Unsupervised Salient Object Detection via Inferring From Imperfect Saliency Models
文献类型:期刊论文
作者 | Quan, Rong1; Han, Junwei1; Zhang, Dingwen1; Nie, Feiping2,3; Qian, Xueming4; Li, Xuelong5; Han, JW (reprint author), Northwestern Polytech Univ, Sch Automat, Xian 710072, Shaanxi, Peoples R China. |
刊名 | IEEE TRANSACTIONS ON MULTIMEDIA |
出版日期 | 2018-05-01 |
卷号 | 20期号:5页码:1101-1112 |
ISSN号 | 1520-9210 |
关键词 | Salient Object Detection Weak Prediction Fusion Strategy Local Spatial Consistency Constraint |
DOI | 10.1109/TMM.2017.2763780 |
产权排序 | 5 |
文献子类 | Article |
英文摘要 | Visual saliency detection has become an active research direction in recent years. A large number of saliency models, which can automatically locate objects of interest in images, have been developed. As these models take advantage of different kinds of prior assumptions, image features, and computational methodologies, they have their own strengths and weaknesses and may cope with only one or a few types of images well. Inspired by these facts, this paper proposes a novel salient object detection approach with the idea of inferring a superior model from a variety of previous imperfect saliency models via optimally leveraging the complementary information among them. The proposed approach mainly consists of three steps. First, a number of existing unsupervised saliency models are adopted to provide weak/imperfect saliency predictions for each region in the image. Then, a fusion strategy is used to fuse each image region's weak saliency predictions into a strong one by simultaneously considering the performance differences among various weak predictions and various characteristics of different image regions. Finally, a local spatial consistency constraint that ensures high similarity of the saliency labels for neighboring image regions with similar features is proposed to refine the results. Comprehensive experiments on five public benchmark datasets and comparisons with a number of state-of-the-art approaches can demonstrate the effectiveness of the proposed work. |
学科主题 | Computer Science, Information Systems |
WOS关键词 | REGION DETECTION ; IMAGE SEGMENTATION ; VISUAL-ATTENTION |
WOS研究方向 | Computer Science ; Telecommunications |
语种 | 英语 |
WOS记录号 | WOS:000430728400007 |
资助机构 | National Science Foundation of China(61473231) |
源URL | [http://ir.opt.ac.cn/handle/181661/30075] |
专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
通讯作者 | Han, JW (reprint author), Northwestern Polytech Univ, Sch Automat, Xian 710072, Shaanxi, Peoples R China. |
作者单位 | 1.Northwestern Polytech Univ, Sch Automat, Xian 710072, Shaanxi, Peoples R China 2.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Shaanxi, Peoples R China 3.Northwestern Polytech Univ, Ctr Opt IMagery Anal & Learning, Xian 710072, Shaanxi, Peoples R China 4.Xi An Jiao Tong Univ, Sch Elect & Informat Engn, Xian 710049, Shaanxi, Peoples R China 5.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China |
推荐引用方式 GB/T 7714 | Quan, Rong,Han, Junwei,Zhang, Dingwen,et al. Unsupervised Salient Object Detection via Inferring From Imperfect Saliency Models[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2018,20(5):1101-1112. |
APA | Quan, Rong.,Han, Junwei.,Zhang, Dingwen.,Nie, Feiping.,Qian, Xueming.,...&Han, JW .(2018).Unsupervised Salient Object Detection via Inferring From Imperfect Saliency Models.IEEE TRANSACTIONS ON MULTIMEDIA,20(5),1101-1112. |
MLA | Quan, Rong,et al."Unsupervised Salient Object Detection via Inferring From Imperfect Saliency Models".IEEE TRANSACTIONS ON MULTIMEDIA 20.5(2018):1101-1112. |
入库方式: OAI收割
来源:西安光学精密机械研究所
其他版本
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。