关闭
当前搜索:

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 architecture that includes warping of the second image with ...
阅读(14) 评论(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 CNN end-to-end to learn predicting the optical flow f...
阅读(15) 评论(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 nearby features along the motion path, and thus impro...
阅读(8) 评论(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/...
阅读(1338) 评论(0)

How to set $LD_LIBRARY_PATH in Ubuntu?

http://serverfault.com/questions/201709/how-to-set-ld-library-path-in-ubuntu...
阅读(737) 评论(0)

Basic build issue regarding libs, pkg-config and opencv

http://stackoverflow.com/questions/10526124/basic-build-issue-regarding-libs-pkg-config-and-opencv...
阅读(695) 评论(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,求星星啊,求星星啊(原谅我那么不要脸~~) 在之前两篇文章中我介绍了怎么编译Fast RCNN,和...
阅读(11293) 评论(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编译Caffe配置pycaffe配置matcaffe 前言: 按照Ca...
阅读(6980) 评论(2)

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

...
阅读(1709) 评论(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: 解决办法:...
阅读(2871) 评论(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体是怎么动的。 3. 脑区之间存在着广泛的联系,同时高级皮层对低级皮层也有很多的反馈投射。 ...
阅读(1318) 评论(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:...
阅读(5717) 评论(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://github.com/BVLC/caffe/blob/master/Makefile.confi...
阅读(2832) 评论(3)

arxiv about computer vision and pattern recognition

Address: http://arxiv.org/list/cs.CV/recent Be updated everyday,  check it everyday....
阅读(598) 评论(0)

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

video address: http://techtalks.tv/talks/whats-wrong-with-deep-learning/61639/...
阅读(733) 评论(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.org/abs/1501.0009  "For Creators", http://piapro.net/en_for_cr...
阅读(1447) 评论(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。。。 可以参考: Lai, K.; Bo, L.; Ren, X. & Fox, D. A large-sca...
阅读(1106) 评论(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....          specially, motion capture generation, body pose labe...
阅读(701) 评论(0)

CUDA 打印输出 printf

示例:       printf("%d\n",mask[ph * pooled_width + pw]);...
阅读(2584) 评论(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........
阅读(534) 评论(0)
85条 共5页1 2 3 4 5 ... 下一页 尾页
    个人资料
    • 访问:1848392次
    • 积分:19562
    • 等级:
    • 排名:第495名
    • 原创:285篇
    • 转载:157篇
    • 译文:19篇
    • 评论:258条
    最新评论