LRDNN: Local-refining based deep neural network for person re-identification with attribute discerning

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	LRDNN: Local-refining based deep neural network for person re-identification with attribute discerning
	Gou, Mengran 1; Zhang, Yulun 1; Sun G(孙干)2,3 ; Lan, Xiangyuan 4; Zhong BN(钟必能)5,6; Zhou, Qinqin 6
	2019
会议日期	August 10-16, 2019
会议地点	Macao, China
页码	1041-1047
英文摘要	Recently, pose or attribute information has been widely used to solve person re-identification (re-ID) problem. However, the inaccurate output from pose or attribute modules will impair the final person re-ID performance. Since re-ID, pose estimation and attribute recognition are all based on the person appearance information, we propose a Local-refining based Deep Neural Network (LRDNN) to aggregate pose estimation and attribute recognition to improve the re-ID performance. To this end, we add a pose branch to extract the local spatial information and optimize the whole network on both person identity and attribute objectives. To diminish the negative affect from unstable pose estimation, a novel structure called channel parse block (CPB) is introduced to learn weights on different feature channels in pose branch. Then two branches are combined with compact bilinear pooling. Experimental results on Market1501 and DukeMTMC-reid datasets illustrate the effectiveness of the proposed method.
源文献作者	Baidu ; et al. ; Huawei ; International Joint Conferences on Artifical Intelligence (IJCAI) ; Sony ; Xiao-i
产权排序	4
会议录	Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
会议录出版者	International Joint Conferences on Artificial Intelligence
语种	英语
ISSN号	1045-0823
ISBN号	978-0-9992411-4-1
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/25875]
专题	沈阳自动化研究所_机器人学研究室
作者单位	1.Department of ECE, Northeastern University, United States 2.University of Chinese Academy of Sciences, China 3.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China 4.Department of Computer Science, Hong Kong Baptist University, Hong Kong 5.Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, China 6.Department of Computer Science and Technology, Huaqiao University, China
推荐引用方式 GB/T 7714	Gou, Mengran,Zhang, Yulun,Sun G,et al. LRDNN: Local-refining based deep neural network for person re-identification with attribute discerning[C]. 见:. Macao, China. August 10-16, 2019.