We present a framework that retains ambiguity in feature matching to increase the performance of 3D object recognition systems. Whereas previous systems removed ambiguous correspo...
We present a region-based active contour detection algorithm for objects that exhibit relatively homogeneous photometric characteristics (e.g. smooth color or gray levels), embedd...
Stefano Soatto, Ganesh Sundaramoorthi, Anthony Yez...
Tracking individuals in extremely crowded scenes is a challenging task, primarily due to the motion and appearance variability produced by the large number of people within the sc...
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local...