cvpr11——Image Retrieval with Geometry-Preserving Visual Phrases
来源:互联网 发布:多线程编程java 编辑:程序博客网 时间:2024/06/05 06:34
Yimeng Zhang, , Zhaoyin Jia, and Tsuhan Chen. “Image Retrieval with Geometry Preserving Visual Phrases” IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (oral presentation, 3.5% acceptance rate) , 2011. [pdf]
这篇文章主要在BoV(bag of visual word)基础上加入了spatial信息,提出了GVP[1](Geometry-Preserving Visual Phrases),其基本思想比较简单,如下图所示:
统计两幅图像中,相同的word之间的距离。设定一阈值k,判断offset space平面中每个方格中的word是否大于k,之后统计GPV的个数。例如上图中:
k=1 GVP的个数为8,k=2 GVP=1(B,F)+1(D,F)+3(3 choose 2, for bin with A;B;C)。之后将GPV融入到索引结果中,其结构如下图:
相当于只增加了位置信息即(划分网格的个数)。
结合TF-IDF机制进行检索,同时可以引入MinHash。效果优于[2][3]。该方法只考虑了平移的特性,对于尺度和旋转在[4]同样可以适合该框架。
[1] Yimeng Zhang, Tsuhan Chen. “Efficient Kernels for Identifying Unbounded Order Spatial Features.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2009. [pdf]
[2] J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Object retrieval with large vocabularies and fast spatial matching. In CVPR, 2007.
[3] Y. Cao, C. Wang, Z. Li, L. Zhang, and L. Zhang. Spatialbag-of-features. In CVPR, 2010.
[4] Yimeng Zhang, Tsuhan Chen. “Weakly Supervised Object Recognition and Localization with Invariant High Order Features.” British Machine Vision Conference (BMVC), 2010. [pdf]
Yimeng Zhang个人主页:http://chenlab.ece.cornell.edu/people/yimeng/
- cvpr11——Image Retrieval with Geometry-Preserving Visual Phrases
- 论文导读(large-scale image retrieval)——large-scale E-commerce Image retrieval with Top-weighted CNN
- 基于Bow模型的图像检索 Image Retrieval with Bag of Visual Words
- [image retrieval] surf and comparison with sift
- (转载)图像检索评估准则——Evaluation Criteria of Image Retrieval : Retrieval Accuracy
- 图像检索评估准则——Evaluation Criteria of Image Retrieval : Retrieval Accuracy
- Image Retrieval
- Image Retrieval
- Manifold Alignment Preserving Global Geometry(笔记)
- Lucene Image retrieval (LIRE)
- LIRE(Lucene Image Retrieval)
- Image Retrieval Framework
- CNN for image retrieval
- Image retrieval C++ implementation
- Image Hash Retrieval
- Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-ide
- 阅读小结:CNN Image Retrieval Learns from BoW:Unsupervised Fine-Tuning with Hard Example:CNN Image Retrie
- LIRE(Lucene Image REtrieval)
- GPGPU::数学基础教程
- 备忘录:java 条形码
- vmware+ubuntu11.04-desktop NAT上网整到吐血!发现原来宿主机是代理上网,在ubuntu上也要加代理!!
- sql语句别名
- discuz xconvert 执行转换 config.inc.php 不可写,转换没法继续啊!!
- cvpr11——Image Retrieval with Geometry-Preserving Visual Phrases
- Linux下Shell脚本输出带颜色文字
- oracle常用命令收集
- 我的博文又开始登上CSDN首页
- heredoc编译的错误分析
- 基本概念
- 第二章 系统架构
- 为什么新人不会编程
- 清除系统垃圾