☕️About Me
Yuki Hirakawa received the BSc in physics from Keio University, Tokyo, Japan, in 2018, and the MEng in artificial intelligence from Tokyo Institute of Technology (now Institute of Science Tokyo), Tokyo, Japan, in 2022. In 2022, he joined ZOZO NEXT Inc. as a research scientist, working on machine learning applications in the fashion domain.
Interests
- Machine learning
- Computer Vision
- Natural Language Processing
- Kansei Engineering
Education
MEng in Artificial Intelligence
Tokyo Institute of Technology (supervised by Prof. Masamichi Shimosaka, A Lightweight Driving Behavior Modeling Using Greedy Feature Optimization)
BSc in Physics
Keio University (supervised by Prof. Ayori Mitsutake, Constant-Temperature Molecular Dynamics of an Argon System)
Recent Papers
(2024).
An Empirical Analysis of GPT-4V's Performance on Fashion Aesthetic Evaluation'.
SIGGRAPH Asia Technical Communications.
(2024).
A Fashion Item Recommendation Model in Hyperbolic Space.
CVPR Workshops.
(2024).
From Snap to Score: A Comprehensive Resource for Predicting Fashion Preferences Using Competitive-Based Ranking.
The 27th Meeting on Image Recognition and Understanding.
(2024).
大規模視覚言語モデルを用いた「似合う」の自動評価法.
第27回 画像の認識・理解シンポジウム.