Blind Omnidirectional Image Quality Assessment (BOIQA) aims to objectively assess the human perceptual quality of omnidirectional images (ODIs) without relying on pristine-quality image information. It is becoming more significant with the increasing advancement of virtual reality (VR) technology. However, the quality assessment of ODIs is severely hampered by the fact that the existing BOIQA pipeline lacks the modeling of the observer's browsing process. To tackle this issue, we propose a novel multi-sequence network for BOIQA called Assessor360, which is derived from the realistic multi-assessor ODI quality assessment procedure. Specifically, we propose a generalized Recursive Probability Sampling (RPS) method for the BOIQA task, combining content and details information to generate multiple pseudo viewport sequences from a given starting point.

Extensive experimental results demonstrate that Assessor360 outperforms state-of-the-art methods on multiple OIQA datasets.

Thus, there is a need for a reference point, on which each model canbetested andfrom where potential improvements canbe derived. In this study, we select publicly available state-of-the-art visual search models and datasets in natural scenes, and provide a common framework for their evaluation. To this end, we apply a unified format and criteria, bridging the gaps between them, and we estimate the models' efficiency and similarity with humans using a specific set of metrics.

This mechanism in adults is very sophisticated.

Progress in human behavior modeling involves understanding both implicit, early-stage perceptual behavior, such as human attention, and explicit, later-stage behavior, such as subjective preferences or likes.

We did our best to answer the provided questions and to reply to some comments. " Are the resulting features better able to perform some task of interest? " We considered the problem of MI-based features were helping in case of small/sparse supervision. " The paper introduces fourth order dynamics, and spends considerable time simplifying this to 2nd order dynamics. " The experiments chose hyperparameters to maximize the mutual information extracted by each algorithm, and it is not We selected the parameters that were leading to the largest MI index at the end of the learning stage, Eq. (8), and not on " The evaluation videos could be better motivated. How many loops were necessary [...]" We selected " The authors need to contrast their work with that of Friston and point out the novel contributions In the experiment [...] fixation/attention locations generated by other state-of-the-art video Bruce and Tsotsos attention emerges maximizing the Self-Information of each local image patch. " (Thm 1) and its proof in the supplementary seem correct, but no learning algorithms are given [...] " " Couldn't understand how exactly the trajectory density estimation, on which the mutual information estimation is based, " We compared different choices for the function " What is actiually assumed about the unknown potential U?How is it learned from the data?