Weakly-supervised scene parsing with multiple contextual cues
文献类型：期刊论文
| 作者 | Teng Li; Xinyu Wu; Bingbing Ni; Ke Lu; Shuicheng Yan |
| 刊名 | Information Sciences
 |
| 出版日期 | 2015 |
| 英文摘要 | Scene parsing, fully labeling an image with each region corresponding to a label, is one of the core problems of computer vision. Previous methods to this problem usually rely on patchlevel models trained from well labeled data. In this paper, we propose a weakly-supervised scene parsing algorithm that semantically parses a collection of images with multi-label, which is guided by the top-down category models and bottom-up local patch contexts across images that closely related segments usually have similar labels. Images are segmented to patches on multi-level and the contextual relations of patches are discovered via sparse representation by 1 minimization, based on which a graph is constructed. The multi-level spatial context of patches is also embedded in the graph, based on which image-level labels can be propagated to segments optimally. The contextual patch labeling process is formulated in an optimization framework and solved by a convergent iterative method. The category models are learned from the decomposed label representations of the image set and applied to the segments. Final labeling is obtained by combining all the information on pixel level. The effectiveness of the proposed method is demonstrated in experiments on two benchmark datasets and comparisons are taken. |
| 收录类别 | SCI |
| 原文出处 | http://www.sciencedirect.com/science/article/pii/S0020025515004569 |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6670]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | Information Sciences |
| 推荐引用方式 GB/T 7714 | Teng Li,Xinyu Wu,Bingbing Ni,et al. Weakly-supervised scene parsing with multiple contextual cues[J]. Information Sciences,2015. |
| APA | Teng Li,Xinyu Wu,Bingbing Ni,Ke Lu,&Shuicheng Yan.(2015).Weakly-supervised scene parsing with multiple contextual cues.Information Sciences. |
| MLA | Teng Li,et al."Weakly-supervised scene parsing with multiple contextual cues".Information Sciences (2015). |
入库方式： OAI收割
来源：深圳先进技术研究院
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。