Dongsheng Jiang

5

Papers

381

Total Citations

Papers (5)

ControlVideo: Training-free Controllable Text-to-video Generation

Improving Image Restoration through Removing Degradations in Textual Representations

Fix-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text

ProReflow: Progressive Reflow with Decomposed Velocity

AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation