3 papers
cs.CV2025
RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space
Jingyun Liang, Jingkai Zhou, Shikai Li +5
Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control ov…
cs.CV2025
On Denoising Walking Videos for Gait Recognition
Dongyang Jin, Chao Fan, Jingzhe Ma +3
To capture individual gait patterns, excluding identity-irrelevant cues in walking videos, such as clothing texture and color, remains a persistent challenge for vision-based gait…
cs.CV2021
ELSA: Enhanced Local Self-Attention for Vision Transformer
Jingkai Zhou, Pichao Wang, Fan Wang +3
Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning. The performance of local self-attention (LSA) is just on par w…