Kuk-Jin Yoon

31

Papers

103

Total Citations

Papers (31)

Towards Robust 3D Object Detection with LiDAR and 4D Radar Fusion in Various Weather Conditions

Towards Real-world Event-guided Low-light Video Enhancement and Deblurring

T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory

Temporal Event Stereo via Joint Learning with Stereoscopic Flow

CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring

Quantifying Task Priority for Multi-Task Optimization

LiDAR-based All-weather 3D Object Detection via Prompting and Distilling 4D Radar

Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection

Event-guided Unified Framework for Low-light Video Enhancement, Frame Interpolation, and Deblurring

WarpHE4D: Dense 4D Head Map toward Full Head Reconstruction

Robust Adverse Weather Removal via Spectral-based Spatial Grouping

DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation

Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training

Doppler-Aware LiDAR-RADAR Fusion for Weather-Robust 3D Detection

Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model

Any6D: Model-free 6D Pose Estimation of Novel Object

Improving Transferability for Cross-Domain Trajectory Prediction via Neural Stochastic Differential Equation

FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks

Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle

Class Tokens Infusion for Weakly Supervised Semantic Segmentation

TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation

From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation

Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning

Frequency-aware Event-based Video Deblurring for Real-World Motion Blur

Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning

WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels

Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras

Multi-modal Knowledge Distillation-based Human Trajectory Forecasting

Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning

From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras

Learning Large Motion Estimation from Intermediate Representations with a High-Resolution Optical Flow Dataset Featuring Long-Range Dynamic Motion