CVPR历年Best Papers

cvpr

作者:我爱机器学习
原文链接:CVPR历年Best Papers

CVPR (Computer Vision)(2000-2016)
年份标题一作一作单位
2016Deep Residual Learning for Image RecognitionKaiming HeMicrosoft Research
2015DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-TimeRichard A. NewcombeUniversity of Washington
2014What Camera Motion Reveals About Shape with Unknown BRDFManmohan ChandrakerNEC Labs America
2013Fast, Accurate Detection of 100,000 Object Classes on a Single MachineThomas DeanGoogle
2012A Simple Prior-free Method for Non-Rigid Structure-from-Motion FactorizationYuchao DaiNorthwestern Polytechnical University
2011Real-time Human Pose Recognition in Parts from Single Depth ImagesJamie ShottonMicrosoft Research
2010Efficient Computation of Robust Low-Rank Matrix Approximations in the Presence of Missing Data usi…Anders ErikssonUniversity of Adelaide
2009Single Image Haze Removal Using Dark Channel PriorKaiming HeThe Chinese University of Hong Kong
2008Global Stereo Reconstruction under Second Order Smoothness PriorsOliver WoodfordUniversity of Oxford
Beyond Sliding Windows: Object Localization by Efficient Subwindow SearchChistoph H. LampertMax Planck Institut
2007Dynamic 3D Scene Analysis from a Moving VehicleBastian LeibeETH Zurich
2006Putting Objects in PerspectiveDerek HoiemCarnegie Mellon University
2005Real-Time Non-Rigid Surface DetectionJulien PiletÉcole Polytechnique Fédérale de Lausanne
2004Programmable Imaging using a Digital Micromirror ArrayShree K. NayarColumbia University
2003Object Class Recognition by Unsupervised Scale-Invariant LearningRob FergusUniversity of Oxford
2001Morphable 3D models from videoMatthew BrandMitsubishi Electric Research Laboratories
2000Real-Time Tracking of Non-Rigid Objects using Mean ShiftDorin ComaniciuSiemens Corporate Research

参考文献:Best Paper Awards in Computer Science (since 1996)

转载于:https://www.cnblogs.com/52machinelearning/p/5821581.html

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值