Guang Dai

11

Papers

56

Total Citations

Papers (11)

2382 SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-Form Layout-to-Image Generation

Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation

A Multimodal, Multi-Task Adapting Framework for Video Action Recognition

SpotActor: Training-Free Layout-Controlled Consistent Image Generation

Action Detail Matters: Refining Video Recognition with Local Action Queries

ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs

Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?

Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval

Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient

Low-Biased General Annotated Dataset Generation