This is the authors' abstract. We don't add key points for this paper.
modeling. The below is an overview and discussion of the accepted papers. 1. Neuroscience studies of human perception, especially those related to quality perception In recent years, a large amount of perceptual quality assessment studies has taken human perception properties into consideration, since human is usually the ultimate judger of signal quality. To study the intrinsic neuroscience working mechanism of human perception, subjective neuroscience and perceptual studies are usually necessary.The influence of audio on perceptual QoE has been studied and verified by some previous studies [4][5][6][7][8]. In this research topic, Sun et al. (Listening Effort Informed Quality of Experience Evaluation) give an overview for the audiology and cognitive science researches which study how cognitive processes influence the quality of listening experience. Moreover, they also propose to introduce these mechanisms from audiology and cognitive science into the current QoE ) study the influence of the refresh rate of a display on the motion perception response. Moreover, they introduce an objective visual electrophysiological assessment model to better select the display parameters.Full understanding of the intrinsic neuroscience working mechanism of human perception is difficult in the current stage, however it is worthwhile to study and take inspiration from neuroscience and utilize these properties for computational modelling of perceptual quality.Over the last two decades, many perceptual quality assessment models have been proposed [1][2][3][9][10][11], and many of them have taken inspirations from neuroscience. Song et al. (IE-IQA: Intelligibility Enriched Generalizable No-Reference Image Quality Assessment) introduce a blind quality assessment model for authentically distorted images by considering both distortion degree and intelligibility. Specifically, they analyze the relation between intelligibility and image quality, and then incorporate such intelligibility into a highly generalizable image quality prediction model. Feng et al. (Cross-Domain Feature Similarity Guided Blind Image Quality Assessment) introduce an end-to-end cross-domain feature similarity guided deep neural network for perceptual quality assessment. This model is built based on the observation that features for the object recognition task and features for the quality prediction task are highly correlated in terms of characteristics of the human visual system. Experimental results have verified the effectiveness of the proposed model.Recently, a growing number of emerging and advanced multimedia technologies or systems have invaded into our daily lives, for example light field, virtual reality, etc. Such emerging multimedia applications also call for new quality perception models, since traditional quality perception models are not good at such contents. In We hope that readers find this research topic useful, timely and informative, in addressing the important topics in computational neuroscience for perceptual quality assessment.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Min et al. (2022) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: