Frustratingly Easy Cross-Modal Hashing

doi:10.1145/2964284.2967218

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Frustratingly Easy Cross-Modal Hashing
	Dekui Ma 1; Jian Liang2,4 ; Xiangwei Kong 1; Ran He(赫然)2,3 ; Liang, Jian
	2016
会议日期	October 15 - 19, 2016
会议地点	Amsterdam, The Netherlands
关键词	Cross-modal Hashing
DOI	10.1145/2964284.2967218
英文摘要	Cross-modal hashing has attracted considerable attention due to its low storage cost and fast retrieval speed. Recently, more and more sophisticated researches related to this topic are proposed. However, they seem to be inefficient computationally for several reasons. On one hand, learning coupled hash projections makes the iterative optimization problem challenging. On the other hand, individual collective binary codes for each content are also learned with a high computation complexity. In this paper we describe a simple yet effective cross-modal hashing approach that can be implemented in just three lines of code. This approach first obtains the binary codes for one modality via unimodal hashing methods (e.g., iterative quantization (ITQ)), then applies simple linear regression to project the other modalities into the obtained binary subspace. Obviously, it is non-iterative and parameter-free, which makes it more attractive for many real-world applications. We further compare our approach with other state-of-the-art methods on four benchmark datasets (i.e., the Wiki, VOC, LabelMe and NUS-WIDE datasets). Despite its extraordinary simplicity, our approach performs remarkably and generally well for these datasets under different experimental settings (i.e., large-scale, high-dimensional and multi-label datasets).
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/20125]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Liang, Jian
作者单位	1.School of Information and Communication Engineering, Dalian University of Technology 2.Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), CASIA 3.CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) 4.University of Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Dekui Ma,Jian Liang,Xiangwei Kong,et al. Frustratingly Easy Cross-Modal Hashing[C]. 见:. Amsterdam, The Netherlands. October 15 - 19, 2016.