庞孟，博士生导师，江西省高层次海外人才，南昌大学全职引进学科优秀人才（校聘教授），现任职于南昌大学数学与计算机学院及数学与交叉科学研究院（任研究院副主任）。2020至2022年在新加坡南洋理工大学电子与电气工程学院ROSE Lab担任博士后研究员，于2019年获得香港浸会大学博士学位，导师为Yiu-ming Cheung（教育部长江学者、IEEE/IET/AAAS Fellow），于2016和2013年分获大连理工大学硕士和学士学位。主要研究领域为人工智能安全和智慧医疗。目前在国际权威期刊和会议上发表高水平论文40余篇，包括TIFS、TNNLS、TMM、TCSVT、PR、ICML、CVPR、ICLR、AAAI、CIKM、WSDM、ICDM等领域内顶级期刊和会议论文。申请国家发明专利14项（8项已授权），申请软件著作权3项。在社会服务方面，担任国际知名SCI期刊《Expert Systems》（CCF-C）Associate Editor，担任中国计算机学会专委委员，获聘江西省数字政府建设专家库专家，获聘江西省互联网协会AI大模型专业委员会专家库专家，长期受邀担任人工智能/模式识别领域权威期刊（TPAMI、TIFS、TIP、TNNLS、TCYB、TMM、TCSVT、PR等）审稿专家、并多次受邀担任计算机视觉/人工智能领域权威会议（CVPR、ICCV、ICLR、ECCV、AAAI、ECAI、WACV、ICME等）程序委员会委员。在获奖荣誉方面，2015年获IEEE图像处理国际会议最佳10%论文奖（排名第一），2019年获第22届博士研究生日最佳研究表现奖。在教学及学生培养方面，获批1项省级和1项校级教育教学改革研究项目，近期指导本科生获批国家级/省部级大学生创新创业训练计划项目2项，获国家级/省部级专业竞赛奖励3次。

近期部分代表性论文：

期刊论文

[J10] Meng Pang, Binghui Wang, Mang Ye, Yintao Zhou, Wei Huang, Bihan Wen. Heterogeneous Prototype Learning from Contaminated Faces across Domains via Disentangling Latent Factors. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024, in press.   【影响因子10.4, 中科院一区期刊】

[J9] Wei Huang, Wenqiang Xu, Renjie Wan, Peng Zhang, Yufei Zha, Meng Pang* (通讯作者). Auto diagnosis of Parkinson’s disease via a deep learning model based on mixed emotional facial expressions. IEEE Journal of Biomedical and Health Informatics (JBHI), 2024, 28(5): 2547-2557.  【影响因子7.021, 中科院一区期刊】

[J8] Wei Huang, Yintao Zhou, Yiu-ming Cheung, Peng Zhang, Yufei Zha, Meng Pang* (通讯作者). Facial expression guided diagnosis of Parkinson’s disease via high-quality data augmentation. IEEE Transactions on Multimedia (TMM), 2023, 25: 7037–7050. 【影响因子8.182, 中科院一区期刊】

[J7] Meng Pang, Binghui Wang, Mang Ye, Yiu-ming Cheung, Yiran Chen, Bihan Wen. DisP+V: A unified framework for disentangling prototype and variation from single sample per Person, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023, 34(2): 867–881. 【影响因子10.4, 中科院一区期刊】

[J6] Meng Pang, Binghui Wang, Siyu Huang, Yiu-ming Cheung, Bihan Wen. A unified framework for bidirectional prototype learning from contaminated faces across heterogeneous domains, IEEE Transactions on Information Forensics and Security (TIFS), 2022, 17: 1544–1557. 【影响因子 7.231，中科院一区期刊】

[J5] Meng Pang, Yiu-ming Cheung, Qiquan Shi, Mengke Li. Iterative dynamic generic learning for face recognition from a contaminated singe-sample per person. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021, 32(4): 1560–1574. 【影响因子14.255, 中科院一区期刊】

[J4] Meng Pang, Binghui Wang, Yiu-ming Cheung, Yiran Chen, Bihan Wen. VD-GAN: A unified framework for joint prototype and representation learning from contaminated single sample per person. IEEE Transactions on Information Forensics and Security (TIFS), 2021, 16: 2246–2259. 【影响因子7.231, 中科院一区期刊】

[J3] Meng Pang, Yiu-ming Cheung, Binghui Wang, Jian Lou. Synergistic generic learning for face recognition from a contaminated single sample per person. IEEE Transactions on Information Forensics and Security (TIFS), 2020, 15: 195–209.  【影响因子7.231, 中科院一区期刊】

[J2] Meng Pang, Yiu-ming Cheung, Binghui Wang, Risheng Liu. Robust heterogeneous discriminative analysis for face recognition with single sample per person. Pattern Recognition (PR), 2019, 89: 91–107. 【影响因子8.518, 中科院一区期刊】

[J1] Meng Pang, Yiu-ming Cheung, Risheng Liu, Jian Lou, Chuang Lin. Toward efficient image representation: Sparse concept discriminant matrix factorization. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019, 29(11): 3184–3198. 【影响因子5.859, 中科院一区期刊】

会议论文

[C15] Wei Huang, Yinxuan Xu, Yintao Zhou, Zhengyu Li, Jing Huang, Meng Pang*(通讯作者). A Multimodal In Vitro Diagnostic Method for Parkinson’s Disease Combining Facial Expressions and Behavioral Gait Data. Proceedings of the Annual Meeting of the Cognitive Science Society (COGSCI), Marriott Marquis, San Francisco, USA, July 30-Aug 2, 2025.   【认知科学旗舰会议, 计算机学会CCF推荐B类会议】

[C14] Meng Pang, Wenjun Zhang, Nanrun Zhou, Shengbo Chen, Hong Rao. UMFN: Unified multi-domain face normalization for joint cross-domain prototype learning and heterogeneous face recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, USA, June 11-June 15, 2025. 【计算机视觉顶级会议, 计算机学会CCF推荐A类会议】

[C13] Jiate Li, Meng Pang, Yun Dong, Binghui Wang. Deterministic certification of graph neural networks against poisoning attacks with arbitrary perturbations. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, USA, June 11-June 15, 2025. 【计算机视觉顶级会议, 计算机学会CCF推荐A类会议】

[C12] Jiate Li, Meng Pang, Yun Dong, Jinyuan Jia, Binghui Wang. Provably robust explainable graph neural networks against graph perturbation attacks. International Conference on Learning Representations (ICLR), Singapore, Apr 24-Apr 28, 2025.  【深度学习顶级会议, 清华TH-CPL推荐A类会议】

[C11] Jiate Li, Meng Pang*(通讯作者), Binghui Wang*. Practicable black-box evasion attacks on link prediction in dynamic graphs—A graph sequential embedding method. Annual AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, USA, February 25-March 4, 2025.  【人工智能顶级会议, 计算机学会CCF推荐A类会议】

[C10] Meng Pang, Houwei Xu, Zheng Huang, Yintao Zhou, Wei Huang, Binghui Wang. Breaking data silos in Parkinson’s disease diagnosis: An adaptive federated learning approach for privacy-preserving facial expression analysis. Annual AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, USA, February 25-March 4, 2025.  【人工智能顶级会议, 计算机学会CCF推荐A类会议】

[C9] Jiate Li, Meng Pang* (通讯作者), Yun Dong, Jinyuan Jia, Binghui Wang*. Graph neural network explanations are fragile. International Conference on Machine Learning (ICML), Vienna, Austria, July 21-27, 2024. 【机器学习顶级会议，计算机学会CCF推荐A类会议】

[C8] Meng Pang, Binghui Wang, Nanrun Zhou, Yintao Zhou, Wei Huang. Reconstructing prototype from contaminated face with variations across heterogeneous domains. IEEE International Conference on Multimedia and Expo (ICME), Niagra Falls, Canada, July 15-19, 2024.   【多媒体图像处理旗舰会议，计算机学会CCF推荐B类会议】

[C7] Yintao Zhou, Meng Pang* (通讯作者), Wei Huang, Binghui Wang. Early Diagnosing Parkinson's disease via a deep learning model based on augmented facial expression data. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024: 1621–1625.   【信号处理顶级会议，计算机学会CCF推荐B类会议】

[C6] Yunpeng Wang, Meng Pang*(通讯作者), Shengbo Chen, Hong Rao. Consistency-GAN: Training gans with consistency model. Annual AAAI Conference on Artificial Intelligence (AAAI), 2024, 38(14): 15743–15751.  【人工智能顶级会议, 计算机学会CCF推荐A类会议】

[C5] Binghui Wang, Meng Pang*(通讯作者), Yun Dong. Turning strengths into weaknesses: A certified robustness inspired attack framework against graph neural networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023: 16394–16403. 【计算机视觉顶级会议, 计算机学会CCF推荐A类会议】

[C4] Binghui Wang, Ang Li, Meng Pang, Hai Li, Yiran Chen. GraphFL: A federated learning framework for semi-supervised node classification on graphs. IEEE International Conference on Data Mining (ICDM), 2022: 498-507.       【数据挖掘顶级会议, 计算机学会CCF推荐B类会议】  

[C3] Meng Pang, Binghui Wang, Shengbo Chen, Yiu-ming Cheung, Rong Zou, Wei Huang. Cross-domain prototype learning from contaminated faces via disentangling latent factors. ACM International Conference on Information & Knowledge Management (CIKM), 2022: 4369-4373.   【数据挖掘顶级会议, 计算机学会CCF推荐B类会议】  

[C2] Meng Pang, Binghui Wang, Mang Ye, Yiran Chen, Bihan Wen. Disentangling prototype and variation for single sample face recognition. IEEE International Conference on Multimedia and Expo (ICME), 2021: 1–6, Shenzhen, China, July 5-9, 2021.  【多媒体图像处理旗舰会议，计算机学会CCF推荐B类会议】

[C1] Meng Pang, Yiu-ming Cheung, Qiquan Shi, Mengke Li. Iterative dynamic generic learning for single sample face recognition with a contaminated gallery. IEEE International Conference on Multimedia and Expo (ICME), 2020: 1–6, London, UK, July 6-10, 2020. 【多媒体图像处理旗舰会议，计算机学会CCF推荐B类会议】

媒体新闻

[4] 我校数学与计算机学院教师庞孟的研究成果被CCF A类会议ICML 2024录用

[3] 我院教师庞孟的系列研究成果被人工智能与神经网络领域的顶级期刊和信号处理领域的顶级会议录用

[2] 我校研究生导师团队论文被知名学术会议ICASSP2024录用

[1] 软件学院硕士研究生王云朋发表人工智能顶级会议AAAI-24论文