Sciweavers

185 search results - page 2 / 37
» Tracking Discontinuous Motion Using Bayesian Inference
Sort
View
HYBRID
2000
Springer
15 years 1 months ago
A Dynamic Bayesian Network Approach to Tracking Using Learned Switching Dynamic Models
Abstract. Switching linear dynamic systems (SLDS) attempt to describe a complex nonlinear dynamic system with a succession of linear models indexed by a switching variable. Unfortu...
Vladimir Pavlovic, James M. Rehg, Tat-Jen Cham
DAGM
2003
Springer
15 years 2 months ago
A Generative Model Based Approach to Motion Segmentation
We address the question of how to choose between different likelihood functions for motion estimation. To this end, we formulate motion estimation as a problem of Bayesian inferen...
Daniel Cremers, Alan L. Yuille
NIPS
2000
14 years 11 months ago
Learning Switching Linear Models of Human Motion
The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. Effective models of human dynamics can be learned from motion capture data usi...
Vladimir Pavlovic, James M. Rehg, John MacCormick
71
Voted
ICCV
2005
IEEE
15 years 3 months ago
Bi-Directional Tracking Using Trajectory Segment Analysis
In this paper, we present a novel approach to keyframe-based tracking, called bi-directional tracking. Given two object templates in the beginning and ending keyframes, the bi-dire...
Jian Sun, Weiwei Zhang, Xiaoou Tang, Heung-Yeung S...
PCM
2004
Springer
168views Multimedia» more  PCM 2004»
15 years 3 months ago
Approximating Inference on Complex Motion Models Using Multi-model Particle Filter
Abstract. Due to its great ability of conquering clutters, which is especially useful for high-dimensional tracking problems, particle filter becomes popular in the visual trackin...
Jianyu Wang, Debin Zhao, Shiguang Shan, Wen Gao