While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle pe...
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 ...