Visual saliency is a cognitive psychology concept that makes some stimuli of a scene stand out relative to their neighbors and attract our attention. Computing visual saliency is a topic of recent interest. Here, we propose a graph-based method for saliency detection, which contains three stages: pre-processing, initial saliency detection and final saliency detection. The initial saliency map i...

Perceptual watermarking should take full advantage of the results from human visual system (HVS) studies. Just noticeable distortion (JND) gives us a way to model the HVS accurately. In this paper, another very important aspect affecting human perception, visual saliency, is introduced to modulate JND model. Based on the visual saliency’s modulatory effect on JND model which incorporates visual...

20 Previous studies comparing eye movements between humans and their closest relatives, 21 chimpanzees, have revealed similarities and differences between the species in terms of 22 where individuals fixate their gaze during free viewing of a naturalistic scene, including 23 social stimuli (e.g. body and face). However, those results were somewhat confounded 24 by the fact that gaze behavior is...

Deep convolutional neural networks have demonstrated high performances for fixation prediction in recent years. How they achieve this, however, is less explored and they remain to be black box models. Here, we attempt to shed light on the internal structure of deep saliency models and study what features they extract for fixation prediction. Specifically, we use a simple yet powerful architectu...

Objectives: We have examined the specificity of face recognition networks in relation to other object recognition modules in normal subjects. In particular, we addressed a current challenge in cognitive neuroscience by using a novel paradigm that allowed for an explicit separation of the neural correlates of the sensory, perceptual and motor components in holistic perceptual decision. This stra...

This paper presents a new method for edge-preserving color image denoising based on the tensor voting framework, a robust perceptual grouping technique used to extract salient information from noisy data. The tensor voting framework is adapted to encode color information through tensors in order to propagate them in a neighborhood by using a specific voting process. This voting process is speci...

This paper proposes a novel technique to expand visual perception in Telexistence systems from a single location to multiple locations. Layered Telepresence (LT) expands perceptual awareness of human modalities by using the concept of layered perception. Telexistence based robots are used as the representation of the user, and are considered as perceptual layers containing the visual, auditory,...

Psychological experiments have revealed that in normal visual perception of humans, color cues are more salient than shape cues, which are more salient than textural patterns. We carried out an artificial language learning experiment to study whether such perceptual saliency hierarchy (color > shape > texture) influences the learning of orders regulating adjectives of involved visual features i...

Visual saliency is the perceptual quality that makes some items in visual scenes stand out from their immediate contexts. Visual saliency plays important roles in natural vision in that saliency can direct eye movements, deploy attention, and facilitate tasks like object detection and scene understanding. A central unsolved issue is: What features should be encoded in the early visual cortex fo...