This paper proposes variance component estimation (VCE) for empirical quality evaluation in computer vision. An outline is given for the scope of VCE in the context of quality eval...
We present a computational framework capable of labeling the effort of an action corresponding to the perceived level of exertion by the performer (low ? high). The approach initi...
We introduce an online learning approach for multitarget tracking. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike ...
Activity recognition in video is dominated by low- and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. Inspired by the...
Video understanding has been an active area of research, where many articles have been published on how to detect and track objects in videos, and how to analyze their trajectorie...