Combining attributes and Fisher vectors for efficient image retrieval
Combining attributes and Fisher vectors for efficient image retrieval
复制标题
DOI：
10.1109/cvpr.2011.5995595
复制
发表时间：
2011-06
期刊：
影响因子：
--
通讯作者：
Matthijs Douze;Arnau Ramisa;C. Schmid
中科院分区：
文献类型：
--
作者：
Matthijs Douze;Arnau Ramisa;C. Schmid
最近的研究表明，属性对于类别识别具有很好的效果。在本文中，我们展示了它们在图像检索方面的性能。首先，我们证明了基于属性向量检索特定对象的图像给出了与现有技术水平相当的结果。其次，我们证明了结合属性和Fisher向量可以提高特定对象和类别的检索性能。第三，我们实现了一种高效的编码技术，将组合的描述符压缩成非常小的代码。在Holidays数据集上的实验结果表明，即使对于每幅图像16个字节的非常紧凑的表示，我们的方法也明显优于最新技术。检索类别图像是在“Web-Queries”数据集上评估的。结果表明，属性特征与Fisher向量相结合可以提高识别性能，图像特征与文本特征相结合可以作为文本特征的补充。
Attributes were recently shown to give excellent results for category recognition. In this paper, we demonstrate their performance in the context of image retrieval. First, we show that retrieving images of particular objects based on attribute vectors gives results comparable to the state of the art. Second, we demonstrate that combining attribute and Fisher vectors improves performance for retrieval of particular objects as well as categories. Third, we implement an efficient coding technique for compressing the combined descriptor to very small codes. Experimental results on the Holidays dataset show that our approach significantly outperforms the state of the art, even for a very compact representation of 16 bytes per image. Retrieving category images is evaluated on the “web-queries” dataset. We show that attribute features combined with Fisher vectors improve the performance and that combined image features can supplement text features.