用深度学习提升新闻界面注意力预测，发现年龄影响用户看图还是看文。
A Deep Learning Framework for Visual Attention Prediction and Analysis of News Interfaces
- 融合DeepGaze IIE优化萨利耶映射与网格评分，提升关键内容排序准确率10.7%
- 30人眼动+375人鼠标追踪显示：36岁以上更关注文字，13-35岁更关注图像
- 鼠标轨迹可替代眼动实验，适用于大规模人群研究，适合界面设计参考
新闻平台争夺用户注意力，推动了面向人口统计特征的显著性预测模型需求。尽管用户界面显著性检测已有进展，但现有数据集规模小且人口构成不均衡。本文提出一种深度学习框架，通过引入DeepGaze IIE增强SaRa（Saliency Ranking）模型，在显著对象排序（SOR）任务上性能提升10.7%。该框架优化了三个核心模块：显著性图生成、网格区域评分和图归一化。基于眼动追踪（30名参与者）和鼠标追踪（375名13–70岁参与者）的双实验，分析不同人群注意力模式。统计检验显示显著年龄差异（p < 0.05, {ε^2} = 0.042），36–70岁用户更关注文本内容，13–35岁用户更关注图像。鼠标追踪数据与眼动行为高度一致（sAUC = 0.86），能有效识别界面中立即吸引注意的元素，验证其在大规模研究中的适用性。结论指出，显著性研究应扩大样本规模，确保人口结构代表性，并明确报告具体分布情况。
原文摘要 · Abstract (English)
News outlets' competition for attention in news interfaces has highlighted the need for demographically-aware saliency prediction models. Despite recent advancements in saliency detection applied to user interfaces (UI), existing datasets are limited in size and demographic representation. We present a deep learning framework that enhances the SaRa (Saliency Ranking) model with DeepGaze IIE, improving Salient Object Ranking (SOR) performance by 10.7%. Our framework optimizes three key components: saliency map generation, grid segment scoring, and map normalization. Through a two-fold experiment using eye-tracking (30 participants) and mouse-tracking (375 participants aged 13--70), we analyze attention patterns across demographic groups. Statistical analysis reveals significant age-based variations (p < 0.05, {ε^2} = 0.042), with older users (36--70) engaging more with textual content and younger users (13--35) interacting more with images. Mouse-tracking data closely approximates eye-tracking behavior (sAUC = 0.86) and identifies UI elements that immediately stand out, validating its use in large-scale studies. We conclude that saliency studies should prioritize gathering data from a larger, demographically representative sample and report exact demographic distributions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。