—We present a generative model and inference algorithm for 3D nonrigid object tracking. The model, which we call G-flow, enables the joint inference of 3D position, orientation, ...
An adaptive spatiotemporal saliency algorithm for video attention detection using motion vector decision is proposed, motivated by the importance of motion information in video se...
Yaping Zhu, Natan Jacobson, Hong Pan, Truong Q. Ng...
We propose a time-scale decomposition approach to measurement-based admission control (MBAC). We identify a critical time scale such that: 1) aggregate traffic fluctuation slower t...
Motion segmentation is a classic and on-going research topic which is an important pre-stage for many video processes. The reliability of the motion field calculation directly dete...
-We solve the problem of time-optimal network queue control: what are the input data rates that make network queue sizes converge to their ideal size in the least possible time aft...