Welcome to Vo Minh Duc Laboratory
Vision, Multimodality, and Deep learning
I am VO Minh Duc, a Project Assistant Professor at Nakayama Lab, Grad. School of Information Science and Technology, the University of Tokyo.
I received B.Sc. and M.S. degrees in Computer Science at the University of Science, Vietnam National University Ho Chi Minh City. I received Ph.D. degree in Computer Science at The Graduate University for Advanced Studies (SOKENDAI) (while at National Institute of Informatics (NII)), advised by Prof. Akihiro Sugimoto.
I am collaborating closely with members of our lab as well as external collaborators (see Team). Our current research interests are computer vision and machine learning, including but not limited to image/video synthesis (GAN, Diffusion model), style transfer, vision and language, image recognition, debiasing, transfer learning, domain adaptation, and deep learning.
We want to be able to build the perfect instruments to answer the scientific questions we deem most important (see our Researchs, and Publications).
News
Mar 2024
Award: 委員特別賞. 言語処理学会第30回年次大会(NLP2024).
1 paper accepted to 2024 IEEE CVPR workshop on fair, data-efficient, and trusted computer vision.
Feb 2024
1 paper accepted to CVPR 2024.
JSPS Grant-in-Aid for Early-Career Scientists (KAKENHI) FY 2024 - 2025.
The National Institute of Informatics (Japan) collaborative research fund FY 2024.
Jan 2024
Attending WACV 2024 in Hawaii, US.
Dec 2023
Attending EMNLP 2023 in Singapore.
Nov 2023
3 papers submitted to CVPR 2024.
Oct 2023
A commentary paper accepted for publication in 日本画像学会誌 (Journal of the Imaging Society of Japan): Anticipation Captioning with Commonsense Knowledge.
3 papers accepted to WACV 2024:
- Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data
- Revisiting Latent Space of GAN Inversion for Robust Real Image Editing
- Label Augmentation as Inter-class Data Augmentation for Conditional Image Synthesis with Imbalanced Data
Attending ICCV 2023 in Paris, France.