To realize context aware applications for smart home environments, it is necessary to recognize function or usage of objects as well as categories of them. On conventional researc...
In order to summarize a video consisting of a sequence of different activities, there are three fundamental problems: tracking the objects of interest, detecting the activity chan...
Recently proposed novel interaction techniques such as cursor jumping [1] and target expansion for tiled arrangements [13] are predicated on an ability to effectively estimate the...
We introduce Topobo, a 3D constructive assembly system embedded with kinetic memory, the ability to record and playback physical motion. Unique among modeling systems is Topoboʼs...
A dynamic texture is a spatio-temporal generative model for video, which represents video sequences as observations from a linear dynamical system. This work introduces the mixtur...