Hyung Jin Chang

37

Papers

31

Total Citations

Papers (37)

MoST: Motion Style Transformer Between Diverse Action Contents

GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement

Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics

PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation

Single-view Image to Novel-view Generation for Hand-Object Interactions

What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation

Unsupervised Learning of Complex Articulated Kinematic Structures Combining Motion and Skeleton Information

Kinematic Structure Correspondences via Hypergraph Matching

Visual Tracking Using Attention-Modulated Disintegration and Integration

Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold

Attentional Correlation Filter Network for Adaptive Visual Tracking

Context-Aware Deep Feature Compression for High-Speed Visual Tracking

Joint Manifold Diffusion for Combining Predictions on Decoupled Observations

G2L-Net: Global to Local Network for Real-Time 6D Pose Estimation With Embedding Vector Features

Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders

FS-Net: Fast Shape-Based Network for Category-Level 6D Object Pose Estimation With Decoupled Rotation Mechanism

FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation

VaB-AL: Incorporating Class Imbalance and Difficulty With Variational Bayes for Active Learning

Collaborative Learning for Hand and Object Reconstruction With Attention-Guided Graph Convolution

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

HS-Pose: Hybrid Scope Feature Extraction for Category-Level Object Pose Estimation

GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields

Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning

DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation

Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images

SeqHAND: RGB-Sequence-Based 3D Hand Pose and Shape Estimation

Combining Task Predictors via Enhancing Joint Predictability

S2Contact: Graph-Based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning

Global-Local Motion Transformer for Unsupervised Skeleton-Based Action Learning

Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline

Contrastive Vicinal Space for Unsupervised Domain Adaptation

PersonaBooth: Personalized Text-to-Motion Generation

3D Prior Is All You Need: Cross-Task Few-shot 2D Gaze Estimation

Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models

AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation

High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation

Switching Temporary Teachers for Semi-Supervised Semantic Segmentation