3 papers
cs.CV2026
Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning
Yuquan Bi, Hongsong Wang, Xinli Shi +3
Diffusion models have demonstrated strong capabilities in generating high-fidelity 3D human poses, yet their iterative nature and multi-hypothesis requirements incur substantial co…
cs.CV2025
Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP Inference
Chengze Jiang, Minjing Dong, Xinli Shi +1
Vision-language pre-training models (VLPs) demonstrate strong multimodal understanding and zero-shot generalization, yet remain vulnerable to adversarial examples, raising concerns…
cs.CV2025
ColorVein: Colorful Cancelable Vein Biometrics
Yifan Wang, Jie Gui, Xinli Shi +3
Vein recognition technologies have become one of the primary solutions for high-security identification systems. However, the issue of biometric information leakage can still pose…