Visual Attention Modeling in Compressed Domain: From Image Saliency Detection to Video Saliency Detection

Visual Attention Modeling in Compressed Domain: From Image Saliency Detection to Video Saliency Detection

FANG Yuming and ZHANG Xiaoqiang

(Jiangxi University of Finance and Economics, Nanchang, Jiangxi 330032, China)

Abstract: Saliency detection models, which are used to extract salient regions in visual scenes, are widely used in various multimedia processing applications. It has attracted much attention in the area of computer vision over the past decades. Since most images or videos over the Internet are stored in compressed domains such as images in JPEG format and videos in MPEG2 format, H.264 format, and MPEG4 Visual format, many saliency detection models have been proposed in compressed domain recently. We provide a review of our works on saliency detection models in compressed domain in this paper. Besides, we introduce some commonly used fusion strategies to combine spatial saliency map and temporal saliency map to compute the final video saliency map.

Keywords: saliency detection; computer vision; compressed domain; visual attention; fusion strategy