In this paper, we present a scene detection framework on continuously recorded videos. Conventional temporal scene segmentation methods work for the videos composed of discrete sh...
Abstract— The ability to tag resources with uncontrolled metadata or “folksonomies” is often characterized as one of the central features of “Web 2.0” applications. Folks...
In this paper, we report on an empirical exploration of digital ink and speech usage in lecture presentation. We studied the video archives of five Master’s level Computer Scien...
Richard J. Anderson, Crystal Hoyer, Craig Prince, ...
We present a novel method to transfer speech animation recorded in low resolution videos onto realistic 3D facial models. Unsupervised learning is utilized on a speech video corpus...
We present the design, implementation, and initial results of a system for remote lecture attendance based on extending on-campus classrooms to accommodate remotely located studen...
Radu Dondera, Chun Jia, Voicu Popescu, Cristina Ni...