Changick Kim

28

Papers

88

Total Citations

Papers (28)

HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts

Focusing on Tracks for Online Multi-Object Tracking

Diffusion Model Patching via Mixture-of-Prompts

Difficulty-aware Balancing Margin Loss for Long-tailed Recognition

SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering

Enhancing Robustness in Incremental Learning with Adversarial Training

Indirect Gradient Matching for Adversarial Robust Distillation

Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation

Improving the Transferability of Targeted Adversarial Examples Through Object-Based Diverse Input

Introducing Competition To Boost the Transferability of Targeted Adversarial Examples Through Clean Feature Mixup

Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection

Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation

Just a Few Points Are All You Need for Multi-View Stereo: A Novel Semi-Supervised Learning Method for Multi-View Stereo

DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes

PG-RCNN: Semantic Surface Point Generation for 3D Object Detection

Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models

ProtoFL: Unsupervised Federated Learning via Prototypical Distillation

Audio-Visual Glance Network for Efficient Video Recognition

Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation

SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis

VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling

SAFIRE: Segment Any Forged Image Region

Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection

Learning to Discriminate Information for Online Action Detection

Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification

Few-Shot Open-Set Recognition by Transformation Consistency

Meta Batch-Instance Normalization for Generalizable Person Re-Identification