papers
Publications (3)
cs.CV2025
Interpreting Low-level Vision Models with Causal Effect Maps
Jinfan Hu, Jinjin Gu, Shiyao Yu +5
Deep neural networks have significantly improved the performance of low-level vision tasks but also increased the difficulty of interpretability. A deep understanding of deep model…
cs.CV2025
Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space
Shiyao Yu, Zi-An Wang, Kangning Yin +4
Motion retrieval is crucial for motion acquisition, offering superior precision, realism, controllability, and editability compared to motion generation. Existing approaches levera…
cs.SD2025
Semantics-Aware Human Motion Generation from Audio Instructions
Zi-An Wang, Shihao Zou, Shiyao Yu +2
Recent advances in interactive technologies have highlighted the prominence of audio signals for semantic encoding. This paper explores a new task, where audio signals are used as…