The varying object appearance and unlabeled data from new frames are always the challenging problem in object tracking. Recently machine learning methods are widely applied to tra...
Traditional dynamical systems used for motion tracking cannot effectively handle high dimensionality of the motion states and composite dynamics. In this paper, to address both is...
We present a fully automatic and weighted dictionary to be used in topical opinion retrieval. We also define a simple topical opinion retrieval function that is free from paramete...
Gianni Amati, Edgardo Ambrosi, Marco Bianchi, Carl...
We present a robust algorithm for point tracking on deformable objects. The key elements are the use of orientation selective rank features (ranklets), local filter adaptation and...
Fabrizio Smeraldi, Alessio Del Bue, Lourdes de Aga...
We present a stochastic tracking algorithm for surveillance video where targets are dim and at low resolution. The algorithm builds motion models for both background and foregroun...