Knowledge Commons of Institute of Automation,CAS
Facade Labeling via Explicit Matrix Factorization | |
Hongfei Xiao![]() ![]() ![]() ![]() ![]() | |
2014-07 | |
会议名称 | International Conference on Image and Signal Processing |
会议日期 | 2014-7-1 |
会议地点 | Cherbourg, France |
摘要 | Facade labeling, namely semantically segmenting the facade images, requires exploiting the facade regularity. To model the regular-ity, this paper proposes a novel matrix multiplication based formulation. In the model, the regularity is described as generalized translation sym-metry (GTS) which enables varying distances between the repeated elements. Moreover, an explicit and intuitive formulation via matrix multi-plication is also derived for the GTS. That is, the symmetry is interpreted as the product of a repetitive pattern and two block matrices. These two block matrices respectively represent the vertical and horizontal repe-titions. Based on the formulation, facade labeling is reformulated into factorizing the facade to calculate the block matrices. An alternating op-timization algorithm is thus developed to solve the matrix factorization problem, where dynamic programming is used to optimize the block ma-trices. Extensive experiments demonstrate the fidelity of our model and the efficiency of the algorithm. |
关键词 | Facade Labeling Repetition Detection Explicit Formulation Matrix Factorization |
DOI | 10.1007/978-3-319-07998-1_54 |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/20625 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Hongfei Xiao |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Hongfei Xiao,Lingfeng Wang,Gaofeng Meng,et al. Facade Labeling via Explicit Matrix Factorization[C],2014. |
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 | ||
85090468.pdf(3756KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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