Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios

CASIA OpenIR > 模式识别实验室

	Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios
	Dangwei Li; Xiaotang Chen; Kaiqi Huang
	2015
会议名称	Asian Conference on Pattern Recognition
会议录名称	Proc. Asian Conference on Pattern Recognition 2015
页码	1-5
会议日期	2015-11-01
会议地点	Kuala Lumpur, Malaysia
摘要	In real video surveillance scenarios, visual pedestrian attributes, such as gender, backpack, clothes types, are very important for pedestrian retrieval and person re-identification. Existing methods for attributes recognition have two drawbacks: (a) handcrafted features (e.g. color histograms, local binary patterns) cannot cope well with the difficulty of real video surveillance scenarios; (b) the relationship among pedestrian attributes is ignored. To address the two drawbacks, we propose two deep learning based models to recognize pedestrian attributes. On the one hand, each attribute is treated as an independent component and the deep learning based single attribute recognition model (DeepSAR) is proposed to recognize each attribute one by one. On the other hand, to exploit the relationship among attributes, the deep learning framework which recognizes multiple attributes jointly (DeepMAR) is proposed. In the DeepMAR, one attribute can contribute to the representation of other attributes. For example, the gender of woman can contribute to the representation of long hair and wearing skirt. Experiments on recent popular pedestrian attribute datasets illustrate that our proposed models achieve the state-of-the-art results.
关键词	Multi-attribute Learning
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12681
专题	模式识别实验室
通讯作者	Kaiqi Huang
作者单位	中国科学院自动化研究所
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Dangwei Li,Xiaotang Chen,Kaiqi Huang. Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios[C],2015:1-5.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
multiattribute_acpr1（247KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载