所属学院：

计算机学院

导师类别：

博士生导师、硕士生导师

科研方向：

多模态人工智能，多模态大模型，机器学习，计算机图形学

联系方式：

minmeng@gdut.edu.cn

硕士招生学院：

计算机学院

人才称号：

广东省“珠江人才计划”高层次人才

个人简述

广东省“珠江人才计划”高层次人才，“青年百人计划”A+类，广东工业大学“2022年度优秀研究生导师”“2021年度优秀研究生导师”、“2020年度优秀研究生导师”。主持国家自然科学基金面上项目/青年项目、广东省自然科学基金项目、广东省教育厅青年创新人才项目，作为技术指导参与两项新加坡教育部研发转化与创新基金项目。在国际重要学术期刊和会议上发表论文50余篇，单篇最高引用100余次，其中以第一或通讯作者在中科院1区和CCF A类IEEE会刊IEEE Transactions on Image Processing，IEEE Transactions on Cybernetics，IEEE Transactions on Multimedia，IEEE Transactions on Circuits and   Systems for Video Technology上发表论文10余篇。

学术兼职

中国计算机学会 计算机辅助设计与图形学专委会 委员

中国图象图形学会 智能图形专委会 委员

中国图象图形学会 三维视觉专委会 委员

《IEEE Trans. on Image Process.》,《IEEE Trans. on Neural Netw. and Learning Syst.》,《IEEE Trans. on Multimedia》,《IEEE Trans. on   Cybern.》等国际期刊审稿人

教育背景

2006/9-2011/6, 浙江大学，应用数学，博士

2002/9-2006/6，郑州大学，信息与计算科学，学士

工作经历

2024/1-至今，广东工业大学，计算机学院，教授

2016/6-2023/12，广东工业大学，计算机学院，副教授

2013/9-2016/6，新加坡理工学院，机械与航天工程学系，研究员

2011/9-2013/8，新加坡南洋理工大学，计算机科学与工程学院，博士后

主要论文

[1] M. Lan, M. Meng(通信作者), J. Yu, J. Wu. Learning to Discover Knowledge: A   Weakly-Supervised Partial Domain Adaptation Approach. IEEE Transactions on Image Processing, 2024, vol. 33, pp. 4090-4103.   (CCF A, 中科院1区)

[2] M. Meng, H. Wang, J. Yu, H. Chen and J. Wu. Asymmetric   Supervised Consistent and Specific Hashing for Cross-Modal Retrieval. IEEE Transactions on Image Processing,   2021, vol. 30, pp. 986-1000. (CCF A, 中科院1区)

[3] M. Meng, M. Lan, J. Yu, J. Wu and D. Tao. Constrained   Discriminative Projection Learning for Image Classification. IEEE Transactions on Image Processing,   2020, vol. 29, pp. 186-198. (CCF A, 中科院1区)

[4] M. Meng and J. Yu. Zero-Shot Learning via Robust Latent   Representation and Manifold Regularization. IEEE Transactions on Image Processing, 2019, 28(4), P1824-1836. (CCF   A, 中科院1区)

[5] M. Meng, W. Chen, J. Liu, J. Yu and J. Wu. CoDi: Contrastive Disentanglement   Generative Adversarial Networks for Zero-Shot Sketch-Based 3D Shape Retrieval.   IEEE Circuits and Systems for Video   Technology, 2025, 35(2), pp. 1910-1920. (CCF B, 中科院1区)

[6] M. Meng, J. Sun, J. Liu, J. Yu and J. Wu. Semantic   Disentanglement Adversarial Hashing for Cross-Modal Retrieval. IEEE Circuits and Systems for Video   Technology, 2024, 34(3), pp. 1914-1926. (CCF B, 中科院1区)

[7] M. Meng, M. Lan, J. Yu and J. Wu. Multiview Consensus Structure   Discovery. IEEE Transactions on   Cybernetics, 2022, 52(5), pp. 3469-3482. (CCF B, 中科院1区)

[8] M. Meng, M. Lan, J. Yu and J. Wu. Dual-Level Adaptive and   Discriminative Knowledge Transfer for Cross-Domain Recognition. IEEE Transactions on Multimedia, 2023,   25, pp. 2266-2279. (CCF B, 中科院1区)

[9] M. Meng, Z. Wu, T. Liang, J. Yu and J. Wu. Exploring   Fine-Grained Cluster Structure Knowledge for Unsupervised Domain Adaptation. IEEE Transactions on Circuits and Systems   for Video Technology, Aug., 2022, 32(8), pp. 5481-5494. (CCF B, 中科院1区)

[10] M. Lan, M. Meng(通讯作者), J. Yu and J. Wu.   Generalized Multi-view Collaborative Subspace Clustering. IEEE Transactions on Circuits and Systems   for Video Technology, Aug., 2022, 32(8), pp. 5481-5494. (CCF B, 中科院1区)

[11] M. Meng, M. Lan, J. Yu and J. Wu. Coupled Knowledge Transfer for   Visual Data Recognition. IEEE   Transactions on Circuits and Systems for Video Technology, 2021, 31(5),   P1176-1789. (CCF B, 中科院1区)

[12] J. Xu, M. Meng J. Liu and J. Wu. Deep Multi-view   Clustering with Diverse and Discriminative Feature Learning. Pattern Recognition, 2025, 161, 111322-280.   (CCF B, 中科院1区)

[13] M. Meng, Q. Chen and J. Wu. Structure Preservation Adversarial   Network for Visual Domain Adaptation. Information   Sciences, Nov. 2021, 579, pp. 266-280. (CCF B, 中科院1区)

[14] M. Meng, Jie Wei and J. Wu. Learning Multi-Part Attention Neural   Network for Zero-shot Classification. IEEE   Transactions on Cognitive and Developmental Systems, Jun., 2022, 16(2),   pp. 414-423. (中科院2区)

[15] Z. Wu, M. Meng(通讯作者), T. Liang and J. Wu. Hierarchical Triple-Level Alignment for   Multiple Source and Target Domain Adaptation. Applied Intelligence, Feb., 2023, vol. 53, pp. 3766-3782. (CCF C,   中科院2区)

[16] J. Guan, M. Meng(通讯作者), T. Liang, J. Liu and J. Wu. Dual-level Contrastive learning   Network for Generalized Zero-Shot Learning. The Visual Computer, 2022, 38, pp. 3087-3095. (CCF C, 中科院3区)

[17] M. Meng, X. Zhan and J. Wu. Joint Discriminative Attributes and   Similarity Embeddings for Zero-shot Recognition. Neurocomputing, 2020, vol. 399, pp. 117-128. (CCF C, 中科院2区)

[18] M. Meng, Y. Liu and J. Wu. Robust Discriminant Projection via   Joint Margin and Locality Structure Preservation. Neural Processing Letters, 2021, vol. 53, pp. 959-982. (CCF C, 中科院3区)

[19] Z. Wu, M. Meng(通讯作者) and J. Wu. Visual   Sentiment Prediction with Attribute Augmentation and Multi-Attention   Mechanism. Neural Processing Letters,   2020, vol. 51, pp. 2403-2416. (CCF C, 中科院3区)

[20] J. He, M. Meng(通讯作者), J. Liu and J. Wu. Multi-scale Similarity Information Fusion   Hashing for Unsupervised Cross-Modal Retrieval. Computer Graphics International (CGI), Jul, 2024. (CCF C)

[21] T. Liang, M. Meng(通讯作者), M. Lan, J. Yu and J. Wu. Group Correspondence: A Statistical   Perspective for Incomplete Multi-View Clustering Augmentation. IEEE International Conference on   Multimedia and Expo (ICME), Jul, 2022. (CCF B)

[22] Z. Wu, T. Liang, M. Meng(通讯作者), J. Liu, J. Yu and J. Wu. Triple Disentangling Network for   Unsupervised Domain Adaptation. IEEE International   Conference on Multimedia and Expo (ICME), Jul, 2022. (CCF B)

[23] H. Lin, M. Meng(通讯作者) and J. Wu. Online Robust Specific and Consistent Hashing. IEEE International Conference on   Multimedia and Expo (ICME), Jul, 2022. (CCF B)

[24] R. Yang, M. Meng(通讯作者), J. Yu and J. Wu. Learning Controlled Semantic Embedding for   Cross-Modal Retrieval. IEEE   International Conference on Multimedia and Expo (ICME), Jul, 2021, P1-7.   (CCF B)

[25] H. Wang, J. Wu, T.   Liang and M. Meng(通讯作者). Stack-VAE Network for   Zero-Shot Learning. International   Conference on Neural Information Processing (ICONIP), 2021, pp. 250-261.   (CCF C)

[26] H. Wang, M. Meng(通讯作者), H. Chen and J. Wu. Supervised Consistent and Specific   Hashing. IEEE International Conference   on Multimedia and Expo (ICME), Aug, 2019, P1822-1827. (CCF B)

[27] H. Wang, H. Chen, M. Meng(通讯作者) and J. Wu. Robust Multi-view Hashing for Cross-Modal   Retrieval. IEEE International   Conference on Multimedia and Expo (ICME), Aug, 2019, P1012-1017. (CCF B)

[28] M. Meng, X. Zhan. Zero-Shot Learning via Low Rank Representation   Based Manifold Regularization. IEEE   Signal Processing Letters, 2018, 25(9), P1379-1383. (CCF C, 中科院3区)

[29] M. Meng, Y.J. Chua, E. Wouterson, C.P.K. Ong. Ultrasonic signal   classification and imaging system for composite materials via deep   convolutional neural networks. Neurocomputing,   2017, 257:128-135. (CCF C, 中科院2区)

[30] M. Meng, and Y. He. Consistent quadrangulation for shape   collections via feature line co-extraction. 2016, Computer-Aided Design, 70, P78-88. (CCF B, 中科院2区)

[31] M. Meng, J. Xia, J. Luo, and Y. He. Unsupervised co-segmentation   for 3D shapes using iterative multi-label optimization. 2013, Computer-Aided Design, 45(2),   P312-320. (CCF B, 中科院2区)

[32] L. Fan, M. Meng, L. Liu. Sketch-based mesh   cutting: a comparative study. 2012, Graphical   Models, 74(6), P292-301. (CCF B, 中科院4区)

[33] M. Meng, L. Fan, L. Liu. A comparative evaluation of   foreground/background sketch-based mesh segmentation algorithms. 2011, Computer & Graphics, 35(3),   P650-660. (CCF C, 中科院3区)

[34] M. Meng, L. Fan, L. Liu. iCutter: a direct cutout-tool for 3D   shapes. 2011, Computer Animation &   Virtual Worlds, 22(4), P335-342. (CCF C, 中科院4区)

科研项目

国家自然科学基金面上项目，面向分层标签数据的跨媒体检索关键技术研究，主持

国家自然科学基金青年项目，基于低秩表示的高精度跨模态形状检索研究，主持

广东省自然科学基金项目，跨域迁移学习关键技术研究，主持

广东省自然科学基金项目，视觉问答关键技术研究，主持

教学活动

本科生课程：数据挖掘、软件工程

团队主页

高性能计算与数据科学实验室 http://hpcds.gdut.edu.cn/