This paper addresses the problem of video anomaly recovery from a sequence of spectrally compressed video frames. Analysis of anomalies occurring in both time and spectrum is impo...
We introduce a stochastic model to characterize the online computational process of an object recognition system based on a hierarchy of classifiers. The model is a graphical netwo...
The Structural SIMilarity Measure (SSIM) combined with the sequential Monte Carlo approach has been shown [1] to achieve more reliable video object tracking performance, compared ...
Artur Loza, Fanglin Wang, Jie Yang, Lyudmila Mihay...
We present metrics to evaluate the performance of video object segmentation and tracking methods quantitatively when groundtruth segmentation maps are not available. The proposed ...
This paper studies the feasibility and investigates various choices in the application of compressive sensing (CS) to object-based surveillance video coding. The residual object e...