Xiaochun Cao

PXDepth achieves a breakthrough in monocular depth estimation by preserving fine structures and boundaries while ensuring global depth accuracy, outperforming traditional methods.

RISTER achieves state-of-the-art accuracy in multi-oriented scene text recognition by embedding rotation invariance with theoretical guarantees, eliminating reliance on data-driven orientation correction.

Multi-item users can face significantly more powerful poisoning attacks, but a new method achieves robust estimation without sacrificing performance.