BROWSE
Detail
Conference Paper
Patched-based Deep Boltzmann Shape Priors for Visual Tracking
Cited 0 time in 
Download 7 time
Share 
Download 7 time
Share
- Authors
- Sanghoon Lee, Ilhong Shin, Eunjun Rhee, Sunghee Lee, Namkyung Lee
- Issue Date
- 2017-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2017, pp.1110-1112
- Language
- English
- Type
- Conference Paper
- Project Code
- 17HR1800, Development of Digilog Signage System on Non-planar Screen, Lee Nam Kyung
- Abstract
- In this paper, we propose a patched-based deep Boltzmann shape priors for visual tracking. The shape priors are generated from deep Boltzmann machine network. The network consists of three layers of hidden and visible units. The generated shapes not only maintain general shapes from a variety of poses, but also entail local modifications with high probability.
- KSP Keywords
- Deep Boltzmann machine(DBM), Local modifications, Visual Tracking, shape prior, three layers