When appearance variation of object and its background, partial occlusion or deterioration in object
images occurs, most existing visual tracking methods tend to fail in tracking ...
1 — Sampling is increasingly utilized by passive measurement systems to save the resources consumption. However, the widely adopted static linear sampling selects packets with th...
Reservoir sampling is a well-known technique for random sampling over data streams. In many streaming applications, however, an input stream may be naturally heterogeneous, i.e., c...
Sampling points with blue noise spectral characteristics are best suited for antialiasing. Compared to Poisson disk sampling, Lloyd's relaxation scheme yields samples that ap...
The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...