Patched-Based. Deep Boltzmann Shape Priors For Visual Tracking

Sanghoon Lee,Ilhong Shin,Eunjun Rhee,Sunghee Lee,Namkyung Lee

2017 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY CONVERGENCE (ICTC)（2017）

引用 0|浏览21

暂无评分

摘要

In this paper, we propose a patched-based deep Boltzmann shape priors for visual tracking. The shape priors are generated front deep Boltzmann machine network. The network consists of three layers of hidden and visible units. The generated shapes not only maintain general shapes front a variety of poses, but also entail local modifications with high probability.

查看译文

关键词

Visual tracking, shape prior, Boltzmann machine

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要