Images can convey rich semantics and induce various emotions in viewers. Recently, with the rapid advancement of emotional intelligence and the explosive growth of visual data, extensive research efforts have been dedicated to affective image content analysis (AICA). In this survey, we will comprehensively review the development of AICA in the recent two decades, especially focusing on the state-of-the-art methods with respect to three main challenges -- the affective gap, perception subjectivity, and label noise and absence. We begin with an introduction to the key emotion representation models that have been widely employed in AICA and description of available datasets for performing evaluation with quantitative comparison of label noise and dataset bias. We then summarize and compare the representative approaches on (1) emotion feature extraction, including both handcrafted and deep features, (2) learning methods on dominant emotion recognition, personalized emotion prediction, emotion distribution learning, and learning from noisy data or few labels, and (3) AICA based applications. Finally, we discuss some challenges and promising research directions in the future, such as image content and context understanding, group emotion clustering, and viewer-image interaction.

中文翻译：

---

情感图像内容分析：两个十年回顾与新视角

图像可以传达丰富的语义，诱发观看者的各种情绪。近来，随着情商的快速进步和视觉数据的爆炸式增长，情感图像内容分析（AICA）的研究工作已经展开。在本次调查中，我们将全面回顾 AICA 近二十年来的发展，特别是针对三个主要挑战——情感差距、感知主观性、标签噪声和缺席，重点关注最先进的方法. 我们首先介绍了在 AICA 中广泛使用的关键情感表示模型，并描述了可用数据集进行评估，并对标签噪声和数据集偏差进行定量比较。然后我们总结并比较了（1）情感特征提取的代表性方法，包括手工和深度特征，（2）主导情感识别的学习方法，个性化情感预测，情感分布学习，以及从噪声数据或少量标签中学习， (3) 基于 AICA 的应用程序。最后，我们讨论了未来的一些挑战和有前景的研究方向，例如图像内容和上下文理解、群体情感聚类和观众-图像交互。