Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
Local appearance models in the neighborhood of salient image features, together with local and/or global geometric constraints, serve as the basis for several recent and effective...
We propose an approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL). Images collected in those cluttered sce...
In an 2D echocardiogram exam, an ultrasound probe
samples the heart with 2D slices. Changing the orientation
and position on the probe changes the slice viewpoint, altering
the ...
Ritwik Kumar, Fei Wang, David Beymer, Tanveer Fath...
This paper proposes a framework of scalable motion estimation and coding with the structure of multi-layers for 3D wavelet video coding. The motion representation consists of mult...