Multi-image aggregation for better visual object retrieval
Multi-image aggregation for better visual object retrieval
复制标题
DOI：
10.1109/icassp.2014.6854414
复制
发表时间：
2014-05
期刊：
影响因子：
--
通讯作者：
Cai-Zhi Zhu;Yu-Hui Huang;S. Satoh
中科院分区：
文献类型：
--
作者：
Cai-Zhi Zhu;Yu-Hui Huang;S. Satoh
我们研究在查询或数据库端聚合多个图像如何影响词袋框架中视觉对象检索的性能。为此，我们首先比较五种不同的多图像聚合方法，并建议在大多数情况下选择平均池化方法，因为它在准确性、速度和内存占用方面具有优越的优势。然后我们通过实验证明更多的图像通常会产生更好的检索性能。更重要的是，我们说明了简单地聚合查询图像而不进行选择远非最佳。在三个大型对象检索数据集上进行了综合实验，并取得了新的最先进水平。这项研究可以在一些实际应用中利用，例如移动搜索，一旦用户捕捉多个查询图像，检索性能就会得到提高。
We study how aggregating multiple images, on query or database side, impacts the performance of visual object retrieval in a Bag-of-Words framework. To this end, we first compare five different multi-image aggregation methods, and suggest selecting the average pooling method in most cases for its superior advantages in accuracy, speed, and memory footprint. Then we prove with experiments that more images generally yield better retrieval performance. What is more, we illustrate that simply aggregating query images without selection is far from optimal. Comprehensive experiments were conducted on three large-scale object retrieval datasets, and the new state-of the-art was achieved. This research can be leveraged in some real applications such as mobile search, where the retrieval performance will be improved once users snap multiple query images.