—Salient areas in natural scenes are generally regarded as areas which the human eye will typically focus on, and finding these areas is the key step in object detection. In com...
We propose a compressed domain video object segmentation method for MPEG or MPEG-like encoded videos. Computational superiority is the main advantage of the compressed domain proc...
Fatih Murat Porikli, Faisal I. Bashir, Huifang Sun
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
Multiresolution video denoising is becoming an increasingly popular research topic over recent years. Although several wavelet based algorithms reportedly outperform classical sing...
Mihajlo Katona, Aleksandra Pizurica, Nikola Teslic...
Segmentation of video foreground objects from background has many important applications, such as human computer interaction, video compression, multimedia content editing and man...