“Ghosts” arise in traditional background subtraction when an object starts to move, causing the exposed background to be labelled as a ghost foreground. With background model ...
Abstract. In this paper, we describe an unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from longterm observations of mo...
This paper presents a novel integrated background model for video surveillance. Our model uses a primal sketch representation for image appearance and 3D scene geometry to capture...
Wenze Hu, Haifeng Gong, Song Chun Zhu, Yongtian Wa...
Abstract. We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it...
This paper presents an energy-based approach that models the distinct wrinkle shapes to represent the different material properties of non-rigid objects at an interactive speed. O...
Yu Wang 0010, Charlie C. L. Wang, Matthew Ming-Fai...