{"id":"https://openalex.org/W3045597402","doi":"https://doi.org/10.13016/4gy2-jubh","title":"Improving Efficiency for Object Detection and Temporal Modeling for Action Localization","display_name":"Improving Efficiency for Object Detection and Temporal Modeling for Action Localization","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W3045597402","doi":"https://doi.org/10.13016/4gy2-jubh","mag":"3045597402"},"language":"en","primary_location":{"id":"mag:3045597402","is_oa":false,"landing_page_url":"https://drum.lib.umd.edu/handle/1903/26044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/4gy2-jubh","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026664462","display_name":"Mingfei Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gao, Mingfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5026664462"],"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9898999929428101,"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":0.9898999929428101,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9516000151634216,"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":0.9366999864578247,"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/action","display_name":"Action (physics)","score":0.552112877368927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.519853413105011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4682620167732239},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.45480912923812866},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4175291359424591},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39597421884536743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26543956995010376},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09845981001853943}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.552112877368927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.519853413105011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4682620167732239},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.45480912923812866},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4175291359424591},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39597421884536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26543956995010376},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09845981001853943},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:3045597402","is_oa":false,"landing_page_url":"https://drum.lib.umd.edu/handle/1903/26044","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:10.13016/4gy2-jubh","is_oa":true,"landing_page_url":"https://doi.org/10.13016/4gy2-jubh","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":"Collection"}],"best_oa_location":{"id":"doi:10.13016/4gy2-jubh","is_oa":true,"landing_page_url":"https://doi.org/10.13016/4gy2-jubh","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":"Collection"},"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/W3207700483","https://openalex.org/W3156070674","https://openalex.org/W2903968927","https://openalex.org/W1656610607","https://openalex.org/W2040132116","https://openalex.org/W1822399335","https://openalex.org/W2990786707","https://openalex.org/W3100232625","https://openalex.org/W3136965813","https://openalex.org/W3107262983","https://openalex.org/W2104265090","https://openalex.org/W2989229573","https://openalex.org/W2901119840","https://openalex.org/W3211024799","https://openalex.org/W1963915446","https://openalex.org/W2171552954","https://openalex.org/W2910027519","https://openalex.org/W3013673841","https://openalex.org/W2196918137","https://openalex.org/W3089929663"],"abstract_inverted_index":{"Despite":[0],"their":[1,302],"great":[2],"predictive":[3],"capability,":[4],"Convolutional":[5],"Neural":[6],"Networks":[7,467],"(CNNs)":[8],"are":[9,305,518,528],"computational-expensive":[10],"to":[11,34,39,49,61,84,150,171,193,206,245,290,398,412,469,492],"deploy":[12],"and":[13,32,43,60,88,138,185,221,241,254,276,301,322,333,348,375,426,450,456,506,520,533],"usually":[14],"require":[15],"a":[16,98,127,132,141,163,179,182,199,212,260,393,406,420,498,523],"tremendous":[17],"amount":[18],"of":[19,52,75,106,135,143,162,211,223,236,257,294,345,396,417,441,495],"annotated":[20],"data":[21,79],"at":[22,181],"training":[23,432,485],"time.":[24],"When":[25],"analyzing":[26,178],"videos,":[27],"it":[28,445],"is":[29,251,368],"very":[30],"important":[31],"challenging":[33],"model":[35,53,164,187,207],"temporal":[36,63,209,493],"dynamics":[37],"due":[38],"large":[40],"appearance":[41],"variation":[42],"complex":[44],"semantics.":[45],"We":[46,264],"propose":[47,198,288,462],"methods":[48,430],"improve":[50,151,399],"efficiency":[51],"deployment":[54],"for":[55,65,78,112,177],"object":[56,86,107,390,422],"detection":[57,68,87,108,153,169,220,273,355],"in":[58,69,120,126,230,307,472],"images":[59],"capture":[62],"dependencies":[64],"online":[66,218,271],"action":[67,219,249,272,299,318,335,343],"videos.":[70,310],"To":[71,437],"relieve":[72],"the":[73,103,136,152,173,224,248,341,346,434,439,459,481,512],"demand":[74],"human":[76],"labor":[77],"annotation,":[80],"we":[81,96,197,287,378,443,461],"introduce":[82,97,379],"approaches":[83],"conduct":[85,451],"natural":[89],"language":[90,477],"localization":[91,325,359],"using":[92,361],"weak":[93],"supervisions.":[94],"First,":[95],"generic":[99],"framework":[100,367],"that":[101,166,189,250,387],"reduces":[102],"computational":[104],"cost":[105],"while":[109],"retaining":[110],"accuracy":[111,175],"scenarios":[113],"where":[114,298],"objects":[115],"with":[116,433,486],"varied":[117],"sizes":[118],"appear":[119],"high":[121],"resolution":[122,145,184],"images.":[123],"Detection":[124,293],"progresses":[125],"coarse-to-fine":[128],"manner,":[129],"first":[130],"on":[131,140,268,330,340,370,454,511,530],"down-sampled":[133],"version":[134],"image":[137],"then":[139],"sequence":[142],"higher":[144,183],"regions":[146,192],"identified":[147],"as":[148,278,280,392,522],"likely":[149],"accuracy.":[154],"Built":[155],"upon":[156],"reinforcement":[157],"learning,":[158],"our":[159,232,266],"approach":[160,233,267,386],"consists":[161],"(R-net)":[165],"uses":[167,388,405],"coarse":[168],"results":[170],"predict":[172],"potential":[174],"gain":[176],"region":[180,409],"another":[186,281],"(Q-net)":[188],"sequentially":[190],"selects":[191],"zoom":[194],"in.":[195],"Second,":[196],"novel":[200],"framework,":[201],"Temporal":[202],"Recurrent":[203],"Network":[204],"(TRN),":[205],"greater":[208],"context":[210],"video":[213],"frame":[214],"by":[215,356,431,484],"simultaneously":[216],"performing":[217],"anticipation":[222],"immediate":[225],"future.":[226],"At":[227],"each":[228,416],"moment":[229],"time,":[231],"makes":[234],"use":[235],"both":[237,256,517],"accumulated":[238],"historical":[239],"evidence":[240],"predicted":[242,342],"future":[243],"information":[244],"better":[246],"recognize":[247],"currently":[252],"occurring,":[253],"integrates":[255],"these":[258],"into":[259,315,446],"unified":[261],"end-to-end":[262,500],"architecture.":[263],"evaluate":[265],"two":[269,316,371,447],"popular":[270],"datasets,":[274,373],"HDD":[275],"TVSeries,":[277],"well":[279],"widely":[282],"used":[283],"dataset,":[284],"THUMOS\u201914.":[285],"Third,":[286],"StartNet":[289],"address":[291],"Online":[292],"Action":[295],"Start":[296],"(ODAS)":[297],"starts":[300],"associated":[303],"categories":[304],"detected":[306],"untrimmed,":[308],"streaming":[309],"Our":[311],"method":[312],"decomposes":[313],"ODAS":[314],"stages:":[317],"classification":[319],"(using":[320,326],"ClsNet)":[321],"start":[323,354],"point":[324],"LocNet).":[327],"ClsNet":[328],"focuses":[329],"per-frame":[331],"labeling":[332],"predicts":[334],"score":[336],"distributions":[337],"online.":[338],"Based":[339],"scores":[344],"past":[347],"current":[349],"frames,":[350],"LocNet":[351],"conducts":[352,507],"class-agnostic":[353],"optimizing":[357],"long-term":[358],"rewards":[360],"policy":[362],"gradient":[363],"methods.":[364],"The":[365],"proposed":[366],"validated":[369],"large-scale":[372],"THUMOS\u201914":[374],"ActivityNet.":[376],"Fourth,":[377],"Count-guided":[380],"Weakly":[381,400,463],"Supervised":[382,401,464],"Localization":[383,402,466],"(C-WSL),":[384],"an":[385],"per-class":[389],"count":[391],"new":[394],"form":[395],"supervision":[397],"(WSL).":[403],"C-WSL":[404],"simple":[407,499],"count-based":[408],"selection":[410,509],"algorithm":[411],"select":[413],"high-quality":[414],"regions,":[415],"which":[418],"covers":[419],"single":[421],"instance":[423],"during":[424],"training,":[425],"improves":[427],"existing":[428],"WSL":[429,448],"selected":[435],"regions.":[436],"demonstrate":[438],"effectiveness":[440],"C-WSL,":[442],"integrate":[444],"architectures":[449],"extensive":[452],"experiments":[453],"VOC2007":[455],"VOC2012.":[457],"In":[458],"last,":[460],"Language":[465],"(WSLLN)":[468],"detect":[470],"events":[471],"long,":[473],"untrimmed":[474],"videos":[475],"given":[476],"queries.":[478],"WSLLN":[479,502],"relieves":[480],"annotation":[482],"burden":[483],"only":[487],"video-sentence":[488,524],"pairs":[489],"without":[490],"accessing":[491],"locations":[494],"events.":[496],"With":[497],"structure,":[501],"measures":[503],"segment-text":[504],"consistency":[505],"segment":[508],"(conditioned":[510],"text)":[513],"simultaneously.":[514],"Results":[515],"from":[516],"merged":[519],"optimized":[521],"matching":[525],"problem.":[526],"Experiments":[527],"conducted":[529],"ActivityNet":[531],"Captions":[532],"DiDeMo.":[534]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}