Visual concept conjunction learning with recurrent neural networks

doi:10.1016/j.neucom.2017.12.068

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Visual concept conjunction learning with recurrent neural networks
	Liang, Kongming 1,2; Chang, Hong 1; Shan, Shiguang 1; Chen, Xilin 1,2
刊名	NEUROCOMPUTING
	2020-06-28
卷号	395 页码:229-236
关键词	Attribute learning Concept conjunction Visual relationship detection Image retrieval
ISSN号	0925-2312
DOI	10.1016/j.neucom.2017.12.068
英文摘要	Learning the conjunction of multiple visual concepts shows practical significance in various real world applications (e.g. multi-attribute image retrieval and visual relationship detection). In this paper, we propose Concept Conjunction Recurrent Neural Network ((CRNN)-R-2) to tackle this problem. With our model, visual concepts involved in a conjunction are mapped into the hidden units and combined in a recurrent way to generate the representation of the concept conjunction, which is then used to compute a concept conjunction classifier as the output. We also present an order invariant version of the proposed method based on attention mechanism to learn the tasks without pre-defined concept order. To tackle concept conjunction learning from multiple semantic domains, we introduce a multiplicative framework to learn the joint representation. Experimental results on multi-attribute image retrieval and visual relationship detection show that our method achieves significantly better performance than other related methods on various datasets. (C) 2019 Published by Elsevier B.V.
资助项目	973 Program[2015CB351802] ; Natural Science Foundation of China[61390515]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000536809500005
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/15281]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chang, Hong
作者单位	1.Chinese Acad Sci, Inst Comp Technol, CAS, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Liang, Kongming,Chang, Hong,Shan, Shiguang,et al. Visual concept conjunction learning with recurrent neural networks[J]. NEUROCOMPUTING,2020,395:229-236.
APA	Liang, Kongming,Chang, Hong,Shan, Shiguang,&Chen, Xilin.(2020).Visual concept conjunction learning with recurrent neural networks.NEUROCOMPUTING,395,229-236.
MLA	Liang, Kongming,et al."Visual concept conjunction learning with recurrent neural networks".NEUROCOMPUTING 395(2020):229-236.