youth0826-CSDN博客

原创 Berkeley Caffe vs Toronto Convnet 大作战

上图上真相，看看Berkeley Caffe和Toronto Convnet的分类效果对比吧。以Toronto网站的10张图为例，比较下他们各自的分类准确度和置信度！

2014-07-21 18:38:23 2264

转载 ICCV 2013 Accepted Tutorials

ICCV 2013 Accepted TutorialsOrganizers, please contact Ryan Farrell with needed updates.

2013-12-05 11:40:38 823

原创 test web link

点击打开链接

2013-10-31 16:22:35 1057

原创 PhD Positions opening at University of Nevada, Reno (Wireless Networking / Cognitive Radio / Wireless Security)

PhD Positions opening at University of Nevada, RenoDept. of Computer Science and Engineering Research Areas: Wireless Networking / Cognitive Radio / Wireless Security Prof. Shamik SenguptaWebsite: htt

2013-10-24 17:54:47 1131

原创 Best of Best系列（6） -- SIGIR

SIGIR (Information Retrieval)(Average MAP score: 0.13) SIGIR (Information Retrieval) 2012 ( MAP score: 1.0 ) TOP BEST PAPER! Rank1 Cited by7 Time-based calibration of effectiveness measures

2013-10-24 17:54:45 1167

原创 Best of Best系列（5） -- IJCAI

IJCAI (Artificial Intelligence)(Average MAP score: 0.0) IJCAI (Artificial Intelligence) 2011 ( MAP score: 0.0 ) TOP Rank1 Cited by46 Connecting the Dots between News Articles Dafna Shahaf, C

2013-10-24 17:54:43 948

原创 Best of Best系列（4） -- AAAI

AAAI (Artificial Intelligence)(Average MAP score: 0.11) AAAI (Artificial Intelligence) 2012 ( MAP score: 0.0 ) TOP Rank1 Cited by16 Search-Based Path Planning with Homotopy Class Constraints

2013-10-24 17:54:40 1100

原创 Best of Best系列（3） -- ICML

ICML (Machine Learning)(Average MAP score: 0.01) ICML (Machine Learning) 2011 ( MAP score: 0.0 ) TOP Rank1 Cited by67 The Importance of Encoding Versus Training with Sparse Coding and Vector

2013-10-24 17:54:38 730

原创 Best of Best系列（2） -- ICCV

ICCV (Computer Vision)(Average MAP score: 0.07) ICCV (Computer Vision) 2011 ( MAP score: 0.0 ) TOP Rank1 Cited by84 ORB: An efficient alternative to SIFT or SURF Ethan Rublee, Vincent Rabaud

2013-10-24 17:54:35 797

原创 Best of Best系列（1） -- CVPR

CVPR (Computer Vision)(Average MAP score: 0.19) CVPR (Computer Vision) 2012 ( MAP score: 0.0 ) TOP Rank1 Cited by25 Are we ready for autonomous driving? The KITTI vision benchmark suite Andr

2013-10-24 17:54:33 1147

原创美国内华达大学招收计算机视觉方向MS/PhD学生，提供RA职位，每月1600$

美国内华达大学（University of Nevada Reno，UNR）计算机视觉实验室（CVL）招收计算机视觉方向的MS、PhD学生，提供RA职位，每月1600$，详细资料见附件。需求：计算机、数学、物理或者工科方向的第一学位；良好的数学基础和C/C++编程技巧；熟悉Linux，熟练使用OpenCV或Matlab；有图像处理、计算机视觉、模式识别或机器学习方向上的背景知识；有过

2013-10-24 17:54:30 1590

原创 Win7 64bit下MexOpenCV的安装，Matlab和C++ & OpenCV的完美结合

1. C++编译环境的安装（Win 7 64bit，x64平台） VS2010 + Windows SDK7.1 + VS2010 Sp1 + VC-Compiler-KB2519277 详细见本博客链接：Windows SDK 7.1 安装 2. OpenCV的安装 OpenCV2.4.x，解压缩安装在D:\OpenCV 将D:\opencv\build\x64\vc10\bin加入到系统

2013-10-24 17:54:28 944

原创 Windows SDK 7.1 安装

安装Microsoft Windows SDK 7.1的时候出现了一下错误：Microsoft Windows SDK for Windows 7 product has reported the following error: Please refer to Samples\Setup\HTML\ConfigDetails.htm document for further informatio

2013-10-24 17:54:26 1732

原创 Deep Learning at NIPS2012

by Kevin Duh on Dec 17, 2012 I went to NIPS2012 to learn about recent advances in Deep Learning (see [1] for conference pre-proceedings and [2] for a well-attended workshop program by Bengio, Bergst

2013-10-24 17:54:24 782

原创 Some Tips on Reading Research Papers

Some Tips on Reading Research Papers by Mubarak Shah @UCF 1. You have to read the paper several times to understand it. When you read the paper first time, if you do not understand something do not g

2013-10-24 17:54:22 513

原创 Comics: do we know that we are not doing research in the wrong way?

by Songchun Zhu, UCLA From a talk given at the Frontiers of Vision in 2011. Download the whole ppt. 1, How to reach the moon? Vision is arguably one of the most challenging, and potentially useful

2013-10-24 17:54:20 652

原创 PCCS-RGB变换表

PCCS Munsell RGB10 RGB16 v1 10RP 4/13.5 185, 31, 87 #b91f57 v2 4R 4.5/14 208, 47, 72 #d02f48 v3 7R 5/14 221, 68, 59 #dd443b v4 10R 5.5/14 233, 91, 35 #e95b23 v5 4YR 6/13.5 230, 120, 0 #e67800

2013-10-24 17:54:18 7714

原创 21世纪初最有影响力的30篇计算机视觉会议论文

选取论文的原则：（1）会议论文，主要来源于以下会议：CVPR, ICCV, ECCV, BMVC, FG, ICIP, ICPR, WACV, ICASSP, MM, IJCAI, UAI, AAAI…（其实后面的几个会议都是打酱油的，AI类的期刊也木有高引CV文章，事实也是如此，没有收录ICML和NIPS等，见谅）（2）发表在2000年以后，数据来源于微软学术搜索(http://acad

2013-10-24 17:54:15 1092

原创 Some Interesting Papers from NIPS 2012

W. Koolen, D. Adamskiy, M. WarmuthPutting Bayes to sleepSome signals look sort of jump Markov — the distribution of the data changes over time so that there are segments which have distribution A, the

2013-10-24 17:54:13 467

原创 21世纪初最有影响力的20篇计算机视觉期刊论文

选取论文的原则：（1）期刊论文，主要来源于以下期刊：TPAMI，IJCV，TIP，CVIU，IVC，MVA，PR，JMIV，IJPRAI… （2）发表在2000年以后（3）SCI检索次数大于1000，来源于Web of Science数据库，2012年12月初的检索结果 Top 20 榜单如下： [1] D. G. Lowe, “Distinctive image featur

2013-10-24 17:54:11 636

原创第十届机器学习及其应用研讨会 MLA’2012 Slides

On Learning Sparse Structured Input-Output Models [PDF], Prof. Eric Xing （卡内基梅隆大学, 美国）Learning with Implicit/Explicit Structures [PDF], Prof. James Kwok（香港科技大

2013-10-24 17:54:09 744

原创 2013年各大小IT公司待遇

转自西电好网，原帖见：http://bbs.xdnice.com/thread-1271163-1-1.html 本人西电硕士，根据今年找工作的情况以及身边同学的汇总，总结各大公司的待遇如下，吐血奉献给各位学弟学妹，公司比较全，你想去的公司不在这里面，基本上是无名小公司了；无名小公司有时也很给力哦以下绝对是各大公司2013届校招的数据，少数几个是2012 2011的数据，都已经特别注明，数据真

2013-10-24 17:54:06 971

原创 Gartner报告：未来一年48项即将大热的技术趋势 (Hype Cycle for Emerging Technologies)

英文稿： The “Hype Cycle for Emerging Technologies” report is the longest-running annual Hype Cycle, providing a cross-industry perspective on the technologies and trends that IT managers should consider

2013-10-24 17:54:04 3313

原创局部图像特征描述概述 by 樊彬

樊彬中国科学院自动化研究所模式识别国家重点实验室 (CASIA NLPR) 局部图像特征描述是计算机视觉的一个基本研究问题，在寻找图像中的对应点以及物体特征描述中有着重要的作用。它是许多方法的基础，因此也是目前视觉研究中的一个热点，每年在视觉领域的顶级会议ICCV/CVPR/ECCV上都有高质量的特征描述论文发表。同时它也有着广泛的应用，举例来说，在利用多幅二维图像进行三维重建、

2013-10-24 17:54:02 849

转载对博士学位说永别

By 王垠（2012.09.08）前情以及作者简介见上一篇blog（清华梦的粉碎——写给清华大学的退学申请）。经过深思熟虑之后，我决定再次“抛弃”我的博士学位。这是我第三次决定离开博士学位，也应该是最后一次了。这应该不是什么惊人的消息，因为我虽然读博士10年了，可是我的目标从来就不是博士学位。我在寻找更重要的东西，而且那个东西已经被我找到了。所以我的“博士生涯”其实完成了它的使命，基本上

2013-10-24 17:54:00 721

原创 History of Best Paper Awards in AI, NLP, CV, PR, and ML

Conference List: AAAI, IJCAI, ACL, CVPR, ICCV, and ICML AAAI (Artificial Intelligence)2012Document Summarization Based on Data ReconstructionZhanying He, Zhejiang University; e

2013-10-24 17:53:56 1005

原创 OpenTLD Installation for Matalb 2012a (64 bit)

Tested on: Matlab 2012a, Microsoft VS 2010, Win 7 (64 bit), OpenCV 2.4.2 See below. (1) Install and Compile OpenCV 2.4.2 , then set PATH variables to link to OpenCV DLLs. (how to? see here) (2) Setu

2013-10-24 17:53:54 620

原创 Compile OpenCV 2.4.2 for Win 7 (64 bit) by using CMake+VS 2010

Tested on: VS 2010 + Win 7 (64 bit) (1) Download OpenCV 2.4.2 (link) (2) Unzip opencv2.4.2.exe to a directory, take mine for example: E:\OpenCV_src (3) Download and Install Cmake (for windows pla

2013-10-24 17:53:51 967

原创 [MATLAB] Simple TF-IDF implementation

Term-Frequency word weighting scheme is one of most used in normalization of document-term matrices in text mining and information retrieval. See wikipedia for details. function Y = tfidf( X )%

2013-10-24 17:53:49 2804 1

原创 The H Index for Computer Science

The index h, defined as the number of papers with citation number higher or equal to h, as a useful index to characterize the scientific output of a researcher (by Hirsch2005). 139 Herbert A. Simon

2013-10-24 17:53:47 1315

原创 Matlab Cody (1)

Size refers to the number of nodes in a parse tree. Generally speaking, you can think of size as code length. What is Cody? see here Problem 1. Times 2 - START HERE function y = times2(x) y = bits

2013-10-24 17:53:45 1504

原创 [Matlab] Walking along a path

Last month I was experimenting with an algorithm in which I needed to construct a set of equidistant steps along a path consisting of line segments. (I'll call this a polyline path, or polyline for sh

2013-10-24 17:53:43 677

原创 Another List for Advanced Topics in Computer Vision in 2010

We provide an overview of the current state-of-the-art of computer vision by studying a set of cutting-edge advanced computer vision topics. Nine selected computer vision research topics reflect the c

2013-10-24 17:53:41 556

原创 Reading Lists for Advanced Computer Vision in 2009 and 2010

--2009--1. Image Descriptors· [SIFT] Lowe, D.G. Distinctive image features from scale-invariant keypoints. IJCV, 2004.·· [GIST] Oliva, A., Torralba, A. Modeling the shape of the scene: a holisti

2013-10-24 17:53:38 608

原创 Interesting Evolutions of Advanced Topics in Computer Vision

A list of topics for advanced computer vision from 2003 to 2010, interestingly, if you make a comparison. 2003 (Link)Texture synthesisImage completionSeparating style from contentSemantics of wo

2013-10-24 17:53:36 475

原创 CVPR 2012 Highlights from Andrej Karpathy

CVPR 2012 just ended in Providence and I wanted to quickly summarize some of my personal highlights, lessons and thoughts.FREAK: Fast Retina KeypointFREAK is a new orientation-invarient bi

2013-10-24 17:53:34 581

原创 Vision Conference in Late 2012

ACCV'12URL: http://www.accv2012.orgPaper Submission: July 1st, 2012Conference: Nov 5-9, 2012 ECCV 2012workshop deadlines are approaching quicklyhttp://eccv2012.unifi.it/ WACV'13

2013-10-24 17:53:32 529

原创 Excellent Papers for 2011

Excellent Papers for 2011Posted by Corinna Cortes and Alfred Spector, Google ResearchCorinna Cortes and Alfred Spector of Google Research have collected up great papers published by Glooglers in

2013-10-24 17:53:30 2760

原创 Windows Media Player 12不能播放MMS

最近喜欢用sina微电台听广播，前几天都好好的，突然某一天就听不了了，死活没声音。检查了下声卡没问题，用ttplayer放音乐ok。于是就查了下那个微电台的插件，发现是wmp，stream是基于mms的。然后尝试用wmp来播放那个mms stream。结果是error，协议不支持。以为是wmp的问题，然后在win7下把media features关闭又打开的，还是没的效果。

2013-10-24 17:53:28 965

原创 NSF awards $1.8 million for joint image-text analysis research

The U.S. National Science Foundation (NSF) has awarded $1.8 million in grants to the University of California-Los Angeles (UCLA) and the University of Illinois at Urbana-Champaign (UIUC) to investigat

2013-10-24 17:53:26 729

机器学习算法原理与编程实践

资源描述：机器学习算法原理与编程实践　

2015-12-05

Python cuda-convnet

cuda-convnet High-performance C++/CUDA implementation of convolutional neural networks This is a fast C++/CUDA implementation of convolutional (or more generally, feed-forward) neural networks. It can model arbitrary layer connectivity and network depth. Any directed acyclic graph of layers will do. Training is done using the back-propagation algorithm.

2014-07-16

Shogun 3.0

The machine learning toolbox's focus is on large scale kernel methods and especially on Support Vector Machines (SVM) [1]. It provides a generic SVM object interfacing to several different SVM implementations, among them the state of the art LibSVM [2] and SVMlight [3]. Each of the SVMs can be combined with a variety of kernels. The toolbox not only provides efficient implementations of the most common kernels, like the Linear, Polynomial, Gaussian and Sigmoid Kernel but also comes with a number of recent string kernels as e.g. the Locality Improved [4], Fischer [5], TOP [6], Spectrum [7], Weighted Degree Kernel (with shifts) [8, 9, 10]. For the latter the efficient LINADD [10] optimizations are implemented. Also SHOGUN offers the freedom of working with custom pre-computed kernels. One of its key features is the *combined kernel* which can be constructed by a weighted linear combination of a number of sub-kernels, each of which not necessarily working on the same domain. An optimal sub-kernel weighting can be learned using Multiple Kernel Learning [11, 12, 16]. Currently SVM 2-class classification and regression problems can be dealt with. However SHOGUN also implements a number of linear methods like Linear Discriminant Analysis (LDA), Linear Programming Machine (LPM), (Kernel) Perceptrons and features algorithms to train hidden markov models. The input feature-objects can be dense, sparse or strings, and of types int/short/double/char. In addition, they can be converted into different feature types. Chains of *preprocessors* (e.g. substracting the mean) can be attached to each feature object allowing for on-the-fly pre-processing.

2013-11-21

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

机器学习算法原理与编程实践

Python cuda-convnet

Shogun 3.0

res.rar for goose88

face recognition

Robust PCA

Pattern Recognition and Machine Learning

空空如也