图像美学信息增强的视觉感知推荐系统  

Image Aesthetics-enhanced Visual Perception Recommendation System

作　　者：张凯煊 蔡国永[2] 朱琨日 ZHANG Kaixuan;CAI Guoyong;ZHU Kunri(College of Computer and Information Security,Guilin University of Electronic Technology,Guilin,Guangxi 541000,China;Key Laboratory of Guangxi Trusted Software(Guilin University of Electronic Technology),Guilin,Guangxi 541000,China)

机构地区：[1]桂林电子科技大学计算机与信息安全学院,广西桂林541000 [2]广西可信软件重点实验室(桂林电子科技大学),广西桂林541000

出　　处：《计算机科学》2023年第S02期273-280,共8页Computer Science

基　　金：国家自然科学基金(61763007);广西可信软件重点实验室项目(kx202060)。

摘　　要：视觉感知推荐系统旨在从视觉认知角度出发,通过提取物品图像的视觉特征来增强用户和物品交互的行为特征,建模用户视觉与行为相关的偏好,从而更好地进行推荐。已有的视觉感知推荐研究中,通常使用预训练的卷积神经网络(CNN)来提取视觉对象语义特征,很少考虑物品外观图像内部隐藏的美学风格特征;其次,在视觉感知推荐中用户和物品的交互行为结构嵌入信息通常被忽视。为了解决这些问题,提出了一个融合图像美学和行为交互结构嵌入的美学特征感知视觉推荐系统(ABVR)。ABVR使用预训练ViT模型提取图像的高层视觉特征——语义类别特征,利用美学提取网络挖掘出图像中的中层美学视觉特征——物品的颜色、形状等特征,利用图卷积神经网络(GCN)模块学习用户物品交互图结点的多层图结构嵌入特征,最后将3类特征关联融合,以实现美学增强的视觉推荐。在两个真实数据集上进行了大量实验,验证了ABVR模型在视觉推荐性能提升上的有效性。The visual perception recommendation system aims to enhance the behavioral features of user-item interaction by extracting the visual features of item images from the perspective of visual cognition,and model the user’s visual and behavior-rela-ted preferences,so as to make better recommendations.In the existing visual perception recommendation research,pre-trained convolutional neural network(CNN)is usually used to extract the semantic features of visual objects,and the hidden aesthetic style features inside the appearance image of the item are rarely considered.In addition,the embedded information of user-item interaction behavior structure is usually ignored in visual perception recommendation.To address these issues,an aesthetic feature-aware visual recommendation system is proposed that fuses image aesthetics and behavioral interaction structure embeddings(ABVR).ABVR uses the pre-trained ViT model to extract the high-level visual features of the image-semantic category features,uses the aesthetic extraction network to mine the middle-level aesthetic visual features in the image--the color,shapes and other features of the items,and uses the graph convolution neural network(GCN)module to learn the multi-layer graph structure embedding features of user item interaction graph nodes,and finally associates and fuses the three types of features to achieve aesthetically enhanced visual recommendations.Extensive experiments are conducted on two real datasets to verify the effectiveness of the ABVR model in improving visual recommendation performance.

关 键 词：视觉感知 美学特征 视觉推荐 图卷积神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]