Changick Kim

papers

1,105

total citations

papers (26)

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

CVPR 2020arXiv

294

citations

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

CVPR 2021arXiv

166

citations

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

ECCV 2020arXiv

150

citations

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

CVPR 2022arXiv

citations

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

CVPR 2023arXiv

citations

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

ECCV 2024arXiv

citations

ProtoFL: Unsupervised Federated Learning via Prototypical Distillation

ICCV 2023arXiv

citations

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

CVPR 2025arXiv

citations

SAFIRE: Segment Any Forged Image Region

AAAI 2025arXiv

citations

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

ICCV 2023arXiv

citations

Focusing on Tracks for Online Multi-Object Tracking

CVPR 2025

citations

Audio-Visual Glance Network for Efficient Video Recognition

ICCV 2023arXiv

citations

DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes

ICCV 2021arXiv

citations

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

ICCV 2025arXiv

citations

Difficulty-aware Balancing Margin Loss for Long-tailed Recognition

AAAI 2025arXiv

citations

Diffusion Model Patching via Mixture-of-Prompts

AAAI 2025arXiv

citations

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

ICCV 2025arXiv

citations

Enhancing Robustness in Incremental Learning with Adversarial Training

AAAI 2025arXiv

citations

Indirect Gradient Matching for Adversarial Robust Distillation

ICLR 2025arXiv

citations

Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition

ECCV 2024arXiv

citations

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

CVPR 2025arXiv

citations

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

ICCV 2021

citations

Changick Kim

papers (26)

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

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

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

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

Learning to Discriminate Information for Online Action Detection

Few-Shot Open-Set Recognition by Transformation Consistency

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

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

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

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

ProtoFL: Unsupervised Federated Learning via Prototypical Distillation

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

SAFIRE: Segment Any Forged Image Region

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

Focusing on Tracks for Online Multi-Object Tracking

Audio-Visual Glance Network for Efficient Video Recognition

DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes

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

Difficulty-aware Balancing Margin Loss for Long-tailed Recognition

Diffusion Model Patching via Mixture-of-Prompts

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

Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition

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

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

papers (26)

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

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

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

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

Learning to Discriminate Information for Online Action Detection

Few-Shot Open-Set Recognition by Transformation Consistency

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

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

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

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

ProtoFL: Unsupervised Federated Learning via Prototypical Distillation

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

SAFIRE: Segment Any Forged Image Region

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

Focusing on Tracks for Online Multi-Object Tracking

Audio-Visual Glance Network for Efficient Video Recognition

DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes

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

Difficulty-aware Balancing Margin Loss for Long-tailed Recognition

Diffusion Model Patching via Mixture-of-Prompts

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

Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition

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

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