— A novel framework to context modeling, based on the probability of co-occurrence of objects and scenes is proposed. The modeling is quite simple, and builds upon the availabili...
In developing automated systems to recognize the emotional content of music, we are faced with a problem spanning two disparate domains: the space of human emotions and the acoust...
Erik M. Schmidt, Douglas Turnbull, Youngmoo E. Kim
Current content-based video copy detection approaches mostly concentrate on the visual cues and neglect the audio information. In this paper, we attempt to tackle the video copy d...
Yang Liu, Wanlei Zhao, Chong-Wah Ngo, Changsheng X...
It’s common experience for human vision to perceive full 3D shape and scene from a single 2D image with the occluded parts “filled-in” by prior visual knowledge. In this pa...
Advances in digital technology for the graphic and textual representation of manuscripts have not, until recently, been applied to the worldʼs oldest manuscripts, cuneiform table...
Jonathan D. Cohen, Donald Duncan, Dean Snyder, Jer...