Object Localization Based on Proposal Fusion

doi:10.1109/TMM.2017.2729786

	Object Localization Based on Proposal Fusion
	Tang, Sheng 1,2; Li, Yu 1,2; Deng, Lixi 1,2; Zhang, Yongdong 1,2
	2017-09-01
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	19 期号:9 页码:2105-2116
摘要	Traditional regression framework of object localization such as Overfeat often suffers from the problem of inaccurate scoring due to the separate scoring of classification network and regression network upon inconsistent regions. To tackle this problem, in this paper, we propose a novel object localization framework based on multiple complementary region proposal methods from the view of classification rather than regression. On top of our framework, we first combine multiple complementary region proposals during both training and testing as a means of data augmentation to generate more dense and reliable proposals for fusion, then achieve optimal compromise between complexity and efficiency through category clustering for bounding box sharing among similar categories, and finally propose a dense proposal fusion approach to merge dense region proposals near true object for fine-tuning of the final bounding box's coordinates and updating the confidence of fused proposals for final decision. Extensive experiments on the well-known large scale ILSVRC 2015 LOC dataset verify the effectiveness of our object localization framework.
关键词	Dense proposal fusion object localization object detection region proposal
DOI	10.1109/TMM.2017.2729786
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61525206] ; National Natural Science Foundation of China[61572472] ; National Key Research and Development Program of China[2016YFB0800403] ; Beijing Natural Science Foundation[4152050] ; Beijing Advanced Innovation Center for Imaging Technology[BAICIT-2016009]
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000411244200013
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：19[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/6814
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Yongdong
作者单位	1.Chinese Acad Sci, Inst Comp Technol, 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	Tang, Sheng,Li, Yu,Deng, Lixi,et al. Object Localization Based on Proposal Fusion[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2017,19(9):2105-2116.
APA	Tang, Sheng,Li, Yu,Deng, Lixi,&Zhang, Yongdong.(2017).Object Localization Based on Proposal Fusion.IEEE TRANSACTIONS ON MULTIMEDIA,19(9),2105-2116.
MLA	Tang, Sheng,et al."Object Localization Based on Proposal Fusion".IEEE TRANSACTIONS ON MULTIMEDIA 19.9(2017):2105-2116.