您的位置:首页 > 理论基础

图像处理与计算机视觉学习资源

2016-09-26 09:16 288 查看

OxfordCourse on CUDA Programming on NVIDIA GPUs点击打开链接

斯坦福大学Andrew Ng Deep Learning 教程中文教程 

机器学习课程URL:http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=MachineLearning

原文链接:http://deeplearning.stanford.edu/wiki/index.php/UFLDL%E6%95%99%E7%A8%8B

学习深度学习的四个步骤:http://mp.weixin.qq.com/s?__biz=MzI0NTE4NjA0OQ==&mid=2658352176&idx=2&sn=f545269f6d02aca45458c954c577b109&chksm=f2d5f75ec5a27e48b7b07471d47772425ced49cea3f9423517b0ed462a7cf736c3dcf6918ed4&scene=1&srcid=0926hQuYqnPuph9S48OBGzJc#rd

图像处理与计算机视觉 http://www.ipcv.org/

caffe学习专栏点击打开链接

用GPU+CoreOS+Docker+TensorFlow搭建高效灵活的深度学习研发平台 
http://www.emergingstack.com/2016/01/10/Nvidia-GPU-plus-CoreOS-plus-Docker-plus-TensorFlow.html
(论文+代码)华盛顿大学CVPR2016新进展-Deep3D: 基于深度学习将2D电影转换为3D电影

博客介绍:http://dmlc.ml/mxnet/2016/04/04/deep3d-automatic-2d-to-3d-conversion-with-CNN.html

代码链接:https://github.com/piiswrong/deep3d

论文链接:http://homes.cs.washington.edu/~jxie/pdf/deep3d.pdf

CVPR2016 Paper 单目3D人体姿态估计论文(论文+代码)

project链接:
https://fling.seas.upenn.edu/~xiaowz/dynamic/wordpress/monocular-human-pose/
论文链接:
http://arxiv.org/abs/1511.09439
visual Tracking 领域最新进展(论文与源码)
http://m.blog.csdn.net/article/details?id=51592156
C++ implementation of Face Alignment at 3000 FPS via Regressing Local Binary Features.
https://github.com/luoyetx/face-alignment-at-3000fps
【论文+代码(MatLab):头像照片风格迁移(模仿)】《Style Transfer for Headshot Portraits》Y Shih, S Paris, C Barnes, W Freeman, F Durand (SIGGRAPH 2014)
http://m.weibo.cn/1402400261/3881452083001194?sourcetype=page&lfid=2302592000382195&lcardid=2302592000382195_-_3881452083001194&mid=3881452083001194&luicode=10000011&_status_id=3881452083001194&uicode=10000002&sudaref=mp.weixin.qq.com&retcode=6102
cv开源代码http://m.blog.csdn.net/article/details?id=49902011
计算机视觉和模式识别 CVPR2016的代码合集:https://tensortalk.com/?cat=conference-cvpr-2016&t=type-code

C++开发人脸性别识别教程(2016-1):http://blog.csdn.net/column/details/genderrecogtion.html

(代码+论文)行为识别最新进展

论文1和代码链接:
http://arxiv.org/abs/1608.00859 https://github.com/yjxiong/temporal-segment-networks
论文2和代码链接:
http://arxiv.org/abs/1608.00797 https://github.com/yjxiong/anet2016-cuhk
10 Papers from ICML and CVPR:https://leotam.github.io/general/2016/07/12/ICMLcVPR.html

一个有趣的360度照相机的开源项目:树莓派+OpenCV:https://github.com/Open360cam/360CamCode

论文+代码:基于级联深度卷积层的兴趣目标预测DeepProposal 

论文链接:http://arxiv.org/abs/1510.04445

code链接:https://github.com/aghodrati/deepproposal

图像视觉领域新文章及相应开源代码:http://blog.csdn.net/cv_family_z/article/details/49902011

从特征描述符到深度学习:计算机视觉发展20年 http://mp.weixin.qq.com/s?__biz=MzAwNjcyOTIwNA==&mid=2659249662&idx=1&sn=a6a15074383f4fdd01e16fffe877253b&scene=1&srcid=0926Hc6ReWyhsbm2AQb6aLts#rd

大牛的《深度学习》笔记,60分钟带你学会Deep Learning  http://mp.weixin.qq.com/s?__biz=MzAwNjcyOTIwNA==&mid=2659249679&idx=1&sn=8ff34e2bab32689a49f1ffb68cec9475&scene=1&srcid=0801UQzDT8yakSv3JLUAI2uC#rd
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: