Hoyoung Choi — accepted AI-conference papers

2024

Integration of Global and Local Representations for Fine-grained Cross-modal Alignment

Seungwan Jin, Hoyoung Choi, Taehyung Noh, Kyungsik Han*

ECCV 2024poster

"Fashion is one of the representative domains of fine-grained Vision-Language Pre-training (VLP) involving a large number of images and text. Previous fashion VLP research has proposed various pre-training tasks to account for fine-grained details in multimodal fusion. However, fashion VLP research…

Cited by 1 Source ↗PDF ↗Scholar ↗

2023

Adversarial Normalization: I Can Visualize Everything (ICE)

Hoyoung Choi, Seungwan Jin, Kyungsik Han

CVPR 2023poster

Vision transformers use [CLS] tokens to predict image classes. Their explainability visualization has been studied using relevant information from [CLS] tokens or focusing on attention scores during self-attention. Such visualization, however, is challenging because of the dependence of the structur…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗