Dongjin Kim

6

Papers

22

Total Citations

Papers (6)

Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge

Object-aware Sound Source Localization via Audio-Visual Scene Understanding

IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising

Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection

REPrune: Channel Pruning via Kernel Representative Selection

Harnessing Meta-Learning for Improving Full-Frame Video Stabilization