Group optimization for multi-attribute visual embedding

Group optimization for multi-attribute visual embedding
复制标题

多属性视觉嵌入的分组优化

DOI:
10.1016/j.visinf.2018.09.004
复制
发表时间:
2018-09
期刊:
影响因子:
3
通讯作者:
Yangyan Li
Yangyan Li
中科院分区:
计算机科学4区
文献类型:
--
作者:
Qiong Zeng;Wenzheng Chen;Zhuo Han;Mingyi Shi;Yanir Kleiman;Daniel Cohen Or;Baoquan Chen;Yangyan Li

文献摘要

参考文献

相似文献

理解图像之间的语义相似性是广泛的计算机图形和计算机视觉应用的核心。然而,图像的视觉上下文通常是模糊的,因为可以通过强调不同的属性来感知图像。在本文中,我们提出了一种学习图像之间的语义视觉相似性的方法,推断它们的潜在属性并将它们嵌入到与每个潜在属性相对应的多空间中。我们将多重嵌入问题视为一种优化函数,用于评估定性众包聚类的嵌入距离。我们方法的关键思想是收集并嵌入在集群中共享相同属性的定性成对元组。为了确保多个度量之间的相似属性共享,将图像分类簇呈现给用户并由用户求解。然后将收集的图像簇转换为元组组,将其输入到我们的组优化算法中,该算法联合推断属性相似性和多属性嵌入。我们的多属性嵌入允许检索不同属性空间中的相似对象。实验结果表明,我们的方法在各种数据集上优于最先进的多嵌入方法,并演示了多属性嵌入在图像检索应用中的使用。
Understanding semantic similarity among images is the core of a wide range of computer graphics and computer vision applications. However, the visual context of images is often ambiguous as images that can be perceived with emphasis on different attributes. In this paper, we present a method for learning the semantic visual similarity among images, inferring their latent attributes and embedding them into multi-spaces corresponding to each latent attribute. We consider the multi-embedding problem as an optimization function that evaluates the embedded distances with respect to qualitative crowdsourced clusterings. The key idea of our approach is to collect and embed qualitative pairwise tuples that share the same attributes in clusters. To ensure similarity attribute sharing among multiple measures, image classification clusters are presented to, and solved by users. The collected image clusters are then converted into groups of tuples, which are fed into our group optimization algorithm that jointly infers the attribute similarity and multi-attribute embedding. Our multi-attribute embedding allows retrieving similar objects in different attribute spaces. Experimental results show that our approach outperforms state-of-the-art multi-embedding approaches on various datasets, and demonstrate the usage of the multi-attribute embedding in image retrieval application.
DOI: --
发表时间: 2011-07
期刊: ArXiv
影响因子: --
作者:
O. Tamuz;Ce Liu;Serge J. Belongie;Ohad Shamir;A. Kalai
通讯作者: O. Tamuz;Ce Liu;Serge J. Belongie;Ohad Shamir;A. Kalai
DOI: 10.1109/cvpr.2011.5995595
发表时间: 2011-06
期刊: CVPR 2011
影响因子: --
作者:
Matthijs Douze;Arnau Ramisa;C. Schmid
通讯作者: Matthijs Douze;Arnau Ramisa;C. Schmid
DOI: 10.14778/2350229.2350263
发表时间: 2012-07
期刊: Proc. VLDB Endow.
影响因子: --
作者:
Jiannan Wang;Tim Kraska;M. Franklin;Jianhua Feng
通讯作者: Jiannan Wang;Tim Kraska;M. Franklin;Jianhua Feng
DOI: 10.1007/s11263-015-0816-y
发表时间: 2015-12-01
影响因子: 19.5
作者:
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者: Fei-Fei, Li
DOI: 10.1145/2766959
发表时间: 2015-07
期刊: ACM Transactions on Graphics (TOG)
影响因子: --
作者:
Sean Bell;Kavita Bala
通讯作者: Sean Bell;Kavita Bala