We propose a novel tracking algorithm that can work robustly in a challenging scenario such that several kinds of appearance and motion changes of an object occur at the same time....
Junseok Kwon (Seoul National University), Kyoung M...
A central problem in the analysis of motion capture (Mo-
Cap) data is how to decompose motion sequences into primitives.
Ideally, a description in terms of primitives should
fac...
Historically non-rigid shape recovery and articulated pose estimation have evolved as separate fields. Recent methods for non-rigid shape recovery have focused on improving the a...
Conditional Random Field models have proved effective for several low-level computer vision problems. Inference in these models involves solving a combinatorial optimization probl...
This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...