7 papers
SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition
Yanan Liu, Anqi Zhu, Jingmin Zhu +6
Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled ex…
GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance
Zehua Chen, Yucheng Yang, Binjie Yuan +3
Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently, bridge models have introduced…
STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning
Zinuo Li, Yongxin Guo, Jun Liu +7
Human understanding of video dynamics relies on forming structured representations of entities, actions, and temporal relations before engaging in abstract reasoning. In contrast,…
ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
Jing Xu, Weiqiang Wang, Cunjian Chen +2
Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production,…
ST-GDance: Long-Term and Collision-Free Group Choreography from Music
Jing Xu, Weiqiang Wang, Cunjian Chen +2
Group dance generation from music has broad applications in film, gaming, and animation production. However, it requires synchronizing multiple dancers while maintaining spatial co…
TSTMotion: Training-free Scene-aware Text-to-motion Generation
Ziyan Guo, Haoxuan Qu, Hossein Rahmani +4
Text-to-motion generation has recently garnered significant research interest, primarily focusing on generating human motion sequences in blank backgrounds. However, human motions…