In order to be useful, XAI explanations have faithful the AI system they seek elucidate and also interpretable people that engage with them. There exist multiple algorithmic methods for assessing faithfulness, but this is not so interpretability, which typically only assessed through expensive user studies. Here we propose two complementary metrics algorithmically evaluate interpretability of s...

An AUX information assisted HEVC is described in this paper. This new functionality provides a tool for HEVC to determine the quantization parameter of CU based on auxiliary input. In this report, a saliency based auxiliary input is employed as a proof-of-concept. As shown in our subjective tests, the new tool achieves up to 12% bit rate reduction with negligible perceptual quality loss.

In many collocated human-robot interaction scenarios, robots are required to accurately and unambiguously indicate an object or point of interest in the environment. Realistic, cluttered environments containing many visually salient targets can present a challenge. In this paper, we describe an experiment and results detailing the effects of visual saliency and pointing modality on human percep...

The neuronal mechanisms underlying perceptual grouping of discrete, similarly oriented elements are not well understood. To investigate this, we measured neural population responses using voltage-sensitive dye imaging in V1 of monkeys trained on a contour-detection task. By mapping the contour and background elements onto V1, we could study their neural processing. Population response early in ...

Contour integration is an important intermediate stage of object recognition, in which line segments belonging to an object boundary are perceptually linked and segmented from complex backgrounds. Contextual influences observed in primary visual cortex (V1) suggest the involvement of V1 in contour integration. Here, we provide direct evidence that, in monkeys performing a contour detection task...

Although gaze can be directed at any location, different locations in the visual environment vary in terms of how likely they are to draw another person’s attention. One could therefore weigh incoming perceptual signals (e.g., eye cues) against this prior knowledge (the relative visual saliency of locations in the scene) in order to infer the true target of another person’s gaze. This Bayesian ...

Like humans and primates, artificial creatures like robots are limited in terms of allocation of their resources to huge sensory and perceptual information. Serial processing mechanisms are believed to have the major role on such limitation. Thus attention control is regarded as the same solution as humans in this regard but of course with different attention control mechanisms than those of pa...

The human vision system can discriminate between the important features in an image (denoted figure) and unnecessary features (denoted background). It also can divide the figure features into groups such that each group represents some image structure, corresponding to some object in the scene. The goal of computerized perceptual organization is to acquire the same ability. The saliency algorit...

We propose an image super resolution(ISR) method using generative adversarial networks (GANs) that takes a low resolution input fundus image and generates a high resolution super resolved (SR) image upto scaling factor of 16. This facilitates more accurate automated image analysis, especially for small or blurred landmarks and pathologies. Local saliency maps, which define each pixel’s importan...

In this paper, we propose an image interpolation algorithm based on the characteristics of the Human Visual System (HVS). Firstly, the saliency map is extracted for the input image by the feature contrast. Based on the saliency detection algorithm, the input image can be divided into salient regions and non-salient regions. A non-local means based interpolation and the bicubic interpolation ope...