Picture for Jiyoung Lee

Jiyoung Lee

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

Apr 10, 2023
Gyeongsik Moon, Hongsuk Choi, Sanghyuk Chun, Jiyoung Lee, Sangdoo Yun

Figure 1 for Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

Figure 2 for Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

Figure 3 for Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

Figure 4 for Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

* Published at CVPRW 2023

Access Paper or Ask Questions

Dual-path Adaptation from Image to Video Transformers

Mar 17, 2023
Jungin Park, Jiyoung Lee, Kwanghoon Sohn

Figure 1 for Dual-path Adaptation from Image to Video Transformers

Figure 2 for Dual-path Adaptation from Image to Video Transformers

Figure 3 for Dual-path Adaptation from Image to Video Transformers

Figure 4 for Dual-path Adaptation from Image to Video Transformers

* CVPR 2023. Code is available at https://github.com/park-jungin/DualPath

Access Paper or Ask Questions

Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech

Feb 27, 2023
Jiyoung Lee, Joon Son Chung, Soo-Whan Chung

Figure 1 for Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech

Figure 2 for Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech

Figure 3 for Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech

Figure 4 for Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech

* ICASSP 2023. Project page: https://facetts.github.io

Access Paper or Ask Questions

Semi-Parametric Video-Grounded Text Generation

Jan 27, 2023
Sungdong Kim, Jin-Hwa Kim, Jiyoung Lee, Minjoon Seo

Figure 1 for Semi-Parametric Video-Grounded Text Generation

Figure 2 for Semi-Parametric Video-Grounded Text Generation

Figure 3 for Semi-Parametric Video-Grounded Text Generation

Figure 4 for Semi-Parametric Video-Grounded Text Generation

* Preprint (16 pages, 5 figures)

Access Paper or Ask Questions

Language-free Training for Zero-shot Video Grounding

Oct 24, 2022
Dahye Kim, Jungin Park, Jiyoung Lee, Seongheon Park, Kwanghoon Sohn

Figure 1 for Language-free Training for Zero-shot Video Grounding

Figure 2 for Language-free Training for Zero-shot Video Grounding

Figure 3 for Language-free Training for Zero-shot Video Grounding

Figure 4 for Language-free Training for Zero-shot Video Grounding

* Accepted to WACV 2023

Access Paper or Ask Questions

Specializing Multi-domain NMT via Penalizing Low Mutual Information

Oct 24, 2022
Jiyoung Lee, Hantae Kim, Hyunchang Cho, Edward Choi, Cheonbok Park

Figure 1 for Specializing Multi-domain NMT via Penalizing Low Mutual Information

Figure 2 for Specializing Multi-domain NMT via Penalizing Low Mutual Information

Figure 3 for Specializing Multi-domain NMT via Penalizing Low Mutual Information

Figure 4 for Specializing Multi-domain NMT via Penalizing Low Mutual Information

* Accepted in EMNLP 2022

Access Paper or Ask Questions