arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2208.09666cs.CV
收藏

图像审美主体性的建模、量化与预测

Modeling, Quantifying, and Predicting Subjectivity of Image Aesthetics

Yonsei University(延世大学);Seoul National University of Science and Technology(首尔科技大学)

Hyeongnam Jang, Yeejin Lee, Jong-Seok Lee

摘要:

图像美学评价是一项具有挑战性的计算机视觉任务。一个原因是审美偏好是高度主观的,并且对于某些图像,人们之间可能会有很大差异。因此,适当地对这种\textit{subjectivity}进行建模和量化是重要的,但是还没有太多的努力来解决这个问题。在本文中,我们提出了一个新的统一的概率框架,可以建模和量化的主观审美偏好的基础上的主观逻辑。在这个框架中,评级分布被建模为beta分布,从该分布中可以获得肯定令人满意、肯定令人不满意和不确定的概率。我们使用不确定性的概率来定义主观性的直观度量。此外,我们提出了一种学习深度神经网络的方法,用于预测图像美学,通过实验表明,该方法可以有效地提高主观性预测的性能。我们还提出了一个应用场景中的框架是有益的美学为基础的图像推荐。

英文摘要:

Assessing image aesthetics is a challenging computer vision task. One reason is that aesthetic preference is highly subjective and may vary significantly among people for certain images. Thus, it is important to properly model and quantify such \textit{subjectivity}, but there has not been much effort to resolve this issue. In this paper, we propose a novel unified probabilistic framework that can model and quantify subjective aesthetic preference based on the subjective logic. In this framework, the rating distribution is modeled as a beta distribution, from which the probabilities of being definitely pleasing, being definitely unpleasing, and being uncertain can be obtained. We use the probability of being uncertain to define an intuitive metric of subjectivity. Furthermore, we present a method to learn deep neural networks for prediction of image aesthetics, which is shown to be effective in improving the performance of subjectivity prediction via experiments. We also present an application scenario where the framework is beneficial for aesthetics-based image recommendation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑