Personalized Fashion Recommendation with Image Attributes and Aesthetics Assessment

TL;DR

This paper introduces a novel personalized fashion recommendation approach that leverages combined image and text attributes, addressing cold-start issues and aligning with user aesthetics, showing promising results on the IQON3000 dataset.

Contribution

The work proposes a new method that integrates image and text attributes into a unified graph, improving recommendation accuracy and cold-start handling using large language and vision models.

Findings

Achieves competitive accuracy on IQON3000 dataset

Effectively models user aesthetics and item attributes

Addresses cold-start problem with attribute graphs

Abstract

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.