6 papers
Controllable Dance Generation with Style-Guided Motion Diffusion
Hongsong Wang, Ying Zhu, Xin Geng +1
Dance plays an important role as an artistic form and expression in human culture, yet automatically generating dance sequences is a significant yet challenging endeavor. Existing…
Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees
Haodong Lei, Hongsong Wang, Xin Geng +2
Autoregressive (AR) image models achieve diffusion-level quality but suffer from sequential inference, requiring approximately 2,000 steps for a 576x576 image. Speculative decoding…
SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
Xiaofeng Tan, Hongsong Wang, Xin Geng +1
Text-to-motion generation is essential for advancing the creative industry but often presents challenges in producing consistent, realistic motions. To address this, we focus on fi…
Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection
Xiaofeng Tan, Hongsong Wang, Xin Geng +1
Video anomaly detection (VAD) is a vital yet complex open-set task in computer vision, commonly tackled through reconstruction-based methods. However, these methods struggle with t…
STHFL: Spatio-Temporal Heterogeneous Federated Learning
Shunxin Guo, Hongsong Wang, Shuxia Lin +2
Federated learning is a new framework that protects data privacy and allows multiple devices to cooperate in training machine learning models. Previous studies have proposed multip…
Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization
Shunxin Guo, Hongsong Wang, Shuxia Lin +2
Federated learning is an efficient framework designed to facilitate collaborative model training across multiple distributed devices while preserving user data privacy. A significa…