We propose a novel tracking framework called visual tracker sampler that tracks a target robustly by searching for the appropriate trackers in each frame. Since the real-world trac...
We study the challenging problem of maneuvering object tracking with unknown dynamics, i.e., forces or torque. We investigate the underlying causes of object kinematics, and propo...
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
In this paper we propose a cascaded hierarchical framework for object detection and tracking. We claim that, by integrating both detection and tracking into a unified framework, t...
In this work we propose an approach to combine audio and video modalities for person tracking using graphical models. We demonstrate a principled and intuitive framework for combi...
Akash Kushal, Mandar Rahurkar, Fei-Fei Li 0002, Je...