Semantic Photo Retargeting Under Noisy Image Labels
文献类型：期刊论文
| 作者 | Zhang, Luming1; Li, Xuelong2 ; Nie, Liqiang3; Yan, Yan4; Zimmermann, Roger3
|
| 刊名 | acm transactions on multimedia computing communications and applications
 |
| 出版日期 | 2016-06-01 |
| 卷号 | 12期号:3 |
| 关键词 | Algorithm Performance Experimentations Retargeting semantic graphlet aesthetics evaluation image label |
| ISSN号 | 1551-6857 |
| 产权排序 | 2 |
| 英文摘要 | with the popularity of mobile devices, photo retargeting has become a useful technique that adapts a high-resolution photo onto a low-resolution screen. conventional approaches are limited in two aspects. the first factor is the de-emphasized role of semantic content that is many times more important than low-level features in photo aesthetics. second is the importance of image spatial modeling: toward a semantically reasonable retargeted photo, the spatial distribution of objects within an image should be accurately learned. to solve these two problems, we propose a new semantically aware photo retargeting that shrinks a photo according to region semantics. the key technique is a mechanism transferring semantics of noisy image labels (inaccurate labels predicted by a learner like an svm) into different image regions. in particular, we first project the local aesthetic features (graphlets in this work) onto a semantic space, wherein image labels are selectively encoded according to their noise level. then, a category-sharing model is proposed to robustly discover the semantics of each image region. the model is motivated by the observation that the semantic distribution of graphlets from images tagged by a common label remains stable in the presence of noisy labels. thereafter, a spatial pyramid is constructed to hierarchically encode the spatial layout of graphlet semantics. based on this, a probabilistic model is proposed to enforce the spatial layout of a retargeted photo to be maximally similar to those from the training photos. experimental results show that (1) noisy image labels predicted by different learners can improve the retargeting performance, according to both qualitative and quantitative analysis, and (2) the category-sharing model stays stable even when 32.36% of image labels are incorrectly predicted. |
| WOS标题词 | science & technology ; technology |
| 类目[WOS] | computer science, information systems ; computer science, software engineering ; computer science, theory & methods |
| 研究领域[WOS] | computer science |
| 关键词[WOS] | scene |
| 收录类别 | SCI ; EI |
| 语种 | 英语 |
| WOS记录号 | WOS:000379425400003 |
| 源URL | [http://ir.opt.ac.cn/handle/181661/28177]  |
| 专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
| 作者单位 | 1.Hefei Univ Technol, Dept CSIE, Hefei, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China 3.Natl Univ Singapore, Sch Comp, Singapore, Singapore 4.Univ Trento, Dept Informat Engn & Comp Sci, Via Sommar 9, I-38123 Trento, Italy |
| 推荐引用方式 GB/T 7714 | Zhang, Luming,Li, Xuelong,Nie, Liqiang,et al. Semantic Photo Retargeting Under Noisy Image Labels[J]. acm transactions on multimedia computing communications and applications,2016,12(3). |
| APA | Zhang, Luming,Li, Xuelong,Nie, Liqiang,Yan, Yan,&Zimmermann, Roger.(2016).Semantic Photo Retargeting Under Noisy Image Labels.acm transactions on multimedia computing communications and applications,12(3). |
| MLA | Zhang, Luming,et al."Semantic Photo Retargeting Under Noisy Image Labels".acm transactions on multimedia computing communications and applications 12.3(2016). |
入库方式： OAI收割
来源：西安光学精密机械研究所
浏览0
下载0
收藏0
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。