[42],"narrowing":[43],"down":[44],"area":[46],"of":[47,148],"interest":[48],"detection":[51],"or":[52],"miniaturizing":[53],"deep":[55],"learning":[56],"model":[57,111],"faster":[59],"time.":[61],"However,":[62],"former":[64],"may":[65],"risk":[66],"missing/delaying":[67],"small":[68],"but":[69,122],"important":[70],"object":[71],"detection,":[72],"potentially":[73],"leading":[74],"disastrous":[76],"consequences":[77],"(e.g.,":[78],"car":[79],"accidents),":[80],"latter":[83],"often":[84],"compromises":[85],"without":[88,128],"fully":[89],"utilizing":[90],"intrinsic":[91],"semantic":[92],"information.":[93],"To":[94],"overcome":[95],"these":[96],"limitations,":[97],"in":[98],"this":[99,132],"work,":[100],"we":[101],"propose":[102],"ScaleFlow,":[103],"a":[104],"closed-loop":[105],"scale-adaptive":[106],"that":[108,170],"can":[109,172],"reduce":[110],"by":[114],"progressively":[115],"vision":[117],"with":[119,145,191],"increasing":[120],"resolution":[121],"decreasing":[123],"spatial":[124],"size,":[125],"achieving":[126],"speedup":[127],"compromising":[129],"accuracy.":[130],"For":[131],"purpose,":[133],"ScaleFlow":[134,171],"refactors":[135],"existing":[136],"neural":[137],"networks":[138],"be":[140],"scale-equivariant":[141],"on":[142,155,196],"multiresolution":[143],"assistance":[147],"wavelet":[149],"theory,":[150],"providing":[151],"predictable":[152],"feature":[153],"patterns":[154],"different":[156],"resolutions.":[158],"Comprehensive":[159],"experiments":[160],"have":[161],"conducted":[163],"evaluate":[165],"ScaleFlow.":[166],"The":[167],"results":[168],"show":[169],"support":[173],"anytime":[174],"inference,":[175],"consistently":[176],"provide":[177],"1.5\u00d7":[178],"2.2\u00d7":[180],"speed":[181],"up,":[182],"save":[184],"around":[185],"25%":[186],"~":[187],"45%":[188],"energy":[189],"consumption":[190],"<":[192],"1%":[193],"loss":[195],"four":[197],"embedded":[198],"edge":[200],"platforms":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}