In this work we construct scale invariant descriptors (SIDs) without requiring the estimation of image scale; we thereby avoid scale selection which is often unreliable. Our start...
The required amount of labeled training data for object detection and classification is a major drawback of current methods. Combining labeled and unlabeled data via semisupervise...
The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
This paper proposes a technique for estimating piecewise planar models of objects from their images and geometric constraints. First, assuming a bounded noise in the localization ...
We propose a novel global pose estimation method to detect body parts of articulated objects in images based on non-tree graph models. There are two kinds of edges defined in the ...