Autonomous systems which learn and utilize a limited
visual vocabulary have wide spread applications.
Enabling such systems to segment a set of cluttered scenes
into objects is ...
Chandra Kambhamettu, Dimitris N. Metaxas, Gowri So...
The visual surveillance task is to monitor the activity of objects in a scene. In far-field settings (i.e., wide outdoor areas), the majority of visible activities are objects movi...
We present a new method for automatically filling in gaps of textural sounds. Our approach is to transform the signal to the time-frequency space, fill in the gap, and apply the i...
Semantic scene classification based only on low-level vision cues has had limited success on unconstrained image sets. On the other hand, camera metadata related to capture condit...
Color appearance of an object is significantly influenced by the color of the illumination. When the illumination color changes, the color appearance of the object will change acc...