{"id":"https://openalex.org/W3173227255","doi":"https://doi.org/10.13016/g6qg-dkfy","title":"Efficient Detection of Objects and Faces with Deep Learning","display_name":"Efficient Detection of Objects and Faces with Deep Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3173227255","doi":"https://doi.org/10.13016/g6qg-dkfy","mag":"3173227255"},"language":"en","primary_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/27189","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/27189","pdf_url":null,"source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/g6qg-dkfy","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021900923","display_name":"Mahyar Najibi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Najibi, Mahyar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5021900923"],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9492999911308289,"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/T11448","display_name":"Face recognition and analysis","score":0.9492999911308289,"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/T10057","display_name":"Face and Expression Recognition","score":0.9154000282287598,"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/deep-learning","display_name":"Deep learning","score":0.5170686841011047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5165647268295288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4663488268852234},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3413746953010559}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5170686841011047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5165647268295288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4663488268852234},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3413746953010559}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:drum.lib.umd.edu:1903/27189","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/27189","pdf_url":null,"source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"mag:3173227255","is_oa":false,"landing_page_url":"https://drum.lib.umd.edu/handle/1903/27189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.13016/g6qg-dkfy","is_oa":true,"landing_page_url":"https://doi.org/10.13016/g6qg-dkfy","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.13016/g6qg-dkfy","is_oa":true,"landing_page_url":"https://doi.org/10.13016/g6qg-dkfy","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2780676650","https://openalex.org/W2891789699","https://openalex.org/W2949096641","https://openalex.org/W3184049243","https://openalex.org/W3121097020","https://openalex.org/W2955004171","https://openalex.org/W2981975404","https://openalex.org/W2972006294","https://openalex.org/W3107902501","https://openalex.org/W3115870437","https://openalex.org/W2796597258","https://openalex.org/W2786443043","https://openalex.org/W3171375902","https://openalex.org/W3126763274","https://openalex.org/W3194225869","https://openalex.org/W2540374523","https://openalex.org/W2982010943","https://openalex.org/W2988916019","https://openalex.org/W3115622771","https://openalex.org/W2806252395"],"abstract_inverted_index":{"Object":[0],"detection":[1,315],"is":[2,10,136,185,420],"a":[3,119,144,214,284,389],"fundamental":[4],"problem":[5,111,237],"in":[6,45,64,283,358,391],"computer":[7],"vision":[8],"and":[9,24,30,35,61,88,249,293,334,399],"an":[11,150,425],"essential":[12],"building":[13],"block":[14],"for":[15,86,159,312,367,406,409],"many":[16],"applications":[17],"such":[18,56,411],"as":[19,57,223,225,388,412],"autonomous":[20],"driving,":[21],"visual":[22,46],"search,":[23],"object":[25,87],"tracking.":[26],"Given":[27],"its":[28,300],"large-scale":[29],"real-time":[31],"applications,":[32],"scalable":[33],"training":[34,153],"fast":[36],"inference":[37,117,130,207,342],"are":[38,84,99,247,259],"critical.":[39],"Deep":[40],"neural":[41,82,363,403],"networks,":[42],"although":[43,123],"powerful":[44],"recognition,":[47],"can":[48,68],"be":[49,201],"computationally":[50],"expensive.":[51],"Besides,":[52],"they":[53],"introduce":[54,92,318],"shortcomings":[55],"lack":[58,113],"of":[59,112,114,217,238,254,296,330,337,394,418],"scale-invariance":[60],"inaccurate":[62],"predictions":[63,419],"crowded":[65,250,347],"scenes":[66,251],"that":[67,275,428],"affect":[69],"detection.":[70,90,241],"This":[71],"dissertation":[72],"studies":[73],"the":[74,110,134,167,218,236,297,313,327,338,355,378,392,401,416],"intrinsic":[75],"problems":[76],"which":[77,98,376,385],"emerge":[78],"when":[79,133],"deep":[80],"convolutional":[81],"networks":[83,364],"used":[85,405],"face":[89,240],"We":[91],"methods":[93,229],"to":[94,180,189,200,212,243,343,354,433],"overcome":[95],"these":[96,228],"issues":[97],"not":[100],"only":[101],"accurate":[102],"but":[103,303],"also":[104,137],"efficient.":[105],"First,":[106],"we":[107,146,194,234,265,317,350,382,423],"focus":[108],"on":[109,118,166,308],"scale-invariance.":[115],"Performing":[116],"multi-scale":[120,129,141,152],"image":[121,174],"pyramid,":[122],"effective,":[124],"increases":[125],"computation":[126],"noticeably.":[127,232],"Moreover,":[128],"really":[131],"blooms":[132],"model":[135],"trained":[138],"using":[139,373],"expensive":[140],"approaches.":[142],"As":[143],"result,":[145],"start":[147],"by":[148,291],"introducing":[149],"efficient":[151,224,239],"algorithm":[154],"called":[155],"\"SNIPER\"":[156],"(Scale":[157],"Normalization":[158],"Image":[160],"Pyramids":[161],"with":[162,256,346],"Efficient":[163],"Re-sampling).":[164],"Based":[165],"ground-truth":[168,187],"annotations,":[169],"SNIPER":[170],"sparsely":[171],"samples":[172],"high-resolution":[173],"regions":[175,199],"wherever":[176],"needed.":[177],"In":[178,262],"contrast":[179],"training,":[181],"at":[182,206,430],"inference,":[183],"there":[184],"no":[186],"information":[188],"guide":[190],"region":[191],"sampling.":[192],"Thus,":[193],"propose":[195,383],"\"AutoFocus\".":[196],"AutoFocus":[197],"predicts":[198],"zoomed-in":[202],"from":[203,299],"low":[204],"resolutions":[205],"time,":[208],"making":[209],"it":[210],"possible":[211,396],"skip":[213],"large":[215],"portion":[216],"input":[219],"pyramid.":[220],"While":[221,362],"being":[222],"single-scale":[226],"detectors,":[227,279],"boost":[230],"performance":[231],"Second,":[233],"study":[235],"Compared":[242],"generic":[244],"objects,":[245],"faces":[246,255,331],"rigid":[248],"containing":[252],"hundreds":[253],"extreme":[257],"scales":[258],"more":[260],"common.":[261],"this":[263],"dissertation,":[264],"present":[266],"\"SSH\"":[267],"(Single":[268],"Stage":[269],"Headless":[270],"Face":[271],"Detector).":[272],"A":[273],"method":[274],"unlike":[276],"two-stage":[277,314,359],"localization/classification":[278,360],"performs":[280],"both":[281],"tasks":[282,410],"single":[285],"stage,":[286],"efficiently":[287,344],"models":[288,386],"scale":[289],"variation":[290],"design,":[292],"removes":[294],"most":[295],"parameters":[298],"underlying":[301],"network,":[302],"still":[304],"achieves":[305],"state-of-the-art":[306],"results":[307],"challenging":[309],"benchmarks.":[310],"Furthermore,":[311,408],"paradigm,":[316],"\"FA-RPN\"":[319],"(Floating":[320],"Anchor":[321],"Region":[322],"Proposal":[323],"Network).":[324],"FA-RPN":[325],"takes":[326],"spatial":[328],"structure":[329],"into":[332],"account":[333],"allows":[335],"modification":[336],"prediction":[339],"density":[340],"during":[341],"deal":[345],"scenes.":[348],"Finally,":[349],"turn":[351],"our":[352],"attention":[353],"first":[356],"step":[357],"detectors.":[361],"were":[365],"deployed":[366],"classification,":[368],"localization":[369,387],"was":[370],"previously":[371],"solved":[372],"classic":[374],"algorithms":[375],"became":[377],"bottleneck.":[379],"To":[380],"remedy,":[381],"\"G-CNN\"":[384],"search":[390],"space":[393],"all":[395],"bounding":[397],"boxes":[398],"deploys":[400],"same":[402],"network":[404],"classification.":[407],"saliency":[413],"detection,":[414],"where":[415],"number":[417],"typically":[421],"small,":[422],"develop":[424],"alternative":[426],"approach":[427],"runs":[429],"speeds":[431],"close":[432],"120":[434],"frames/second.":[435]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}