• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Image Categorization by Learning a Propagated Graphlet Path
【24h】

Image Categorization by Learning a Propagated Graphlet Path

机译：通过学习传播的Graphlet路径进行图像分类

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Spatial pyramid matching is a standard architecture for categorical image retrieval. However, its performance is largely limited by the prespecified rectangular spatial regions when pooling local descriptors. In this paper, we propose to learn object-shaped and directional receptive fields for image categorization. In particular, different objects in an image are seamlessly constructed by superpixels, while the direction captures human gaze shifting path. By generating a number of superpixels in each image, we construct graphlets to describe different objects. They function as the object-shaped receptive fields for image comparison. Due to the huge number of graphlets in an image, a saliency-guided graphlet selection algorithm is proposed. A manifold embedding algorithm encodes graphlets with the semantics of training image tags. Then, we derive a manifold propagation to calculate the postembedding graphlets by leveraging visual saliency maps. The sequentially propagated graphlets constitute a path that mimics human gaze shifting. Finally, we use the learned graphlet path as receptive fields for local image descriptor pooling. The local descriptors from similar receptive fields of pairwise images more significantly contribute to the final image kernel. Thorough experiments demonstrate the advantage of our approach.
机译：空间金字塔匹配是用于分类图像检索的标准体系结构。但是，在合并本地描述符时，其性能在很大程度上受到预定的矩形空间区域的限制。在本文中，我们提议学习对象形和方向性接收场以进行图像分类。尤其是，图像中的不同对象是由超像素无缝构建的，而方向则捕获了人的视线移动路径。通过在每个图像中生成多个超像素，我们构造了可描述不同对象的图小图。它们用作图像比较对象形状的接收场。由于图像中的小图数量众多，提出了一种基于显着性的小图选择算法。流形嵌入算法使用训练图像标签的语义对图集进行编码。然后，我们导出流形传播，以利用视觉显着性图来计算嵌入后的小图。顺序传播的小图构成了模仿人类凝视移动的路径。最后，我们将学习到的graphlet路径用作本地图像描述符池的接受域。来自成对图像相似接受域的局部描述符对最终图像内核的贡献更大。全面的实验证明了我们方法的优势。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号