Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...
As technology advances we encounter more available data on moving objects, which can be mined to our benefit. In order to efficiently mine this large amount of data we propose an ...
In this paper, we present a distributed multicamera face tracking system suitable for large wired camera networks. Unlike previous multicamera face tracking systems, our system doe...
Josiah Yoder, Henry Medeiros, Johnny Park, Avinash...
This paper presents an approach to unsupervised segmentation of moving and static objects occurring in a video. Objects are, in general, spatially cohesive and characterized by lo...
We propose a novel method for temporally and spatially corresponding moving objects by automatically learning the relevance of the objects' appearance features to the task of...
Mahesh Saptharishi, John B. Hampshire II, Pradeep ...