QQ客服 官方微博 反馈留言

	Enhancing Sketch-Based Image Retrieval via Deep Discriminative Representation
	Huang, Fei1; Cheng, Yong1; Jin, Cheng1; Zhang, Yuejie1; Zhang, Tao2
	2016
卷号	285
DOI	10.3233/978-1-61499-672-9-1626
页码	1626-1627
英文摘要	In this paper we aim to employ deep learning to enhance SBIR via deep discriminative representation. Our main contributions focus on: 1) The deep discriminative representation is established to bridge both the visual appearance gap and the semantic gap between sketches and images; 2) The deep learning pattern is applied to our SBIR model through training on our transformed sketch-like images to overcome the rarity of training sketches. Our experiments on a large number of public sketch and image data have obtained very positive results.
会议录出版者	IOS PRESS
会议录出版地	NIEUWE HEMWEG 6B, 1013 BG AMSTERDAM, NETHERLANDS
语种	英语
WOS研究方向	Computer Science
WOS记录号	WOS:000385793700217
内容类型	会议论文
源URL	[http://10.2.47.112/handle/2XS4QKH4/3373]
专题	上海财经大学
作者单位	1.Fudan Univ, Sch Comp Sci, Shanghai Key Lab Intelligent Informat Proc, Shanghai, Peoples R China; 2.Shanghai Univ Finance & Econ, Sch Informat Management & Engn, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Huang, Fei,Cheng, Yong,Jin, Cheng,et al. Enhancing Sketch-Based Image Retrieval via Deep Discriminative Representation[C]. 见:.

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。