Xianzhong Long — accepted AI-conference papers

2026

Point Cloud Quality Assessment via Multi-View Structure-Aware Feature Fusion

Jian Xiong, Lingxia Jiang, Xianzhong Long, Miaohui Wang, Hao Gao

AAAI 2026technical

Point cloud quality assessment (PCQA) is essential for reliable 3D visual applications. While point-based methods face challenges in characterizing distortions due to point cloud disorder, projection-based approaches offer better efficiency but suffer from geometric distortion insensitivity and text

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training

Yao Ge, Yun Li, Keji Han, Junyi Zhu, Xianzhong Long

ICCV 2023oral

Deep neural networks have achieved remarkable results across various tasks. However, they are susceptible to adversarial examples, which are generated by adding adversarial perturbations to original data. Adversarial training (AT) is the most effective defense mechanism against adversarial examples…

Cited by 10 PDF ↗code ↗Scholar ↗