To Aggregate or Not to aggregate: Selective Match Kernels for Image Search
To Aggregate or Not to aggregate: Selective Match Kernels for Image Search
复制标题
DOI：
10.1109/iccv.2013.177
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Giorgos Tolias;Yannis Avrithis;H. Jégou
中科院分区：
文献类型：
--
作者：
Giorgos Tolias;Yannis Avrithis;H. Jégou
本文考虑了一族基于局部描述符的图像比较度量族。它包括VLAD描述符和匹配技术，如汉明嵌入。通过在这些方法之间架起桥梁，我们提出了一种匹配核，它通过结合聚集过程和选择性匹配核来充分利用现有技术。最后，对支持该核的表示进行了近似，提供了精确和可伸缩的大规模图像搜索，如我们在几个基准测试上的实验所显示的那样。
This paper considers a family of metrics to compare images based on their local descriptors. It encompasses the VLAD descriptor and matching techniques such as Hamming Embedding. Making the bridge between these approaches leads us to propose a match kernel that takes the best of existing techniques by combining an aggregation procedure with a selective match kernel. Finally, the representation underpinning this kernel is approximated, providing a large scale image search both precise and scalable, as shown by our experiments on several benchmarks.