This paper proposes a novel saliency detection method by combining region-level saliency estimation and pixel-level saliency prediction with CNNs (denoted as CRPSD). For pixel-level saliency prediction, a fully convolutional neural network (called pixel-level CNN) is constructed by modifying the VGGNet architecture to perform multiscale feature learning, based on which an image-to-image predict...

Saliency map detection, as a method for detecting important regions of an image, is used in many applications such as image classification and recognition. We propose that context detection could have an essential role in image saliency detection. This requires extraction of high level features. In this paper a saliency map is proposed, based on image context detection using semantic segmentati...

An efficient modified video compression HEVC technique based on high quality assessment saliency features presented for the assessment of high quality videos. To create an efficient saliency map we extract global temporal alignment component and robust spatial components. To obtain high quality saliency here, we combine spatial saliency features and temporal saliency features together for diffe...

We describe a general framework for the acquisition of perception-based navigational behaviors in autonomous mobile robots. A self-organizing sparse distributed memory equivalent to a three-layered neural network is used to learn the desired transfer function mapping sensory input into motor commands. The memory is initially trained by teleoperating the robot on a small number of paths within a...

Perceptual learning is associated with experience-based changes in stimulus salience. Here, we use a novel procedure to show that learning a new association between a self-label and a neutral stimulus produces fast alterations in social salience measured by interference when targets associated with other people have to be selected in the presence of self-associated distractors. Participants ass...

In contrast to the wealth of saliency models in the vision literature, there is a relative paucity of models exploring auditory saliency. In this work, we integrate the approaches of (Kayser, Petkov, Lippert, & Logothetis, 2005) and (Zhang, Tong, Marks, Shan, & Cottrell, 2008) and propose a model of auditory saliency. The model combines the statistics of natural soundscapes and the recent past ...

In this paper, we introduce a biologically-motivated model to detect image saliency. The model employs an isophote based operator to detect potential structure and global saliency information related to each pixel, which are then combined with integral image to build up final saliency maps. We show that the proposed model outperforms seven state-of-the-art saliency detectors in experimental stu...

of Dissertation Presented to the Graduate School of the University of Florida in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy CONTENT-AWARE APPROACHES FOR DIGITAL VIDEO ADAPTATION, SUMMARIZATION AND COMPRESSION By Taoran Lu December 2010 Chair: Dapeng Oliver Wu Major: Electrical and Computer Engineering In this dissertation, we mainly present our work on three ...

Humans and many other species sense visual information with varying spatial resolution across the visual field (foveated vision) and deploy eye movements to actively sample regions of interests in scenes. The advantage of such varying resolution architecture is a reduced computational, hence metabolic cost. But what are the performance costs of such processing strategy relative to a scheme that...