排序:
默认
按更新时间
按访问量

为什么开始写csdn博客?

还记得最开始注册csdn账号~ 资源积分不够,不

2014-05-25 13:16:21

阅读数:1322

评论数:1

解读:FlowNet 2.0 evolution of optical flow estimation with deep networks

贡献点: 1. focus on the training data and show that the schedule of presenting data during training is very important.  2. develop a stacked architect...

2017-11-30 22:19:51

阅读数:219

评论数:0

解读: FlowNet learning optical flow with convolutional networks

贡献点:            Construct CNNs which are capable of solving the optical flow estimation problem as a supervised learning task.             Train CN...

2017-11-30 22:10:02

阅读数:222

评论数:0

解读flow-guided feature aggregation for video object detection

文章主要贡献点: Flow-guided feature aggregation, an end-to-end framework for video object detection. Improve the per-frame features by aggregation of nearb...

2017-11-30 20:03:49

阅读数:238

评论数:0

Matlab R2014b配置vlfeat0.9.20

网址:http://blog.csdn.net/u011718701/article/details/51452011

2017-05-03 16:55:16

阅读数:416

评论数:0

投稿期刊和会议,截止日期查询网址:Special issue top conference

http://www.guide2research.com/special-issues/

2017-02-15 10:45:08

阅读数:1529

评论数:0

caffe model for the face task

VGG: http://www.robots.ox.ac.uk/~vgg/software/vgg_face/ CMU-OpenFace: http://cmusatyalab.github.io/openface/

2016-03-21 17:27:45

阅读数:1457

评论数:0

How to set $LD_LIBRARY_PATH in Ubuntu?

http://serverfault.com/questions/201709/how-to-set-ld-library-path-in-ubuntu

2016-03-14 17:23:42

阅读数:828

评论数:0

Basic build issue regarding libs, pkg-config and opencv

http://stackoverflow.com/questions/10526124/basic-build-issue-regarding-libs-pkg-config-and-opencv

2016-03-14 17:20:55

阅读数:780

评论数:0

Example rebuttal for "YOLO: Real-Time Object Detection"

From : http://pjreddie.com/publications/yolo/

2016-03-11 18:35:08

阅读数:1397

评论数:0

Intersection-over-union between two detections

1) You have two overlapping bounding boxes. You compute the intersection of the boxes, which is the area of the overlap. You compute the union of the...

2016-03-11 09:56:27

阅读数:2075

评论数:0

Fast RCNN 训练自己的数据集(3训练和检测)

转载自 楼燚(yì)航的blog,http://www.cnblogs.com/louyihang-loves-baiyan/ https://github.com/YihangLou/fast-rcnn-train-another-dataset 这是我在github上修改的几个文件的链接...

2016-01-08 15:24:09

阅读数:12618

评论数:2

Ubuntu14.04 安装Caffe(仅CPU)

转自:http://blog.csdn.net/u011762313/article/details/47262549#配置pycaffe 前言GPU版本正文 安装依赖库一安装BLAS安装python安装matlab安装opencv安装依赖库二下载Caffe如果安装的是opencv30...

2016-01-08 14:40:26

阅读数:7150

评论数:2

Putty: _tkinter.TclError: no display name and no diplay environment variable

2016-01-08 14:27:59

阅读数:2018

评论数:0

Installing OpenCV for Python on Ubuntu, getting ImportError: No module named cv2.cv

参考paper:http://stackoverflow.com/questions/25215102/installing-opencv-for-python-on-ubuntu-getting-importerror-no-module-named-cv2 错误: ...

2016-01-08 11:16:53

阅读数:3250

评论数:1

大脑视觉处理~~

1. 大脑对视觉信息的处理是分层级的,低级脑区可能处理对边度,边缘什么的,高级脑区处理更抽象的比如人脸啊,房子啊,物体的运动之类的。信息被一层一层抽提出来往上传递进行处理。 2. 大脑对视觉信息的处理也是并行的,不同的脑区提取出不同的信息干不同的活,有的负责处理这个物体是什么,有的负责处理这个物...

2015-12-27 16:44:49

阅读数:1677

评论数:0

Matlab实现灰度图像的水平和垂直投影

clear all clc close all %% 读入图像数据 I=imread('2.bmp'); % I=rgb2gray(I); [m n]=size(I); % 求垂直投影 for y=1:n      S(y)=sum(I(1:m,y)); end y=1:n;...

2015-12-15 19:17:52

阅读数:6364

评论数:0

图像搜索目标框---Matlab中regionprops的使用示例

图像搜索目标框 版权声明:本文为shaoxiaohu原创文章,欢迎转载,请注明出处,谢谢。 有这样一幅图, 我们想获取其中的连通区域,可以使用以下代码: [plain] view plaincopy ...

2015-12-15 19:16:50

阅读数:3018

评论数:2

VS2010+Opencv-2.4.0的配置攻略

VS2010+Opencv-2.4.0的配置攻略 http://www.cnblogs.com/freedomshe/archive/2012/04/25/2470540.html

2015-12-14 17:41:26

阅读数:780

评论数:0

第一个python程序出错,SyntaxError: invalid syntax

不废话,上图~

2015-12-10 16:41:48

阅读数:3458

评论数:0

python获取当前路径的方法

python获取当前路径的方法 >>> import os >>> homedir = os.getcwd() >>> print homedir D:\python\test http://www.cnblogs.c...

2015-12-10 15:08:55

阅读数:1125

评论数:0

Caffe编译出错:/usr/bin/ld: cannot find lcblas

错误如下: BLAS或许是没有安装,或许是路径有问题。 安装这个即可:

2015-11-17 11:14:56

阅读数:6533

评论数:1

Caffe编译出问题:This tool requires OpenCV; compile with USE_OPENCV.

解决方法: 在Makefile.config文件中,添加: USE_OPENCV := 0 即可正常编译。 参考文件: https://groups.google.com/forum/m/#!topic/caffe-users/-zvZ9_RQapI https...

2015-11-12 21:49:11

阅读数:3373

评论数:3

修改paper的时候,一些标记符号

 \newcommand{\cy}[1]{{\color{blue}#1}} \newcommand{\cyC}[1]{{\color{red}[#1: cy's comments to be removed!]}}

2015-09-09 20:04:48

阅读数:1063

评论数:0

latex 下划线

 \uline{concat}

2015-09-09 20:02:32

阅读数:928

评论数:0

latex 删除标记

 \sout{spatisal}

2015-09-09 19:27:38

阅读数:1612

评论数:0

LaTex表格内单元格内容强制换行

 /newcommand{/tabincell}[2]{/begin{tabular}{@{}#1@{}}#2/end{tabular}}%放在导言区 %然后使用&/tabincell{c}{}&就可以在表格中自动换行 %比如这么用 /begin{tabular}{|c...

2015-09-08 16:38:09

阅读数:3350

评论数:0

Evernote 整理文档好工具 可同步

https://evernote.com/ 下载地址。。。

2015-08-24 15:15:43

阅读数:782

评论数:0

arxiv about computer vision and pattern recognition

Address: http://arxiv.org/list/cs.CV/recent Be updated everyday,  check it everyday.

2015-08-05 11:05:14

阅读数:695

评论数:0

Yann LeCun video: (What's Wrong with Deep Learning?)

video address: http://techtalks.tv/talks/whats-wrong-with-deep-learning/61639/

2015-08-05 11:03:10

阅读数:846

评论数:0

Image Super-Resolution Using Deep Convolutional Network (with demo)

Paper:  Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang, "Image Super-Resolution Using Deep Convolutional Networks", http://arxiv.or...

2015-08-05 11:01:18

阅读数:1816

评论数:0

RGB-D 图像 (Semantic Pose using Deep Networks Trained on Synthetic RGB-D)

RGB-D图像其实是两幅图像:一个是普通的RGB三通道彩色图像,另一个是Depth图像。Depth图像类似于灰度图像,只是它的每个像素值是传感器距离物体的实际距离。通常RGB图像和Depth图像是配准的,因而像素点之间具有一对一的对应关系。 利用Kinect可以采集RGB-D 图像。。。 可以...

2015-08-05 10:56:43

阅读数:1578

评论数:0

Recurrent network model for kinematic tracking

Model:   Encoder-Recurrent-Decoder (ERD) model  Task: for recognition and prediction of human body pose in videos and motion capture....          s...

2015-08-04 12:25:27

阅读数:743

评论数:0

CUDA 打印输出 printf

示例:       printf("%d\n",mask[ph * pooled_width + pw]);

2015-07-31 16:49:06

阅读数:3277

评论数:0

解决办法:matlab Exception in thread "AWT-EventQueue-0" java.lang.OutOfMemoryError: Java heap

好几天没用matlab。。。 竟然有问题了,不停的弹出。。。 Exception in thread "AWT-EventQueue-0" java.lang.OutOfMemoryError: Java heap 解决办法: 在C:\Users\$username$...

2015-07-30 10:34:07

阅读数:9220

评论数:0

Interaction between Visual cortex (biological) and computer vision

Deep hierarchies in the primate visual cortex: what can we learn for computer vision?  TPAMI 2013 august.....

2015-07-24 11:15:28

阅读数:561

评论数:0

Semantic segmentation (with deconvolutional CNN) 作者公布源码和模型

作者主页:http://cvlab.postech.ac.kr/~hyeonwoonoh/ 看到这两篇工作,因为公布了好多有用的layer,融合了unpooling layer,batch normorlization layer.... 同时公布了protxt, model等文件。。 1、...

2015-07-21 20:06:14

阅读数:8716

评论数:1

CIFAR数据库预处理 (python)

code说明和下载地址: http://deeplearning.net/software/pylearn2/tutorial/index.html#tutorial

2015-07-13 17:02:54

阅读数:1089

评论数:0

notepad++ 联想输入 如何关掉

转自:http://www.zixue7.com/forum.php?mod=viewthread&tid=18932 有时候这个提示好烦人,要去掉,怎么办? 中文版:菜单栏,设置-----首选项---自动完成-----去掉勾 英文...

2015-06-22 10:21:17

阅读数:5931

评论数:1

Image Super-Resolution using CNN

paper:         Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. Learning a Deep Convolutional Network for Image Super-Resolution, in Proceedin...

2015-06-20 17:22:34

阅读数:6809

评论数:0

Zero-shot learning on the ImageNet of over 20000 classes

Devise: A deep visual-semantic embedding model (NIPS2013) Zero-Shot Learning by Convex Combination of Semantic Embeddings (http://arxiv.org/...

2015-06-05 10:44:05

阅读数:1444

评论数:0

有公布code。Project-Out Cascaded Regression with an application to Face Alignment

Project-Out Cascaded Regression with an application to Face Alignment 传统方法做的,效果还不错。

2015-06-03 15:41:16

阅读数:1876

评论数:2

Some paper related to Image Deblurring

Generalized Video Deblurring for Dynamic Scenes Kernel Fusion for Better Image Deblurring Deep Convolutional Neural Network for Image Deconvolut...

2015-06-03 15:22:11

阅读数:1210

评论数:0

Scene Labeling with LSTM Recurrent Neural Networks

结果图:

2015-06-03 15:20:35

阅读数:1624

评论数:0

Deep Learning Tutorials

Deep Learning Tutorials: http://deeplearning.net/tutorial/

2015-06-03 15:08:40

阅读数:758

评论数:0

STRIVING FOR SIMPLICITY: THE ALL CONVOLUTIONAL NET _CIFAR10 CIFAR100

网络结构图: 结果还不错。。。

2015-06-03 14:27:33

阅读数:1744

评论数:0

Classify Images with Conceptor Network CIFAR-10 CIFAR-100 MNIST...

2015-06-03 11:25:48

阅读数:1103

评论数:0

常用 blas 函数

转自:http://www.cnblogs.com/huashiyiqike/p/3886670.html

2015-06-02 18:42:57

阅读数:534

评论数:0

Large-scale Scene Understanding (LSUN) 竞赛

http://lsun.cs.princeton.edu/#organizers

2015-06-02 18:33:53

阅读数:826

评论数:0

CVPR15 publiscation list

http://www.cv-foundation.org/openaccess/CVPR2015.py

2015-05-29 11:11:55

阅读数:556

评论数:0

提示
确定要删除当前文章?
取消 删除
关闭
关闭