Research Areas：

Computer Vision and Machine Learning

Artificial Intelligence Security

Selective publications（Full list：https://dblp.org/Pang:Shanmin  or https://scholar.google.com）

Journal papers：

[1]  Qi Guo, Shanmin Pang, Xiaojun Jia, Yang Liu, Qing Guo. Efficient generation of targeted and transferable adversarial examples for vision-language models via diffusion models [J], IEEE Transactions on Information Forensics & Security, 20: 1333-1348, 2025.

[2]  Shanmin Pang, Yueyang Zeng, Jiawei Zhao, Jianru Xue. A mutually textual and visual refinement network for image-text matching [J], IEEE Transactions on Multimedia, 26: 7555-7566, 2024.

[3]  Wenzhao Qiu, Shanmin Pang, Hao Zhang, Jianwu Fang, Jianru Xue. A tightly coupled temporal fusion pipeline for vectorized HD map learning [J], IEEE Robotics and Automation Letters, 12(9): 11289-11296, 2024.

[4]  Wenyu Hao, Shanmin Pang, Xiuxiu Bai, Jianru Xue. Tensor-based incomplete multi-view clustering with low-rank data reconstruction and consistency guidance [J]. IEEE Transactions on Circuits and Systems for Video Technology, 33(12):7156-7169, 2023.

[5]  Xingyu Chen, Jianru Xue, Shanmin Pang. Sparse Semantic Map-Based Monocular Localization in Traffic Scenes Using Learned 2D-3D Point-Line Correspondences [J], IEEE Robotics and Automation Letters, 7(4):11894-11901, 2022.

Conference Papers：

[1] Lizhen Xu, Xiuxiu  Bai, Xiaojun Jia, Jianwu Fang, Shanmin Pang. Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning [C], ICCV 2025. (Project Page)

[2] Wenzhao Qiu, Shanmin Pang, Hao zhang, Jianwu Fang, Jianru Xue. HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning [C], WACV 2025. (Project Page)

[3] Yizhuo Ma, Shanmin Pang, Qi Guo, Tianyu Wei, Qing Guo. ColJailBreak: Collaborative generation and editing for jailbreaking text-to-image deep generation [C], NeurIPS 2024. (Project Page)

[4] Zhikai Chen, Lingxi Xie, Shanmin Pang, Yong He, Bo Zhang. MagDR: Mask-guided detection and reconstruction for defending deepfakes [C], CVPR 2021.

[5] Ruijian Jia, Xinsheng Wang, Shanmin Pang, Jihua Zhu, Jianru Xue. Look, Listen and Infer [C], ACM MM 2020. (Project Page)