In this paper, we propose a novel predictive model for
object boundary, which can integrate information from any
sources. The model is a dynamic “object” model whose
manifes...
Tian Shen (Lehigh University), Hongsheng Li (Lehig...
In this paper, we propose techniques to make use of two complementary bottom-up features, image edges and texture patches, to guide top-down object segmentation towards higher pre...
Thomas Brox, Lubomir Bourdev, Subhransu Maji, Jite...
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
We present a region based active contour model which does not require any initialisation and is capable of modelling multi-modal image regions. Its external force is based on stat...