Abstract. A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighborhood. However, the differences ...
We propose a model of the hippocampus aimed at learning the timed association between subsequent sensory events. The properties of the neural network allow it to learn and predict ...
This paper presents our ongoing research on view synthesis of free-viewpoint 3D multi-view video for 3DTV. With the emerging breakthrough of stereoscopic 3DTV, we have extended a ...
We propose low-rank representation (LRR) to segment data drawn from a union of multiple linear (or affine) subspaces. Given a set of data vectors, LRR seeks the lowestrank represe...
This two-day workshop brings together the interdisciplinary community of scholars and practitioners involved in the design of interactive systems and sharing a common interest in ...