Location:
Search - saliency m
Search list
Description: GPU based saliency map generation and selective rendering paper.
Platform: |
Size: 3811328 |
Author: alok |
Hits:
Description: 本代码为清华大学程明明在2011年CVPR上发表的一篇视觉显著性的源代码。-It is the source code of visual saliency detection proposed by M.M Cheng in CVPR2011, which is coded by C++.
Platform: |
Size: 27437056 |
Author: wang |
Hits:
Description: 本资源是清华大学程明明在2011年CVPR上发表的一篇关于视觉显著性的代码，资源包括原文及matlab版本的代码。-It is a source code of visual saliency detection proposed by M.M Cheng in cvpr2011.And it is coded with matlab.
Platform: |
Size: 15614976 |
Author: wang |
Hits:
Description: 提出一种新的显着性检测方法，通过将区域级显着性估计和像素级显着性预测与CNN（表示为CRPSD）相结合。对于像素级显着性预测，通过修改VGGNet体系结构来执行完全卷积神经网络（称为像素级CNN）以执行多尺度特征学习，基于该学习进行图像到图像预测以完成像素级显着性检测。对于区域级显着性估计，首先设计基于自适应超像素的区域生成技术以将图像分割成区域，基于该区域通过使用CNN模型（称为区域级CNN）来估计区域级显着性。通过使用另一CNN（称为融合CNN）融合像素级和区域级显着性以形成nal显着图，并且联合学习像素级CNN和融合CNN。对四个公共基准数据集的大量定量和定性实验表明，所提出的方法大大优于最先进的显着性检测方法。-A new saliency detection method by significant regional level estimates and forecast significant pixel level and CNN (expressed as CRPSD) combined. For pixel-level significant prediction to perform a full convolution neural network by modifying VGGNet architecture (called pixel-level CNN) learning to perform multi-scale features, image to image prediction to complete the pixel level detection based on the significant learning . For regional levels significantly estimate, the first generation technology to design image is divided into regions based on adaptive super-pixel area, based on the model of the region through the use of CNN (CNN called regional level) to estimate regional levels significantly. By using another CNN (CNN called fusion) Fusion pixel level and regional level to form nal significant saliency map, and the Joint Learning pixel level fusion CNN and CNN. Four common reference data set of a large number of quantitative and qualitative experiments show that the proposed m
Platform: |
Size: 4427776 |
Author: 祖祖- |
Hits:
Description: 参照psychophysicsexample.m写了一个main函数，调用AIM.m 直接运行main函数就可以了
显著性模型-Saliency based on information maximization
Platform: |
Size: 26362880 |
Author: 张明航 |
Hits:
Description: 基于贝叶斯框架的显著性检测
saliencyimage.msaliencyimage_convolution.m作用一样，运行结果差不多，saliencyimage_convolution.m
处理大图像时用它，比较节省内存空间。-A bayesian framework for saliency using
Platform: |
Size: 2944000 |
Author: 张明航 |
Hits:
Description: GBVS显著性
直接运行mean_Itti.m
直接运行mean_gbvs.m-Graph-Based Visual Saliency
Platform: |
Size: 12936192 |
Author: 张明航 |
Hits:
Description: 显著性物体检测的matlab代码实现
Rahtu E & Kannala J & Salo M & Heikkil? J (2010) Segmenting salient objects from images and Videos. Proc. European Conference on Computer Vision (ECCV 2010)(Matlab codes for measuring image saliency
Segmenting salient objects from images and Videos)
Platform: |
Size: 4096 |
Author: 毕小敏 |
Hits:
Description: BMS saliency model的代码，The code has been tested on Windows system, using Matlab 2012 and OpenCV 2.40+.(The code has been tested on Windows system, using Matlab 2012 and OpenCV 2.40+.
To compile the code (only for Windows):
1. Put the extracted files in a**<root_dir>**.
2. Install OpenCV 2.40+.
3. Go to**<root_dir>/mex * and specify the relevant OpenCV paths at the
begining of the**compile.m**.
4. Run**compile.m** in Matlab.
5. Go to**<root_dir>** and run**demo.m** in Matlab.)
Platform: |
Size: 844800 |
Author: 车朝晖 |
Hits: