Sciweavers

144 search results - page 5 / 29
» Discriminative Tracking by Metric Learning
Sort
View
ECCV
2008
Springer
14 years 11 months ago
Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers
Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the fie...
Gérard G. Medioni, Qian Yu, Thang Ba Dinh
CVPR
2009
IEEE
15 years 4 months ago
Discriminatively Trained Particle Filters for Complex Multi-Object Tracking
This work presents a discriminative training method for particle filters in the context of multi-object tracking. We are motivated by the difficulty of hand-tuning the many mode...
Alan Fern, Robin Hess
CVPR
2008
IEEE
14 years 11 months ago
Visual tracking via incremental Log-Euclidean Riemannian subspace learning
Recently, a novel Log-Euclidean Riemannian metric [28] is proposed for statistics on symmetric positive definite (SPD) matrices. Under this metric, distances and Riemannian means ...
Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang, ...
CVPR
2012
IEEE
11 years 11 months ago
Learning hierarchical similarity metrics
Categories in multi-class data are often part of an underlying semantic taxonomy. Recent work in object classification has found interesting ways to use this taxonomy structure t...
Nakul Verma, Dhruv Mahajan, Sundararajan Sellamani...
IJCV
2002
133views more  IJCV 2002»
13 years 8 months ago
Probabilistic Tracking with Exemplars in a Metric Space
Abstract. A new, exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especia...
Kentaro Toyama, Andrew Blake