We propose the use of 3D (2D+time) Shape Context to recognize the spatial and temporal details inherent in human actions. We represent an action in a video sequence by a 3D point ...
Franziska Meier, Irfan A. Essa, Matthias Grundmann
Recent research has exploited the multi-homing property (one terminal with multiple network interfaces) of modern devices to improve communication performance in wireless networks...
This paper addresses the problem of video anomaly recovery from a sequence of spectrally compressed video frames. Analysis of anomalies occurring in both time and spectrum is impo...
This paper presents a complete framework for attention-based video streaming for low bandwidth networks. First, motivated by the fovea-periphery distinction of biological vision s...
In [1], Adaptive Prediction Error Coding (APEC) in spatial and frequency domain is proposed and significantly improves the coding efficiency of video coders. However, this approac...