发表在CVPR13上的行人检测方法
China(ProjectNo.61005057),andGuangdongInnovativeResearchTeamProgram(No.201001D0104648280)..
References
[1]Y.Bengio.LearningdeeparchitecturesforAI.Foundations
andTrendsinMachineLearning,2(1):1–127,2009.2
[2]S.Dai,M.Yang,Y.Wu,andA.Katsaggelos.Detectoren-semble.InCVPR,2007.2
[3]N.DalalandB.Triggs.Histogramsoforientedgradientsfor
humandetection.InCVPR,2005.6
[4]J.Deng,W.Dong,R.Socher,L.-J.Li,K.Li,andL.Fei-Fei.Imagenet:alarge-scalehierarchicalimagedatabase.InCVPR,2009.2
[5]C.Desai,D.Ramanan,andC.Fowlkes.Discriminativemod-elsformulti-classobjectlayout.InICCV,2009.2
[6]Y.DingandJ.Xiao.Contextualboostforpedestriandetec-tion.InCVPR,2012.2,6[7]P.Doll´ar,R.Appel,andW.Kienzle.Crosstalkcascadesfor
frame-ratepedestriandetection.InECCV,2012.6[8]P.Doll´ar,S.Belongie,andP.Perona.Thefastestpedestrian
detectorinthewest.InBMVC,2010.6[9]P.Doll´ar,C.Wojek,B.Schiele,andP.Perona.Pedestrian
detection:anevaluationofthestateoftheart.IEEETrans.PatternAnal.Mach.Intell.,34(4):743–761,2012.6,7[10]G.Duan,H.Ai,http://www.77cn.com.cno.Astructural lterapproachto
humandetection.InECCV,2010.2
[11]M.Enzweiler,A.Eigenstetter,B.Schiele,andD.M.Gavrila.
Multi-cuepedestrianclassi cationwithpartialocclusionhandling.InCVPR,2010.2
[12]D.Erhan,Y.Bengio,A.Courville,P.-A.Manzagol,P.Vin-cent,andS.Bengio.Whydoesunsupervisedpre-traininghelpdeeplearning?J.MachineLearningResearch,11:625–660,2010.4
[13]A.Ess,B.Leibe,andL.V.Gool.Depthandappearancefor
mobilesceneanalysis.InICCV,2007.6
[14]P.Felzenszwalb,R.B.Grishick,D.McAllister,andD.Ra-manan.Objectdetectionwithdiscriminativelytrainedpartbasedmodels.IEEETrans.PatternAnal.Mach.Intell.,32:1627–1645,2010.4,6
[15]G.E.Hinton.Trainingproductsofexpertsbyminimizing
contrastivedivergence.NeuralComputation,14:1771–1800,2002.5
[16]G.E.Hinton,S.Osindero,andY.Teh.Afastlearningal-gorithmfordeepbeliefnets.NeuralComputation,18:1527–1554,2006.2,5
[17]G.E.HintonandR.R.Salakhutdinov.Reducingthe
dimensionalityofdatawithneuralnetworks.Science,313(5786):504–507,July2006.2
[18]K.Jarrett,K.Kavukcuoglu,M.Ranzato,andY.LeCun.
Whatisthebestmulti-stagearchitectureforobjectrecog-nition?InCVPR,2009.2
[19]A.Krizhevsky,I.Sutskever,andG.Hinton.Imagenetclas-si cationwithdeepconvolutionalneuralnetworks.InNIPS,2012.2,3
[20]H.Lee,R.Grosse,R.Ranganath,andA.Y.Ng.Convolu-tionaldeepbeliefnetworksforscalableunsupervisedlearn-ingofhierarchicalrepresentations.InICML,2009.2
[21]B.Leibe,E.Seemann,andB.Schiele.Pedestriandetection
incrowdedscenes.InCVPR,2005.2
[22]Z.Lin,L.S.Davis,D.Doermann,andD.DeMenthon.Hi-erarchicalpart-templatematchingforhumandetectionandsegmentation.InICCV,2007.2
[23]P.Luo,X.Wang,andX.Tang.Hierarchicalfaceparsingvia
deeplearning.InCVPR,2012.2
[24]M.Norouzi,M.Ranjbar,andG.Mori.Stacksofconvolu-tionalrestrictedboltzmannmachinesforshift-invariantfea-turelearning.InCVPR,2009.2,3
[25]W.OuyangandX.Wang.Adiscriminativedeepmodel
forpedestriandetectionwithocclusionhandling.InCVPR,2012.1,2,3,6
[26]W.OuyangandX.Wang.Single-pedestriandetectionaided
bymulti-pedestriandetection.InCVPR,2013.2
[27]D.Park,D.Ramanan,andC.Fowlkes.Multiresolutionmod-elsforobjectdetection.InECCV,2010.2,6
[28]M.Ranzato,J.Susskind,V.Mnih,andG.Hinton.On
deepgenerativemodelswithapplicationstorecognition.InCVPR,2011.2
[29]V.D.Shet,J.Neumann,V.Ramesh,andL.S.Davis.
Bilattice-basedlogicalreasoningforhumandetection.InCVPR,2007.2
[30]S.Tang,M.Andriluka,andB.Schiele.Detectionandtrack-ingofoccludedpeople.InBMVC,Surrey,UK,2012.2[31]S.Walk,N.Majer,K.Schindler,andB.Schiele.Newfea-turesandinsightsforpedestriandetection.InCVPR,2010.2,6
[32]X.Wang,X.Han,andS.Yan.Anhog-lbphumandetector
withpartialocclusionhandling.InCVPR,2009.2
[33]B.WuandR.Nevatia.Detectionofmultiple,partiallyoc-cludedhumansinasingleimagebybayesiancombinationofedgeletpartdetectors.InICCV,2005.2
[34]B.WuandR.Nevatia.Detectionandsegmentationofmul-tiple,partiallyoccludedobjectsbygrouping,merging,as-signingpartdetectionresponses.Int’http://www.77cn.com.cnputerVision,82(2):185–204,2009.2
[35]T.WuandS.Zhu.Anumericstudyofthebottom-upandtop-downinferenceprocessesinand-orgraphs.Int’http://www.77cn.com.cnputerVision,93(2):226–252,Jun.2011.2
[36]J.Yan,Z.Lei,D.Yi,andS.Z.Li.Multi-pedestriandetection
incrowdedscenes:Aglobalview.InCVPR,2012.2
[37]Y.Yang,S.Baker,A.Kannan,andD.Ramanan.Recogniz-ingproxemicsinpersonalphotos.InCVPR,2012.2
[38]Y.YangandD.Ramanan.Articulatedposeestimationwith
exiblemixtures-of-parts.InCVPR,2011.2
[39]B.YaoandL.Fei-Fei.Modelingmutualcontextofobject
andhumanposeinhuman-objectinteractionactivities.InCVPR,2010.2
[40]L.Zhu,Y.Chen,A.Yuille,http://www.77cn.com.cntenthier-archicalstructurallearningforobjectdetection.InCVPR,2010.2