The recognition of text in everyday scenes is made difficult by viewing conditions, unusual fonts, and lack of linguistic context. Most methods integrate a priori appearance info...
David Smith, Jacqueline Feild, Eric Learned-Miller
We describe a framework for robot navigation that exploits the continuity of image sequences. Tracked visual features both guide the robot and provide predictive information about...
We consider the problem of estimating 3-d structure from a single still image of an outdoor urban scene. Our goal is to efficiently create 3-d models which are visually pleasant. W...
Olga Barinova, Vadim Konushin, Anton Yakubenko, Ke...
Learning typical motion patterns or activities from videos of crowded scenes is an important visual surveillance problem. To detect typical motion patterns in crowded scenarios, w...
We derive a family of kernels on dynamical systems by applying the Binet-Cauchy theorem to trajectories of states. Our derivation provides a unifying framework for all kernels on d...
S. V. N. Vishwanathan, Alexander J. Smola, Ren&eac...