Scale invariant feature detectors often find stable scales in only a few image pixels. Consequently, methods for feature matching typically choose one of two extreme options: mat...
not abstract asymmetry: different sides looks different clumps different from "data objects" need grid structure, alignment [Design Guidelines for Landmarks to Support Na...
Jock D. Mackinlay, Stuart K. Card, George G. Rober...
We study the problem of object classification when training
and test classes are disjoint, i.e. no training examples of
the target classes are available. This setup has hardly be...
Christoph H. Lampert, Hannes Nickisch, Stefan Harm...
Recently, we proposed marginal space learning (MSL) as
a generic approach for automatic detection of 3D anatom-
ical structures in many medical imaging modalities. To
accurately...
Several spatiotemporal feature point detectors have been recently used in video analysis for action recognition. Feature points are detected using a number of measures, namely sali...
Konstantinos Rapantzikos, Stefanos D. Kollias, Yan...