[ICML 2010] 3D Convolutional Neural Networks for Human Action Recognition

[ICML 2010] 3D Convolutional Neural Networks for Human Action Recognition

ID:40702363

大小:355.95 KB

页数:8页

时间:2019-08-06

[ICML 2010] 3D Convolutional Neural Networks for Human Action Recognition_第1页
[ICML 2010] 3D Convolutional Neural Networks for Human Action Recognition_第2页
[ICML 2010] 3D Convolutional Neural Networks for Human Action Recognition_第3页
[ICML 2010] 3D Convolutional Neural Networks for Human Action Recognition_第4页
[ICML 2010] 3D Convolutional Neural Networks for Human Action Recognition_第5页
资源描述:

《[ICML 2010] 3D Convolutional Neural Networks for Human Action Recognition》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、3DConvolutionalNeuralNetworksforHumanActionRecognitionShuiwangJishuiwang.ji@asu.eduArizonaStateUniversity,Tempe,AZ85287,USAWeiXuxw@sv.nec-labs.comMingYangmyang@sv.nec-labs.comKaiYukyu@sv.nec-labs.comNECLaboratoriesAmerica,Inc.,Cupertino,CA95014,USAAbstractclutteredbackgrounds,occlusions,andviewpoi

2、ntvari-ations,etc.Therefore,mostoftheexistingapproachesWeconsiderthefullyautomatedrecognition(Efrosetal.,2003;Sch¨uldtetal.,2004;Doll´aretal.,ofactionsinuncontrolledenvironment.Most2005;Laptev&P´erez,2007;Jhuangetal.,2007)existingworkreliesondomainknowledgetomakecertainassumptions(e.g.,smallscalea

3、ndview-constructcomplexhandcraftedfeaturesfrompointchanges)aboutthecircumstancesunderwhichinputs.Inaddition,theenvironmentsarethevideowastaken.However,suchassumptionssel-usuallyassumedtobecontrolled.Convolu-domholdinreal-worldenvironment.Inaddition,mosttionalneuralnetworks(CNNs)areatypeofoftheseap

4、proachesfollowtheconventionalparadigmdeepmodelsthatcanactdirectlyontherawofpatternrecognition,whichconsistsoftwostepsininputs,thusautomatingtheprocessoffea-whichthefirststepcomputescomplexhandcraftedfea-tureconstruction.However,suchmodelsareturesfromrawvideoframesandthesecondsteplearnscurrentlylimi

5、tedtohandle2Dinputs.Inthisclassifiersbasedontheobtainedfeatures.Inreal-worldpaper,wedevelopanovel3DCNNmodelforscenarios,itisrarelyknownwhichfeaturesareimpor-actionrecognition.Thismodelextractsfea-tantforthetaskathand,sincethechoiceoffeatureisturesfrombothspatialandtemporaldimen-highlyproblem-depend

6、ent.Especiallyforhumanac-sionsbyperforming3Dconvolutions,therebytionrecognition,differentactionclassesmayappearcapturingthemotioninformationencodeddramaticallydifferentintermsoftheirappearancesinmultipleadjacentframes.Thedevelopedandmotionpatterns.modelgeneratesmultiplechannelsofinfor-mationfromthei

7、nputframes,andthefinalDeeplearningmodels(Fukushima,1980;LeCunetal.,featurerepresentationisobtainedbycom-1998;Hinton&Salakhutdinov,2006;Hintonetal.,bininginformationfromallchannels.We2006;Bengio,2009)areaclassofmac

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。