Chenye Xu — accepted AI-conference papers

2026

Alert-CLIP: Abnormality-aware Latent-Enhanced Representation Tuning of CLIP for Video Anomaly Detection

Yiyan Zhu, Menghao Zhang, Haifeng Sun, Pengfei Ren, Xianao Chu, Chenye Xu +4

CVPR 2026

With the rise of pre-trained vision-language models such as CLIP, performing video anomaly detection (VAD) through cross-modal reasoning has become an emerging trend. However, we observe that CLIP still suffers from weak abnormality awareness: normal and abnormal descriptions are highly entangled in

Cited by 0 Source ↗Scholar ↗

2023

Improving Robust Fariness via Balance Adversarial Training

Chunyu Sun, Chenye Xu, Chengyuan Yao, Siyuan Liang, Yichao Wu, Ding Liang +2

AAAI 2023technical

Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the robust fairness problem. Previously proposed Fair Robust Learning (FRL) adaptively reweights different classes to improv…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗