发表机构
Eastern Switzerland University of Applied Sciences (OST)（东瑞士应用科学大学（OST））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对问题性互联网使用，本文提出基于MobileNetV4和FiLM的实时情感编辑模型，以3.7毫秒前向传播替代80秒迭代优化，在用户研究中有效降低唤醒度并保持高质量，已集成至Android应用实现60fps实时处理。
AI 中文摘要
问题性互联网使用影响的人口比例日益增长，然而常见的干预措施，如时间限制、屏蔽、强制休息，具有强制性且容易被规避。我们探索一种限制性较小的替代方案：调整视觉内容的情感强度。先前的研究表明，优化方法可以引导图像的情感内容，但其逐图像优化的成本使其无法实现实时部署。我们转而学习一个模型，通过单次前向传播预测这种变换：一个基于MobileNetV4骨干网络和FiLM（特征级线性调制）情绪条件化的模型，输出可微分的全局变换参数。这将先前的迭代优化（每张图像80秒）替换为单次3.7毫秒的前向传播。在一项用户研究（N=54）中，与未编辑图像相比，该模型降低了观看者报告的唤醒度，与灰度健康滤镜效果相当，同时在感知质量上获得更高评分。我们将该模型集成到一个Android应用中，可实时适配Instagram视频，在三星Galaxy S23上保持60帧每秒的流畅运行。
英文摘要
Problematic internet use affects a growing share of the population, yet common interventions, e.g., time limits, blocking, forced breaks, are coercive and easily circumvented. We explore a less restrictive alternative: adapting the emotional intensity of visual content. Prior work has shown that optimization can steer an image's affective content, but its per-image optimization cost makes it impractical for real-time deployment. We instead learn a model that predicts this transformation in a single forward pass: a MobileNetV4 backbone with FiLM-based emotion conditioning outputs parameters for differentiable global transformations. This replaces prior iterative optimization (80 s per image) with a single 3.7 ms forward pass. In a user study (N = 54), the model reduced viewer-reported arousal relative to unedited images, comparably to the grayscale well-being filter, while being rated higher in perceived quality. We integrate the model into an Android app that adapts Instagram video in real time, sustaining 60 fps on a Samsung Galaxy S23.
Comments18 pages, 13 figures
