Dongyoon Wee

10

Papers

22

Total Citations

Papers (10)

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs

Humans as a Calibration Pattern: Dynamic 3D Scene Reconstruction from Unsynchronized and Uncalibrated Videos

Regularizing Dynamic Radiance Fields with Kinematic Fields

CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images

CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval

Regularization on Spatio-Temporally Smoothed Feature for Action Recognition

Decomposed Cross-Modal Distillation for RGB-Based Temporal Action Detection

SEFD: Learning to Distill Complex Pose and Occlusion

READ: Reciprocal Attention Discriminator for Image-to-Video Re-Identification