Research Interests

• Multimodal Learning

- Image(Video)-Text

Dense Video Captioning / Video Question Grounding / Video Moment Retrieval / Change Captioning

- Image(Video)-Audio

Sound Source Localization

• Autonomous Driving 

- Trajectory Prediction

- 3D Object Detection

- Pedestrian Detection

• Multi-task Learning 

- Multi-task Learning

Sound Source Localization

Image(Video)-Audio
Audio Visual Question Answering

Moment Retrieval/Highlight Detection

3D Object Detection

Pedestrian Detection