← Search

Yi-Lun Lee

2 accepted papers

2023

Multimodal Prompting With Missing Modalities for Visual Recognition

CVPR 2023poster

In this paper, we tackle two challenges in multimodal learning for visual recognition: 1) when missing-modality occurs either during training or testing in real-world situations; and 2) when the computation resources are not available to finetune on heavy transformer models. To this end, we propose…

2020

Learning Face Recognition Unsupervisedly by Disentanglement and Self-Augmentation

ICRA 2020poster

As the growth of smart home, healthcare, and home robot applications, learning a face recognition system which is specific for a particular environment and capable of self-adapting to the temporal changes in appearance (e.g., caused by illumination or camera position) is nowadays an important topic.…

Cited by 7SourceScholar