The classical optical flow assumes that a feature point maintains constant brightness across the frames. For fluidtype motions such as smoke or clouds, the constant brightness ass...
We present algorithms for recognizing human motion in monocular video sequences, based on discriminative Conditional Random Field (CRF) and Maximum Entropy Markov Models (MEMM). E...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
We consider the segmentation of a trajectory into piecewise polynomial parts, or possibly other forms. Segmentation is typically formulated as an optimization problem which trades...
Richard Mann, Allan D. Jepson, Thomas F. El-Maragh...
We propose a new dynamic model which can be used within blob trackers to track the target's center of gravity. A strong point of the model is that it is designed to track a va...
Matej Kristan, Stanislav Kovacic, Ales Leonardis, ...
We introduce an online learning approach for multitarget tracking. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike ...