{"id":"https://openalex.org/W3175158881","doi":"https://doi.org/10.1145/3469116.3470010","title":"Benchmarking Video Object Detection Systems on Embedded Devices under Resource Contention","display_name":"Benchmarking Video Object Detection Systems on Embedded Devices under Resource Contention","publication_year":2021,"publication_date":"2021-06-24","ids":{"openalex":"https://openalex.org/W3175158881","doi":"https://doi.org/10.1145/3469116.3470010","mag":"3175158881"},"language":"en","primary_location":{"id":"doi:10.1145/3469116.3470010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3469116.3470010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3469116.3470010","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3469116.3470010","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102943714","display_name":"Jayoung Lee","orcid":"https://orcid.org/0000-0002-1011-6002"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayoung Lee","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441284","display_name":"Pengcheng Wang","orcid":"https://orcid.org/0000-0002-2797-6973"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengcheng Wang","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056643573","display_name":"Ran Xu","orcid":"https://orcid.org/0000-0003-2913-9420"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ran Xu","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027071723","display_name":"Venkat Dasari","orcid":"https://orcid.org/0000-0001-9795-6567"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkat Dasari","raw_affiliation_strings":["Army Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Research Lab","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058132819","display_name":"Noah Weston","orcid":"https://orcid.org/0000-0002-2152-8854"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah Weston","raw_affiliation_strings":["Army Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Research Lab","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451141","display_name":"Yin Li","orcid":"https://orcid.org/0000-0003-4173-9453"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin Li","raw_affiliation_strings":["University of Wisconsin at Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin at Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310442","display_name":"Saurabh Bagchi","orcid":"https://orcid.org/0000-0002-4239-5632"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Bagchi","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055585728","display_name":"Somali Chaterji","orcid":"https://orcid.org/0000-0002-3651-6362"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Somali Chaterji","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9983000159263611,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8376493453979492},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6742581129074097},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5155732035636902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48258745670318604},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4771127998828888},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.46630656719207764},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46196433901786804},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.45079827308654785},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44565722346305847},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4305873513221741},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.40676602721214294},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.36169761419296265},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.360181987285614},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1532864272594452},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.12923681735992432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376493453979492},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6742581129074097},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5155732035636902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48258745670318604},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4771127998828888},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.46630656719207764},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46196433901786804},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.45079827308654785},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44565722346305847},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4305873513221741},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40676602721214294},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36169761419296265},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.360181987285614},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1532864272594452},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.12923681735992432},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3469116.3470010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3469116.3470010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3469116.3470010","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3469116.3470010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3469116.3470010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3469116.3470010","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G7104039644","display_name":null,"funder_award_id":"W911NF-20-2-0026","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3175158881.pdf","grobid_xml":"https://content.openalex.org/works/W3175158881.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2165737454","https://openalex.org/W2407521645","https://openalex.org/W2897268228","https://openalex.org/W2954611552","https://openalex.org/W2963037989","https://openalex.org/W2963163009","https://openalex.org/W2963786238","https://openalex.org/W2971861286","https://openalex.org/W2990578161","https://openalex.org/W2994810768","https://openalex.org/W3034467781","https://openalex.org/W3034971973","https://openalex.org/W3035414587","https://openalex.org/W3046498456","https://openalex.org/W3088055053","https://openalex.org/W3103203826","https://openalex.org/W3106250896","https://openalex.org/W3107788976","https://openalex.org/W3176147180","https://openalex.org/W3203251378","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W3034529322","https://openalex.org/W2113597336","https://openalex.org/W2115913271","https://openalex.org/W2004851054","https://openalex.org/W2965594636","https://openalex.org/W1875422203","https://openalex.org/W4310880131","https://openalex.org/W2912550626","https://openalex.org/W3216382677","https://openalex.org/W2810129309"],"abstract_inverted_index":{"Adaptive":[0],"and":[1,17,101,127,207,214,253,265],"efficient":[2,42],"computer":[3,11],"vision":[4,12],"systems":[5],"have":[6,167],"been":[7],"proposed":[8],"to":[9,98,147,168,173,188,259],"make":[10],"tasks,":[13],"e.g.,":[14],"object":[15,18,61,66,74,80,91,157,165,225],"classification":[16],"detection,":[19],"optimized":[20],"for":[21],"embedded":[22,107],"boards":[23,108],"or":[24,36,45],"mobile":[25,114],"devices.":[26],"These":[27],"studies":[28],"focus":[29],"on":[30,104,150,191],"optimizing":[31],"the":[32,47,65,111,155,177,192,222,230,260],"model":[33],"(deep":[34],"network)":[35],"system":[37],"itself,":[38],"by":[39],"designing":[40],"an":[41],"network":[43,48],"architecture":[44,49],"adapting":[46],"at":[50,234],"runtime":[51],"using":[52],"approximation":[53],"knobs,":[54],"such":[55,71],"as":[56,72,143],"image":[57],"size,":[58],"type":[59],"of":[60,64,118,121,137,237],"tracker,":[62],"head":[63],"detector":[67],"(e.g.,":[68,180],"lighter-weight":[69],"heads":[70],"one-shot":[73],"detectors":[75,81,166],"like":[76,82,204],"YOLO":[77,208,255],"over":[78,238],"two-shot":[79],"FRCNN).":[83],"In":[84],"this":[85],"work,":[86],"we":[87,130],"benchmark":[88],"different":[89,106,135],"video":[90,156,224],"detection":[92,158,226],"protocols,":[93],"including":[94],"FastAdapt,":[95,205,250],"with":[96,154,171,176],"respect":[97],"accuracy,":[99],"latency,":[100],"energy":[102,244],"consumption":[103,245],"three":[105],"that":[109,164,249],"represent":[110],"leading":[112],"edge":[113],"GPUs.":[115],"Our":[116,160,243],"set":[117],"protocols":[119,203,262],"consists":[120],"Faster":[122],"R-CNN,":[123],"YOLOv3,":[124],"SELSA,":[125,263],"MEGA,":[126,264],"REPP.":[128,266],"Further,":[129],"characterize":[131],"their":[132],"performance":[133],"under":[134,218],"levels":[136],"resource":[138,219],"contention,":[139,142],"specifically":[140],"GPU":[141],"would":[144],"arise":[145],"due":[146],"co-located":[148],"applications":[149],"these":[151],"boards,":[152],"contending":[153],"task.":[159],"key":[161],"insights":[162],"are":[163,256],"be":[169],"coupled":[170],"trackers":[172],"keep":[174],"up":[175,187],"latency":[178,236],"requirements":[179],"30":[181],"fps).":[182],"With":[183],"this,":[184],"FastAdapt":[185],"achieves":[186,229],"76":[189],"fps":[190],"most":[193],"well-resourced":[194],"NVIDIA":[195,198],"Jetson-class":[196],"board---the":[197],"AGX":[199],"Xavier.":[200],"Second,":[201],"adaptive":[202,211,251,254],"FRCNN,":[206,252],"(specifically":[209],"our":[210],"variants,":[212],"FRCNN+":[213],"YOLO+)":[215],"work":[216],"well":[217],"constraints.":[220],"Among":[221],"latest":[223],"heads,":[227],"SELSA":[228],"highest":[231],"accuracy":[232],"but":[233],"a":[235],"2":[239],"sec":[240],"per":[241],"frame.":[242],"experiments":[246],"bring":[247],"out":[248],"best-in-class,":[257],"relative":[258],"non-adaptive":[261]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}