The extrinsic camera parameters from video stream images can be accurately estimated by tracking features through the image sequence and using these features to compute parameter ...
This paper presents a robust and efficient skeleton-based graph matching method for object recognition and recovery applications. The novel feature is to unify both object recogni...
In order for an autonomous agent to behave robustly in a variety of environments, it must have the ability to learn approximations to many different functions. The function approx...
We describe a new dynamic level-of-detail (LOD) technique that allows real-time rendering of large tetrahedral meshes. Unlike approaches that require hierarchies of tetrahedra, ou...
Existing retrieval models generally do not offer any guarantee for optimal retrieval performance. Indeed, it is even difficult, if not impossible, to predict a model’s empirica...