Visual tracking of bare fingers allows more direct manipulation of digital objects, multiple simultaneous users interacting with their two hands, and permits the interaction on l...
Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been u...
Abstract: One of the basic tasks of automotive collision avoidance and collision mitigation systems is the robust and reliable detection of objects as well as the prediction of fut...
Norman Mattern, Robin Schubert, Christian Adam, Ge...
This paper presents an integrated framework for interactive content-based retrieval in video databases by means of visual queries. The proposed system incorporates algorithms for ...
Anastasios D. Doulamis, Yannis S. Avrithis, Nikola...
In a known environment, objects may be tracked in multiple views using a set of background models. Stereo-based models can be illumination-invariant, but often have undefined valu...
Trevor Darrell, David Demirdjian, Neal Checka, Ped...