Junyu Dong

8

Papers

14

Total Citations

Papers (8)

NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting

OmniVTON: Training-Free Universal Virtual Try-On

Correlation-Attention Masked Temporal Transformer for User Identity Linkage Using Heterogeneous Mobility Data

PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium

Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecasting

Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution

Where the Devil Hides: Deepfake Detectors Can No Longer Be Trusted

Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection