상세정보
학술대회
Patched-based Deep Boltzmann Shape Priors for Visual Tracking
- 발행일
- 201710
- 출처
- International Conference on Information and Communication Technology Convergence (ICTC) 2017, pp.1110-1112
- 협약과제
- 17HR1800, 사물스크린 환경 기반의 공간일체형 디지로그 사이니지 기술 개발, 이남경
- 초록
- 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 제안 키워드
- Deep Boltzmann machine(DBM), Local modifications, Visual Tracking, shape prior, three layers