In the arts and sciences, as well as in our daily lives, symmetry has made a profound and
lasting impact. Likewise, a computational treatment of symmetry and group theory (the …

In this paper, we show that tracking different kinds of interacting objects can be formulated
as a network-flow mixed integer program. This is made possible by tracking all objects …

Crowd video analysis has applications in crowd management, public space design, and
visual surveillance. Example tasks potentially aided by automated analysis include anomaly …

Minimum-cost flow algorithms have recently achieved state-of-the-art results in multi-object
tracking. However, they rely on the whole image sequence as input. When deployed in real …

Tracking objects like a basketball from a monocular view is challenging due to its small size,
potential to move at high velocities as well as the high frequency of occlusion. However …

We propose a novel, self-validating approach for detecting curved reflection symmetry
patterns from real, unsegmented images. Our method benefits from the observation that any …

We present a novel method for translational symmetry detection, optimization, and symmetry
object segmentation in façade images. Unlike most previous methods, our detection …

Kernel-based method has been proved to be effective in solving single-target tracking
problem. However, facing more complicated multitarget tracking task, most classic kernel …

We propose a visual tracking method for dense fish schools in which occlusions occur
frequently. Although much progress has been made for tracking multiple objects in video …

We propose a measurement method for the mean speed distribution of collective motions of
highly dense groups with optical flow based on our previous work. This measurement is …