← Search

Gwantae Kim

2 accepted papers

2024

Towards Multi-Domain Face Landmark Detection with Synthetic Data from Diffusion Model

ICASSP 2024accepted

Recently, deep learning-based facial landmark detection for in-the-wild faces has achieved significant improvement. However, there are still challenges in face landmark detection in other domains (e.g. cartoon, caricature, etc). This is due to the scarcity of extensively annotated training data. To…

Cited by 0SourceScholar
2023

MPE4G : Multimodal Pretrained Encoder for Co-Speech Gesture Generation

ICASSP 2023accepted

When virtual agents interact with humans, gestures are crucial to delivering their intentions with speech. Previous multimodal co-speech gesture generation models required encoded features of all modalities to generate gestures. If some input modalities are removed or contain noise, the model may no…

Cited by 0SourceScholar