Image Categorization by Learning a Propagated Graphlet Path | |
Zhang, Luming1; Hong, Richang1; Gao, Yue2; Ji, Rongrong3; Dai, Qionghai2; Li, Xuelong4 | |
作者部门 | 光学影像学习与分析中心 |
2016-03-01 | |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
ISSN | 2162-237X |
卷号 | 27期号:3页码:674-685 |
产权排序 | 4 |
摘要 | Spatial pyramid matching is a standard architecture for categorical image retrieval. However, its performance is largely limited by the prespecified rectangular spatial regions when pooling local descriptors. In this paper, we propose to learn object-shaped and directional receptive fields for image categorization. In particular, different objects in an image are seamlessly constructed by superpixels, while the direction captures human gaze shifting path. By generating a number of superpixels in each image, we construct graphlets to describe different objects. They function as the object-shaped receptive fields for image comparison. Due to the huge number of graphlets in an image, a saliency-guided graphlet selection algorithm is proposed. A manifold embedding algorithm encodes graphlets with the semantics of training image tags. Then, we derive a manifold propagation to calculate the postembedding graphlets by leveraging visual saliency maps. The sequentially propagated graphlets constitute a path that mimics human gaze shifting. Finally, we use the learned graphlet path as receptive fields for local image descriptor pooling. The local descriptors from similar receptive fields of pairwise images more significantly contribute to the final image kernel. Thorough experiments demonstrate the advantage of our approach. |
文章类型 | Article |
关键词 | Feature Learning Image Categorization Manifold Embedding Object Shaped Propagation |
学科领域 | 计算机应用其他学科(含图像处理) |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TNNLS.2015.2444417 |
收录类别 | SCI ; EI |
关键词[WOS] | OBJECT RECOGNITION ; MEAN SHIFT ; MACHINES |
语种 | 英语 |
WOS研究方向 | Computer Science ; Engineering |
项目资助者 | State High-Tech Development Plan(2014AA015104) ; Program for New Century Excellent Talents in University(NCET-13-0764) ; Shaanxi Key Innovation Team of Science and Technology(2012KCT-04) |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000372022900014 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/27893 |
专题 | 光谱成像技术研究室 |
作者单位 | 1.Hefei Univ Technol, Dept Elect Engn & Informat Syst, Hefei 230009, Peoples R China 2.Tsinghua Univ, Beijing 100084, Peoples R China 3.Xiamen Univ, Sch Informat Sci & Engn, Dept Cognit Sci, Xiamen 361006, Peoples R China 4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning, Xian 710119, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Luming,Hong, Richang,Gao, Yue,et al. Image Categorization by Learning a Propagated Graphlet Path[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2016,27(3):674-685. |
APA | Zhang, Luming,Hong, Richang,Gao, Yue,Ji, Rongrong,Dai, Qionghai,&Li, Xuelong.(2016).Image Categorization by Learning a Propagated Graphlet Path.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,27(3),674-685. |
MLA | Zhang, Luming,et al."Image Categorization by Learning a Propagated Graphlet Path".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 27.3(2016):674-685. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Image Categorization(4755KB) | 期刊论文 | 作者接受稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
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。
修改评论