Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Forouzandehmehr, Najmeh, Cao, Yijie, Thakurdesai, Nikhil, Giahi, Ramin, Ma, Luyi, Farrokhsiar, Nima, Xu, Jianpeng, Korpeoglu, Evren, Achan, Kannan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914677166964736
author Forouzandehmehr, Najmeh
Cao, Yijie
Thakurdesai, Nikhil
Giahi, Ramin
Ma, Luyi
Farrokhsiar, Nima
Xu, Jianpeng
Korpeoglu, Evren
Achan, Kannan
author_facet Forouzandehmehr, Najmeh
Cao, Yijie
Thakurdesai, Nikhil
Giahi, Ramin
Ma, Luyi
Farrokhsiar, Nima
Xu, Jianpeng
Korpeoglu, Evren
Achan, Kannan
contents The outfit generation problem involves recommending a complete outfit to a user based on their interests. Existing approaches focus on recommending items based on anchor items or specific query styles but do not consider customer interests in famous characters from movie, social media, etc. In this paper, we define a new Character-based Outfit Generation (COG) problem, designed to accurately interpret character information and generate complete outfit sets according to customer specifications such as age and gender. To tackle this problem, we propose a novel framework LVA-COG that leverages Large Language Models (LLMs) to extract insights from customer interests (e.g., character information) and employ prompt engineering techniques for accurate understanding of customer preferences. Additionally, we incorporate text-to-image models to enhance the visual understanding and generation (factual or counterfactual) of cohesive outfits. Our framework integrates LLMs with text-to-image models and improves the customer's approach to fashion by generating personalized recommendations. With experiments and case studies, we demonstrate the effectiveness of our solution from multiple dimensions.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05941
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs
Forouzandehmehr, Najmeh
Cao, Yijie
Thakurdesai, Nikhil
Giahi, Ramin
Ma, Luyi
Farrokhsiar, Nima
Xu, Jianpeng
Korpeoglu, Evren
Achan, Kannan
Information Retrieval
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
The outfit generation problem involves recommending a complete outfit to a user based on their interests. Existing approaches focus on recommending items based on anchor items or specific query styles but do not consider customer interests in famous characters from movie, social media, etc. In this paper, we define a new Character-based Outfit Generation (COG) problem, designed to accurately interpret character information and generate complete outfit sets according to customer specifications such as age and gender. To tackle this problem, we propose a novel framework LVA-COG that leverages Large Language Models (LLMs) to extract insights from customer interests (e.g., character information) and employ prompt engineering techniques for accurate understanding of customer preferences. Additionally, we incorporate text-to-image models to enhance the visual understanding and generation (factual or counterfactual) of cohesive outfits. Our framework integrates LLMs with text-to-image models and improves the customer's approach to fashion by generating personalized recommendations. With experiments and case studies, we demonstrate the effectiveness of our solution from multiple dimensions.
title Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs
topic Information Retrieval
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2402.05941