Journal of Eye Movement Research最新文献

This study investigates public perception and acceptance of AI-generated art using an integrated system that merges eye-tracking methodologies with advanced bidirectional encoder representations from transformers (BERT)-based sentiment analysis. Eye-tracking methods systematically document the visual trajectories and fixation spots of consumers viewing AI-generated artworks, elucidating the inherent relationship between visual activity and perception. Thereafter, the BERT-based sentiment analysis algorithm extracts emotional responses and aesthetic assessments from numerous internet reviews, offering a robust instrument for evaluating public approval and aesthetic perception. The findings indicate that consumer perception of AI-generated art is markedly affected by visual attention behavior, whereas sentiment analysis uncovers substantial disparities in aesthetic assessments. This paper introduces enhancements to the BERT model via domain-specific pre-training and hyperparameter optimization utilizing deep Gaussian processes and dynamic Bayesian optimization, resulting in substantial increases in classification accuracy and resilience. This study thoroughly examines the underlying mechanisms of public perception and assessment of AI-generated art, assesses the potential of these techniques for practical application in art creation and evaluation, and offers a novel perspective and scientific foundation for future research and application of AI art.

This document contains all abstracts of the 22th European Conference on Eye Movements, August 25-29, 2024, in Maynooth, Irland.

Leading lines, a fundamental composition technique in photography, are crucial to guiding the viewer's visual attention. Leading line composition is an effective visual strategy for influencing viewers' cognitive processes. However, in-depth research on the impact of leading line composition on cognitive psychology is lacking. This study investigated the cognitive effects of leading line composition on perception and behavior. The eye movement behaviors of 34 participants while they viewed photographic works with leading lines were monitored through eye-tracking experiments. Additionally, subjective assessments were conducted to collect the participants' perceptions of the images in terms of aesthetics, complexity, and directional sense. The results revealed that leading lines significantly influenced the participants' attention to key elements of the work, particularly when prominent subject elements were present. This led to greater engagement, longer viewing times, and enhanced ratings on aesthetics and directional sense. These findings suggest that skilled photographers can employ leading lines to guide the viewer's gaze and create visually compelling and aesthetically pleasing works. This research offers specific compositional strategies for photography applications and underscores the importance of leading lines and subject elements in enhancing visual impact and artistic expression.

This study aims to explore the distribution of visual attention on sustainability graphics when viewing an eco-friendly product and the recall of sustainability information afterward. Twenty-five students majoring in environmental studies and twenty-five students from non-environmental majors participated in the study. They were further divided into a higher group and a lower group based on their sustainability level. Participants viewed diagrams of an eco-trash boat design with sustainability graphics and a 15-page design description. Their eye-movement data and verbal reports on the recall of sustainability information were collected. Higher sustainability group had higher fixation count in sustainability graphics. Non-environmental majors had a shorter time to first fixation to sustainability graphics, and there was an interaction effect. Environmental students detected graphics faster in the lower group, but the opposite occurred in the higher group. Higher-sustainability non-environmental students were quicker, while the reverse was true for environmental students. In terms of recalling sustainability graphics, the higher group scored higher, while environmental majors scored higher in recalling sustainability features. In the recall coding, the most frequently mentioned terms were "green," "plant," "vivid," and "eco." The study offers new insights into sustainable development and provides design recommendations for eco-product designers.

Digital picture-book (DPB) with animated elements can enhance children's engagement, but irrelevant animations may interfere with their comprehension. To determine the effect of the relevance of animated elements on preschoolers' comprehension, an experimental study was conducted. Thirtythree preschoolers between the aged 4-5 years engaged with DPB in three conditions: high- and lowrelevant animations and a static control while listening to the story; their eye movements were recorded simultaneously. The study found that preschoolers had lower comprehension when exposed to low-relevant animation, but had comparable scores to the static condition with high-relevant animation. The results of eye-movement analysis showed that children who focused less on highrelevant or more on low-relevant elements had poorer comprehension. Those exposed to low-relevant animations looked less at high-relevant elements and more at low-relevant elements than those in the static and high-relevant conditions. These results suggested that low-relevant animations in DPB interfered with children's comprehension by directing their visual attention away from crucial, highrelevant elements and more to less relevant elements. Therefore, designers creating DPBs, as well as parents and caregivers selecting DPBs for children, should consider the importance of the relevance of animated elements. And the corresponding mechanism of animation effect in DPB comprehension was discussed.

Purpose: Working on computers for long hours has become a regular task for millions of people around the world. This has led to the increase of eye and vision issues related to prolonged computer use, known as computer vision syndrome (CVS). A main contributor to CVS caused by dry eyes is the reduction of blinking rates. In this pilot study, an intelligent, standalone eye blinking monitoring system to promote healthier blinking behaviors for computer users was developed using components that are affordable and easily available in the market. Methods: The developed eye blinking monitoring system used a camera to track blinking rates and operated audible, visual and tactile alarm modes to induce blinks. The hypothesis in this study is that the developed eye blinking monitoring system would increase eye blinks for a computer user. To test this hypothesis, the developed system was evaluated on 20 subjects. Results: The eye blinking monitoring system detected blinks with high accuracy (95.9%). The observed spontaneous eye blinking rate was 43.1 ± 14.7 blinks/min (mean ± standard deviation). Eye blinking rates significantly decreased when the subjects were watching movie trailers (25.2 ± 11.9 blinks/min; Wilcoxon signed rank test; p<0.001) and reading articles (24.2 ± 12.1 blinks/min; p<0.001) on a computer. The blinking monitoring system with the alarm function turned on showed an increase in blinking rates (28.2 ± 12.1 blinks/min) compared to blinking rates without the alarm function (25.2 ± 11.9 blinks/min; p=0.09; Cohen's effect size d=0.25) when the subjects were watching movie trailers. Conclusions: The developed blinking monitoring system was able to detect blinking with high accuracy and induce blinking with a personalized alarm function. Further work is needed to refine the study design and evaluate the clinical impact of the system. This work is an advancement towards the development of a profound technological solution for preventing CVS.

Eye movement detection algorithms (e.g., I-VT) require the selection of thresholds to identify eye fixations and saccadic movements from gaze data. The choice of threshold is important, as thresholds too low or large may fail to accurately identify eye fixations and saccades. An inaccurate threshold might also affect the resulting visual scan path, the time-ordered sequence of eye fixations and saccades, carried out by the participant. Commonly used approaches to evaluate threshold accuracy can be manually laborious, or require information about the expected visual scan paths of participants, which might not be available. To address this issue, we propose two different computational approaches, labeled as "between-participants comparisons" and "within-participants comparisons." The approaches were evaluated using the open-source Gazebase dataset, which contained a bullseyetarget tracking task, where participants were instructed to follow the movements of a bullseye-target. The predetermined path of the bullseye-target enabled us to evaluate our proposed approaches against the expected visual scan path. The approaches identified threshold values (220°/s and 210°/s) that were 83% similar to the expected visual scan path, outperforming a 30°/s benchmark threshold (41.5%). These methods might assist researchers in identifying accurate threshold values for the IVT algorithm or potentially other eye movement detection algorithms.

The theory of expertise suggests that there should be observable differences in the eye movement patterns between experts and non-experts. Previous studies have investigated how expertise influences eye movement patterns during cognitive tasks like reading. However, the impact of expertise on eye movements in comics, a multimodal form of text, remains unexplored. This article reports on a study that uses eye tracking to examine patterns in the ways that experts and non-experts read comics. Expert participants (14) with experience in reading comics than non-expert participants (17). When controlling for variables such as layout and text quantity, we found significant differences in visual scanning between experts and non-experts. Experts exhibited more frequent saccades and greater amplitude of saccades. Further analysis revealed distinct strategies in processing text and image content between the two groups: the interaction between expertise level and content type in specific AOI showed significant differences across multiple visual measurement metrics, including Average duration of fixations, number of fixations, and number of saccades within AOI. These findings not only support the applicability of the expertise level theory in the field of comic reading but also provide a new perspective for understanding the reading processing of multimodal texts.

This study employs subjective evaluation and eye movement experiments to explore the application and conveyance of logo graphics design, which conforms to the Gestalt principle of closure, to understand the psychological process of this principle in the perception of a logo. The study found that there is no significant difference between completely enclosed logos and unenclosed ones that conform to the principle of closure in their influence on sightline behavior due to the effects of closure, but the subjective evaluation favors unenclosed logos as more attractive and comfortable to perceive, which agrees with modern logo design trends. In addition, the sightline distribution of the image-type logos is more scattered and has the most extended fixation duration. In contrast, the sightline distribution of text-type logos is more concentrated. Designers who understand the principle of closure can intentionally incorporate imperfection into logo design, triggering the automatic mental filling of gaps and instilling new meaning and visual effect into a design.

The evaluation of design results plays a crucial role in the development of design. This study presents a design work evaluation system for design education that assists design instructors in conducting objective evaluations. An automatic design evaluation model based on convolutional neural networks has been established, which enables intelligent evaluation of student design works. During the evaluation process, the CAM is obtained. Simultaneously, an eye-tracking experiment was designed to collect gaze data and generate eye-tracking heat maps. By comparing the heat maps with CAM, an attempt was made to explore the correlation between the focus of the evaluation's attention on human design evaluation and the CNN intelligent evaluation. The experimental results indicate that there is some certain correlation between humans and CNN in terms of the key points they focus on when conducting an evaluation. However, there are significant differences in background observation. The research results demonstrate that the intelligent evaluation model of CNN can automatically evaluate product design works and effectively classify and predict design product images. The comparison shows a correlation between artificial intelligence and the subjective evaluation of human eyes in evaluation strategy. Introducing artificial intelligence into the field of design evaluation for education has a strong potential to promote the development of design education.