Hi! I’m Heeseung Yun, a Ph.D. student at Seoul National University Vision and Learning Lab, working with Prof. Gunhee Kim. My research goal is to endow intelligent systems with multisensory, omnidirectional perception for reasoning or interaction as humans effortlessly do in ther daily lives. I’m generally interested in multimodal representation learning, video understanding, and geometric deep learning.
Here is my Curriculum Vitae.
- Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal DistillationIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2023
- Fusing Pre-trained Language Models with Multimodal Prompts through Reinforcement LearningIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023
- Panoramic Vision Transformer for Saliency Detection in 360° Videos ✨In European Conference on Computer Vision (ECCV) 2022
- Pano-AVQA: Grounded Audio-Visual Question Answering on 360° VideosIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2021
- Transitional Adaptation of Pretrained Models for Visual StorytellingIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021
- Character Grounding and Re-identification in Story of Videos and Text DescriptionsIn European Conference on Computer Vision (ECCV) 2020
How to pronounce my firstname: Hissing without second i ( [ hísŋ ] )
(Simpler way: A song that he sung)