Most current methods for image emotion analysis suffer from the affective gap, in which features directly extracted from images are supervised by a single emotional label, which may not align with users’ perceived emotions. To effectively address this limitation, this article introduces a novel multi-stage perception approach inspired by the human staged emotion perception process. The proposed approach comprises three perception modules: entity perception, attribute perception, and emotion perception. The entity perception module identifies entities in images, while the attribute perception module captures the attribute content associated with each entity. Finally, the emotion perception module combines entity and attribute information to extract emotion features. Pseudo-labels of entities and attributes are generated through image segmentation and vision-language models to provide auxiliary guidance for network learning. A progressive understanding of entities and attributes allows the network to hierarchically extract semantic-level features for emotion analysis. Comprehensive experiments on image emotion classification, regression, and distribution learning demonstrate the superior performance of our multi-stage perception network.

中文翻译：

---

用于图像情感分析的多阶段视觉感知方法


目前大多数图像情感分析方法都存在情感差距，即直接从图像中提取的特征由单个情感标签监督，这可能与用户感知的情感不一致。为了有效解决这一限制，本文引入了一种新颖的多阶段感知方法，其灵感来自于人类阶段性情感感知过程。所提出的方法包括三个感知模块：实体感知、属性感知和情感感知。实体感知模块识别图像中的实体，而属性感知模块捕获与每个实体相关的属性内容。最后，情感感知模块结合实体和属性信息提取情感特征。通过图像分割和视觉语言模型生成实体和属性的伪标签，为网络学习提供辅助指导。对实体和属性的渐进理解允许网络分层提取语义级特征以进行情感分析。图像情感分类、回归和分布学习的综合实验证明了我们的多级感知网络的优越性能。