文献类型：期刊文献

英文题名：Fine-Grained Emotion Adaptive Alignment Network for Image Emotion Distribution Transfer

作者：Zhang, Jing[1];Zhu, Jixiang[1];Kang, Yumo[1];Li, Dongdong[1];Wang, Zhe[1]

机构：[1]East China Univ Sci & Technol, Shanghai 200231, Peoples R China

年份：2026

卷号：17

期号：2

起止页码：2383

外文期刊名：IEEE TRANSACTIONS ON AFFECTIVE COMPUTING

收录：;EI(收录号：20260419962886);WOS:【SCI-EXPANDED(收录号:WOS:001783796600020)】；

基金：This work was supported by the Natural Science Foundation of Shanghai "Research on image sentiment analysis and expression based on human vision and cognitive psychology" under Grant 22ZR1418400.

语种：英文

外文关键词：Image color analysis; Semantics; Feature extraction; Transformers; Cognition; Adaptive systems; Accuracy; Visualization; Psychology; Deep learning; Image emotion distribution transfer; fine-grained emotion adaptive alignment; multiple codebooks; feature-enhanced driven attention

摘要：Our research found that images dominated by a particular emotion typically exhibit certain commonalities, and mapping the features of images with similar emotion distribution to adjacent emotion feature space helps capture the emotion distribution of the images. Based on this, we propose a novel Fine-grained Emotion adaptive Alignment Network (FEA-Net) for image emotion distribution transfer, which utilizes multiple codebooks to store the latent distributions of images from different emotion categories for realizing the transfer of emotion distributions between images. To ensure the consistency between the emotion distributions of generated and target images, we propose an adaptive feature alignment module, which maps emotion features to different channels and computes the adaptive soft cross-entropy loss to reduce the gap in emotion features at the channel level. In addition, a feature-enhanced driven attention module is proposed to enhance the quality of generated images, which utilizes feature self-enhancement to enrich the information of discrete features, combines with a residual connection structure to retain volatile content information. Experiments on the widely used public dataset indicate that our proposed FEA-Net not only presents outstanding emotion consistency between source and target image after emotion transfer but also can generate content consistent and emotion changing high-quality images.