In recent years, digital images and videos have become increasingly popular over the internet and bring great social impact to a wide audience. In the meanwhile, technology advanc...
Several spatiotemporal feature point detectors have been recently used in video analysis for action recognition. Feature points are detected using a number of measures, namely sali...
Konstantinos Rapantzikos, Stefanos D. Kollias, Yan...
In this work, we address the problem of building recognition across two camera views with large changes in scales and viewpoints. The main idea is to construct a semantically rich...
Conventional Difference of Gaussian (DOG) filter is usually used to model the early stage of visual processing. However, convolution operation used with DOG does not explicitly a...
Consecutive corrupted MBs or slice errors are commonly seen in modern video transmission systems. Temporal error concealment is an effective approach to reduce the impact of error...
Hai Gao, Jo Yew Tham, Wei Siong Lee, Kwong Huang G...