no code implementations • 11 Mar 2024 • Yuki Tatsukawa, I-Chao Shen, Anran Qi, Yuki Koyama, Takeo Igarashi, Ariel Shamir
To solve this problem, we present FontCLIP: a model that connects the semantic understanding of a large vision-language model with typographical knowledge.
1 code implementation • 29 Nov 2023 • Toby Chong, Alina Chadwick, I-Chao Shen, Haoran Xie, Takeo Igarashi
We repeated the process for the same skin patch under three cosmetic products.
1 code implementation • 13 Jun 2022 • Yi He, Xi Yang, Chia-Ming Chang, Haoran Xie, Takeo Igarashi
Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions.
no code implementations • 29 Mar 2022 • I-Chao Shen, Yu Ju Chen, Oliver van Kaick, Takeo Igarashi
The key idea of our method is the use of the Monte Carlo tree search (MCTS) algorithm and differentiable rendering to separately predict sequential topological actions and geometric actions.
no code implementations • 10 Sep 2021 • Toby Chong, I-Chao Shen, Nobuyuki Umetani, Takeo Igarashi
Furthermore, we proposed to use a custom-designed measurement garment, and we captured paired images of the measurement garment and the target garments.
no code implementations • 9 Apr 2021 • Heng Fang, Xi Yang, Taichi Kin, Takeo Igarashi
Whole-brain surface extraction is an essential topic in medical imaging systems as it provides neurosurgeons with a broader view of surgical planning and abnormality detection.
no code implementations • 8 Mar 2021 • Toby Chong, Nolwenn Maudet, Katsuki Harima, Takeo Igarashi
How to handle gender with machine learning is a controversial topic.
no code implementations • 29 Jun 2020 • Xi Yang, Ding Xia, Taichi Kin, Takeo Igarashi
In this study, we offer a two-step surface-based deep learning pipeline that achieves significantly higher performance.
1 code implementation • CVPR 2020 • Xi Yang, Ding Xia, Taichi Kin, Takeo Igarashi
In this paper, instead of 2D medical images, we introduce an open-access 3D intracranial aneurysm dataset, IntrA, that makes the application of points-based and mesh-based classification and segmentation models available.
no code implementations • 20 Feb 2020 • Yuki Koyama, Takeo Igarashi
One promising approach is to leverage human computation; that is, to incorporate human input into the computation process.
no code implementations • 24 Jun 2019 • Toby Chong Long Hin, I-Chao Shen, Issei Sato, Takeo Igarashi
We present a human-in-the-optimization method that allows users to directly explore and search the latent vector space of generative image modeling.
no code implementations • 2 May 2019 • Xi Yang, Bojian Wu, Issei Sato, Takeo Igarashi
Deep neural networks (DNNs) have a high accuracy on image classification tasks.