QQ客服 官方微博 反馈留言

	Weakly Supervised Learning for Attribute Localization in Outdoor Scenes
	Wang, Shuo ; Joo, Jungseock ; Wang, Yizhou ; Zhu, Song-Chun
	2013
英文摘要	In this paper, we propose a weakly supervised method for simultaneously learning scene parts and attributes from a collection of images associated with attributes in text, where the precise localization of the each attribute left unknown. Our method includes three aspects. (i) Compositional scene configuration. We learn the spatial layouts of the scene by Hierarchical Space Tiling (HST) representation, which can generate an excessive number of scene configurations through the hierarchical composition of a relatively small number of parts. (ii) Attribute association. The scene attributes contain nouns and adjectives corresponding to the objects and their appearance descriptions respectively. We assign the nouns to the nodes (parts) in HST using non-maximum suppression of their correlation, then train an appearance model for each noun+adjective attribute pair. (iii) Joint inference and learning. For an image, we compute the most probable parse tree with the attributes as an instantiation of the HST by dynamic programming. Then update the HST and attribute association based on the inferred parse trees. We evaluate the proposed method by (i) showing the improvement of attribute recognition accuracy; and (ii) comparing the average precision of localizing attributes to the scene parts.; Computer Science, Artificial Intelligence; CPCI-S(ISTP); 3
语种	英语
DOI标识	10.1109/CVPR.2013.400
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/405762]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Wang, Shuo,Joo, Jungseock,Wang, Yizhou,et al. Weakly Supervised Learning for Attribute Localization in Outdoor Scenes. 2013-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。