arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.03085cs.IRcs.AI
收藏

利用图像属性与美学评估进行个性化时尚推荐

Personalized Fashion Recommendation with Image Attributes and Aesthetics Assessment

Chongxian Chen, Fan Mo, Xin Fan, Hayato Yamana

AI总结:

本文提出融合图像与文本构建双属性图的个性化时尚推荐方法,利用大型语言与视觉模型提取细粒度属性,以提升推荐准确率并缓解新商品冷启动问题。

摘要:

个性化时尚推荐是一项困难任务,原因在于:1)推荐决策与用户的审美偏好高度相关,而以往工作常常忽视这一点;2)大量新商品持续推出,导致流行的基于身份(ID)的推荐方法面临严重的冷启动问题。由于消费主义受潮流驱动,推荐这些新商品至关重要。在本工作中,我们旨在提供更准确的个性化时尚推荐,并通过将可用信息(尤其是图像)转换为两个属性图来解决冷启动问题,这两个图分别聚焦于优化图像利用和降低噪声的用户建模。与以往将图像和文本作为两个独立组成部分的方法不同,所提出的方法结合图像与文本信息,以构建更丰富的属性图。借助大型语言模型和视觉模型的进展,我们尝试使用两种不同的提示词,按预期高效提取细粒度属性。在 IQON3000 数据集上的初步实验表明,与基线相比,所提出方法取得了具有竞争力的准确率。

英文摘要:

Personalized fashion recommendation is a difficult task because 1) the decisions are highly correlated with users' aesthetic appetite, which previous work frequently overlooks, and 2) many new items are constantly rolling out that cause strict cold-start problems in the popular identity (ID)-based recommendation methods. These new items are critical to recommend because of trend-driven consumerism. In this work, we aim to provide more accurate personalized fashion recommendations and solve the cold-start problem by converting available information, especially images, into two attribute graphs focusing on optimized image utilization and noise-reducing user modeling. Compared with previous methods that separate image and text as two components, the proposed method combines image and text information to create a richer attributes graph. Capitalizing on the advancement of large language and vision models, we experiment with extracting fine-grained attributes efficiently and as desired using two different prompts. Preliminary experiments on the IQON3000 dataset have shown that the proposed method achieves competitive accuracy compared with baselines.

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。

↑