@inproceedings{10.1145/3681758.3698022,
author = {Hirakawa, Yuki and Wada, Takashi and Morishita, Kazuya and Shimizu, Ryotaro and Furusawa, Takuya and Kham, Sai Htaung and Saito, Yuki},
title = {An Empirical Analysis of GPT-4V's Performance on Fashion Aesthetic Evaluation},
year = {2024},
isbn = {9798400711404},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3681758.3698022},
doi = {10.1145/3681758.3698022},
abstract = {Fashion aesthetic evaluation is the task of estimating how well the outfits worn by individuals in images suit them. In this work, we examine the zero-shot performance of GPT-4V on this task for the first time. We show that its predictions align fairly well with human judgments on our datasets, and also find that it struggles with ranking outfits in similar colors. The code is available at https://github.com/st-tech/gpt4v-fashion-aesthetic-evaluation.},
booktitle = {SIGGRAPH Asia 2024 Technical Communications},
articleno = {24},
numpages = {4},
keywords = {vision and language, aesthetic evaluation, fashion},
location = {
},
series = {SA '24}
}