Publications

SAND: Stage-Aware Noise Decomposition for Training-Free Diffusion Guidance

EG-3DVG: Expression and Geometry Aware Grounding Decoder for 3D Visual Grounding [codes]

Dual-Path Temporal Decoder for End-to-End Multi-Object Tracking [codes]

EVOLVE: Event-Guided Deformable Feature Transfer and Dual-Memory Refinement for Low-Light Video Object Segmentation [codes]

GRAE-3DMOT: Geometry Relation-Aware Encoder for Online 3D Multi-Object Tracking [codes]

SOAP: Vision-Centric 3D Semantic Scene Completion with Scene-Adaptive Decoder and Occluded Region-Aware View Projection [codes]

Luminance-aware Color Transform for Multiple Exposure Correction [codes]

Local Connectivity-Based Density Estimation for Face Clustering [codes]

BAAM: Monocular 3D Pose and Shape Reconstruction with Bi-contextual Attention Module and Attention-Guided Modeling [codes]

Representative Color Transform for Image Enhancement

Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps

Global and Local Enhancement Networks For Paired and Unpaired Image Enhancement

PieNet: Personalized Image Enhancement Network

Interactive Video Object Segmentation Using Global and Local Transfer Modules

Instance-Level Future Motion Estimation in a Single Image Based on Ordinal Regression

Meta Learning for Unsupervised Clustering

Interactive Video Object Segmentation Using Sparse-to-Dense Networks

Sequential Clique Optimization for Video Object Segmentation

CDTS: Collaborative Detection, Tracking, and Segmentation for Online Multiple Object Segmentation in Videos

Primary Object Segmentation in Videos Based on Region Augmentation and Reduction [project page]

POD: Discovering Primary Objects in Videos Based on Evolutionary Refinement of Object Recurrence, Background, and Primary Object Models [project page]

Dark Image Enhancement Based on Pairwise Target Contrast and Multi-scale Detail Boosting

Robust Video Stabilization Based on Mesh Grid Warping of Rolling-free Features

Dual-Stream Feature Aggregation and Dual Guided Upsampling for Efficient Multi-Exposure Correction

Image Enhancement with Intensity Transformation on Embedding Space

Center-Guided Transformer for Panoptic Segmentation

Joint Appearance and Motion Model With Temporal Transformer for Multiple Object Tracking

deepGBLUP: Joint Deep Learning Networks and GBLUP Framework for Accurate Genomic Prediction of Complex Traits in Korean Native Cattle

Video Frame Interpolation Based on Symmetric and Asymmetric Motions

Sequential Clique Optimization for Unsupervised and Weakly Supervised Video Object Segmentation

Local Memory Read-and-Comparator for Video Object Segmentation

Use of a Graph Neural Network to the Weighted Gene Co-expression Network Analysis of Korean Native Cattle

Light Field Image Super-Resolution Based on Multi-Level Structures

BTENet: Back-Fat Thickness Estimation Network for Automated Grading of the Korean Commercial Pig

MSENet: Marbling Score Estimation Network for Automated Assessment of Korean Beef

Unpaired Screen-Shot Image Demoiréing With Cyclic Moiré Learning

Blind and Compact Denoising Network Based on Noise Order Learning

Multi-Scale Warping for Video Frame Interpolation

Light Field Super-Resolution via Adaptive Feature Remixing

Online Multiple Object Tracking Based on Open-Set Few-Shot Learning

Instance-Level Future Motion Estimation in a Single Image Based on Ordinal Regression and Semi-Supervised Domain Adaptation

Multiscale Feature Extractors for Stereo Matching Cost Computation

Unsupervised Primary Object Discovery in Videos Based on Evolutionary Primary Object Modeling with Reliable Object Proposals [project page]

Video Stabilization Based on Feature Trajectory Augmentation and Selection and Robust Mesh Grid Warping [project page]

Efficient Fine-granular Scalable Coding of 3D Mesh Sequences