ETRI-Knowledge Sharing Plaform

논문 검색
Type SCI
Year ~ Keyword


Conference Paper Patched-based Deep Boltzmann Shape Priors for Visual Tracking
Cited 0 time in scopus Download 5 time Share share facebook twitter linkedin kakaostory
Sanghoon Lee, Shin Il Hong, Rhee Eun Jun, Lee Sunghee, Lee Nam Kyung
Issue Date
International Conference on Information and Communication Technology Convergence (ICTC) 2017, pp.1110-1112
Project Code
17HR1800, Development of Digilog Signage System on Non-planar Screen, Lee Nam Kyung
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