招生信息
MMRC团队现诚聘优秀人才
新闻
齐壮论文"Clustering-based curriculum construction forsample-balanced Federated learning"
刘进兴论文"Prompt Learning with Cross-Modal Feature Alignment for Visual Domain Adaptation"
孙玮琳论文"Sequential Fusion of Multi-view Video Frames for 3D Scene Generation"
吴杭论文"VAFA: a Visually-Aware Food Analysis System for Socially-Engaged Diet Management"
王雨晴论文"Causal lnference with Sample Balancing for Out-Of-Distribution Detection in Visual Classification"
个人简介
孟雷,教授、博导,2020年起就职于山东大学软件学院。2010年于山东大学获得工学学士学位,2015年于新加坡南洋理工大学(NTU)计算机科学与工程学院获得博士学位,导师Ah-Hwee Tan教授。2015年就职于Joint NTU-UBC Research Center of Excellence in Active Living for the Elderly (LILY),任Research Fellow,合作导师为南洋理工大学苗春燕教授和英属哥伦比亚大学Cyril Leung教授。2018年就职于NUS-Tsinghua-Southampton Centre for Extreme Search (NExT++),任Senior Research Fellow,合作导师为新加坡国立大学Tat-Seng Chua教授。
围绕互联网大数据驱动下的多媒体计算和数据挖掘等科学问题,长期从事多媒体知识挖掘与内容表征的机器学习理论与技术研究。组建多媒体挖掘推理与生成(MMRC)实验室,入选济南市“新高校20条”引进创新团队计划。面向健康大数据分析开展智慧家庭关键技术研究,自主构建千万级饮食健康大数据,研制适老化搜索引擎、非打扰风险研判、健康饮食管理等应用系统并得到推广应用;面向国家市域社会治理现代化战略需求,聚焦多尺度社会治理场景的数字化感知和智能化决策问题,在多媒体理解、跨模态推理、数字孪生等方向开展先导性创新研究。主要课题研究包括(1)基于自适应谐振原理(ART)的自组织聚类算法;(2)跨模态增强的视觉表征算法;(3)面向不平衡数据的深度学习方法;(4)结合跨模态推理的因果特征学习方法;(5)基于视频数据的3D场景生成方法。
在Springer出版英文专著一部“Adaptive Resonance Theory in Social Media Data Clustering”,在TKDE、TNNLS、TMM、MM、AAAI等人工智能和多媒体领域期刊和会议发表学术论文六十余篇,申请或获得国际、国内发明专利八项。入选山东省泰山学者青年专家、山东省优秀青年科学基金项目(海外)、山东大学齐鲁青年学者(第一层次)等人才计划。获得2021年度中国工程院中国工程前沿杰出青年学者、ACM济南分会学术新星、山东省人工智能优青等荣誉称号,入选国家科技专家库、中国工程院 CAFOE专家库、山东省技术研发专家库及全国研究生教育评估监测专家库、获得2024年度中国人工智能学会吴文俊人工智能科学技术奖科技进步二等奖。主持国家重点研发计划课题、国家自然科学基金委青年科学基金及CCF-腾讯犀牛鸟基金等科研项目5项,累计经费500余万。担任中科院SCI一区期刊《Applied Soft Computing》的副主编(Associate Editor)、中国计算机学会(CCF)多媒体专委会执行委员、中国计算机学会青年计算机科技论坛(CCF YOCSEF)济南分论坛2023-2024届主席、山东省人工智能学会理事。长期担任计算机学报、计算机科学、TNNLS等期刊的审稿人,以及MM、AAAI、IJCAI等会议的(高级)程序/技术委员会成员。
团队简介
多媒体挖掘、推理与生成(MMRC)实验室依托教育部数字媒体技术工程研究中心,围绕国家市域社会治理现代化战略需求,聚焦多尺度社会治理场景的数字化感知和智能化决策问题,在多媒体理解、跨模态推理、三维场景生成、数字孪生等方向开展先导性创新研究。现有成员13人,包括教授2人、副教授/研究员4人、科研岗1人、博士研究生4人、硕士研究生15人。自团队创建先后主持国家重点研发计划2项、国家自然科学基金项目2项,山东省自然科学基金重点项目1项。 MMRC团队人员
教育背景
2010年8月30日 – 2015年2月11日,博士, 计算机科学与工程专业,南洋理工大学,新加坡。
2006年9月7日 – 2010年6月30日,本科, 计算机科学与技术专业,山东大学,中国。
工作经历
2020年10月13日至今:教授, 山东大学,中国。
2018年12月3日至2020年9月23日:高级研究员, 新加坡国立大学—清华—南安普顿下一代搜索技术联合研究中心(NExT++),新加坡国立大学,新加坡。
2018年5月——2018年7月: 访问学者, UBTECH悉尼人工智能中心,悉尼大学,悉尼,澳大利亚。
2015年1月15日—2018年12月1日: 研究员, 百合卓越联合研究中心(LILY),南洋理工大学,新加坡。
2014年8月–2015年1月: 助理研究员, 新加坡国立大学—清华下一代搜索技术联合研究中心(NExT),新加坡国立大学,新加坡。
主讲课程
主讲教师 – 深度学习及应用 (sd03032640), 第二学期, 2023-2024, 软件学院,山东大学,中国。
主讲教师 – 多媒体计算 (sd03032560), 第一学期, 2023-2024, 软件学院,山东大学,中国。
主讲教师 – 多媒体计算 (sd03032560), 第一学期, 2022-2023, 软件学院,山东大学,中国。
主讲教师 – 深度学习及应用 (sd03032640), 第二学期, 2022-2023, 软件学院,山东大学,中国。
主讲教师 – 多媒体计算 (sd03032560), 第一学期, 2021-2022, 软件学院,山东大学,中国。
主讲教师 – 机器学习课程设计 (sd03031560), 第二学期, 2021-2022, 软件学院,山东大学,中国。
主讲教师 – 机器学习课程设计 (sd03031560), 第二学期, 2020-2021, 软件学院,山东大学,中国。
学术职务
学术协会任职
会议委员会会员
学术活动
会议报告
重要职务
获奖与荣誉
山东大学齐鲁青年学者(第一层次),2020
ACM济南分会新星奖,2021
论著
专著
Lei Meng, Ah-Hwee Tan, and Donald C. Wunsch II, “Adaptive Resonance Theory in Social Media Data Clustering – Roles, Methodologies, and Applications,” Advanced Information and Knowledge Processing Series, SpringerNature, May 29, 2019. ISBN:978-3-030-02985-2.
教材
代表性期刊论文 (*通讯作者;#共同一作)
张慕楠, 曲晓峥,孟雷,《傲慢与偏见:英国主流媒体“一带一路”报道话语分析》,新传播,2024.(PDF文件)
Xiangxian Li, Yuze Zheng, Haokai Ma, Zhuang Qi, Lei Meng*, Xiangxu Meng,“Cross-modal Learning Using Privileged Information for Long-tailed Image Classification”Computational Visual Media journal (CVM),Shenzhen,China,April 6-8,2024.(PDF文件)
Lei Meng, Zhuang Qi*, Lei Wu, Xiaoyu Du, Zhaochuan Li, Lizhen Cui, Xiangxu Meng, "Improving Global Generalization and Local Personalization for Federated Learning", IEEE Transactions on Neural Networks and Learning Systems(TNNLS),2024.(PDF文件)https://github.com/qizhuang-qz/TNNLS
Xu Chen, Lei Wu*, Yongliang Su, Lei Meng, Xiangxu Meng, "Font transformer for few-shot font generation", Computer Vision and Image Understanding,245:104043,2024.(PDF文件)
Pei Dong, Lei Wu*, Ruichen Li, Xiangxu Meng, Lei Meng, "Text to image synthesis with multi-granularity feature aware enhancement Generative Adversarial Networks", Computer Vision and Image Understanding,245:104042,2024.(PDF文件)
Haokai Ma, Ruobing Xie, Lei Meng*, Xin Chen, Xu Zhang, Leyu Lin, Jie Zhou, "Triple Sequence Learning for Cross-domain Recommendation", ACM Transactions on Information Systems (TOIS),42(4):1-29,2024.(PDF文件) https://dl.acm.org/doi/10.1145/3638351
Weilin Sun, Manyi Li, Peng Li, Xiao Cao, Xiangxu Meng, Lei Meng*, "Sequential Selection and Calibration of Video Frames for 3D Outdoor Scene Reconstruction", CAAI Transactions on Intelligence Technology (CAAI Trans),9(6):1500-1514,2024.(PDF文件)
李象贤,郑裕泽,马浩凯,齐壮,孟祥旭,孟雷,“基于跨模态特权信息增强的图像分类方法 ”,软件学报,2024:1-17.(PDF文件)
Qing-Ling Guan, Yuze Zheng, Lei Meng*, Li-Quan Dong Qun Hao, "Improving the Generalization of Visual Classification Models Across IoT Cameras via Cross-Modal Inference and Fusion", IEEE Internet of Things Journal(IoT),10(18):15835-15846 ,2023.(PDF文件)
Yuqing Wang, Xiangxian Li, Yannan Liu, Xiao Cao, Xiangxu Meng, Lei Meng*.“Causal lnference for Out-Of-Distribution Recognition via Sample Balancing”, CAAI Transactions on Intelligence Technology(CAAI Trans), 9(5):1172-1184,2023.(PDF文件)
Pei Dong, Lei Wu*, Lei Meng*, Xiangxu Meng, “HR-PrGAN: High-Resolution Story Visualization with Progressive Generative Adversarial Networks,” Information Sciences, 614:548-562,2022.(PDF文件)
Wenya Guo, Ying Zhang*, Xiangrui Cai, Lei Meng, Jufeng Yang, Xiaojie Yuan, “LD-MAN: Layout-Driven Multimodal Attention Network for Online News Sentiment Recognition,” IEEE Transactions on Multimedia, 23:1785-1798,2020.(PDF文件)
Lei Meng*, Ah-Hwee Tan, Chunyan Miao, “Salience-Aware Adaptive Resonance Theory for Large-Scale Sparse Data Clustering,” Neural Networks,vol.120,pp.143-157,Sept.21,2019.(PDF文件)
Ah-Hwee Tan*, Budhitama Subagdja, Di Wang, Lei Meng, “Self-Organizing Neural Networks for Universal Learning and Multimodal Memory Encoding,” Neural Networks,vol.120,pp.58-73,Sept.2,2019.(PDF文件)
Lei Meng*, Chunyan Miao, and Cyril Leung, “Towards Online and Personalized Daily Activity Recognition, Habit Modeling, and Anomaly Detection for the Solitary Elderly Through Unobtrusive Sensing,” Multimedia Tools and Applications, vol.76,no.8,pp. 10779-10799,2017.(PDF文件)
Lei Meng, Ah-Hwee Tan and Donald C. Wunsch II, “Adaptive Scaling of Cluster Boundaries for Large-Scale Social Media Data Clustering,”IEEE Transactions on Neural Networks and Learning Systems (TNNLS),vol.27,no.12,pp.2656-2669,Dec.1,2016.(PDF文件)
Lei Meng, Ah-Hwee Tan and Dong Xu, “Semi-Supervised Heterogeneous Fusion for Multimedia Data Co-clustering,”IEEE Transactions on Knowledge and Data Engineering (TKDE),vol.26,no.9,pp.2293-2306,2014.(PDF文件)
代表性会议论文
Zhuang Qi, Ying-Peng Tang, Lei Meng*, Han Yu, Xiaoxiao Li , Xiangxu Meng. "Class-wise Balancing Data Replay for Federated Class-Incremental Learning." The Thirty-ninth Annual Conference on Neural Information Processing Systems 2025 (NeurIPS'25), accepted, 2025.(PDF文件)https://github.com/qizhuang-qz/FedCBDR
Zhuang Qi, Yu Pan, Lei Meng*, Sijin Zhou, Han Yu, Xiaoxiao Li, Xiangxu Meng. "Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning." The Thirty-ninth Annual Conference on Neural Information Processing Systems 2025 (NeurIPS'25), accepted, 2025.(PDF文件)https://github.com/qizhuang-qz/GPR-NIAM
Zhuang Qi, Sijin Zhou, Lei Meng∗, Han Hu, Han Yu, and Xiangxu Meng.“Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization.” International Joint Conference on Artificial Intelligence, 2025 (IJCAI'25), Guangzhou, China,August 16-August 22 , 2025(PDF文件)https://github.com/qizhuang-qz/FedDDL
Xiaoshuo Yan, Zhaochuan Li , Lei Meng*, Zhuang Qi, Wei Wu, Zixuan Li, Xiangxu Meng.“Empowering Vision Transformers with Multi-Scale Causal Intervention for Long-Tailed Image Classification.” International Joint Conference on Artificial Intelligence, 2025 (IJCAI'25), Guangzhou, China,August 16-August 22 , 2025(PDF文件)https://github.com/stu-xsy/TSCNet
Zixuan Li , Lei Meng∗ , Guoqing Chao , Wei Wu , Xiaoshuo Yan , Yimeng Yang , Zhuang Qi , Xiangxu Meng. “Semantic-Space-Intervened Diffusive Alignment for Visual Classification.” International Joint Conference on Artificial Intelligence (IJCAI'25) , Guangzhou, China,August 16-August 22 , 2025.(PDF文件)https://github.com/bigwahaha/SeDA
Anran Yu#, Wei Feng#, Xiang Li, Lei Meng*, Wei Wu*, Yaochen Zhang , Xiangxu Meng. “LLM-Enabled Style and Content Regularization for Personalized Text-to-Image Generation.” International Joint Conference on Neural Networks 2025 (IJCNN'25), Rome, Italy,June 30 - July 5, 2025.(PDF文件)ttps://github.com/ffww11/LLM-Enabled-Style-and-Content-Regularization-for-Personalized-Text-to-Image-Generation
Xiaozheng Qu, Zhaochuan Li, Zhuang Qi, Xiang Li, Haibei Huang, Lei Meng*, Xiangxu Meng. “Towards Initialization-Agnostic Clustering with Iterative Adaptive Resonance Theory.” IEEE International Joint Conference on Neural Networks 2025 (IJCNN'25),Rome, Italy,June 30 - July 5, 2025.(PDF文件)https://github.com/xiaozhengqu/IR-ART
Zhuang Qi#, Runhui Zhang#, Lei Meng*, Wei Wu, Yachong Zhang, Xiangxu Meng. “Global Intervention and Distillation for Federated Out-of-Distribution Generalization.” IEEE International Conference on Multimedia and Expo 2025 (ICME'25), Nantes, France,June 30 - July 4 , 2025.(PDF文件)https://github.com/qizhuang-qz/FedGID
Weilin Sun, Xinran Li, Manyi Li*, Kai Xu*, Xiangxu Meng, Lei Meng*. “Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model.” AAAI Conference on Artificial Intelligence, Philadelphia, February 27–March 4 , 2025.(PDF文件)https://github.com/SunWeiLin-Lynne/Hierarchically-Structured-Open-Vocabulary-Indoor-Scene-Synthesis
Yimeng Yang, Haokai Ma, Lei Meng*, Shuo Xu, Ruobing Xie, Xiangxu Meng. “Curriculum Conditioned Diffusion for Multimodal Recommendation.” AAAI Conference on Artificial Intelligence, Philadelphia, February25–March4,2025.(PDF文件)https://github.com/Yimeng-yang/CCDRec
Lei Meng, Xiangxian Li, Xiaoshuo Yan*, HaoKai Ma,Zhuang Qi,Wei Wu,Xiangxu Meng. “Causal Inference over Visual-Semantic-Aligned Graph for Image Classification.” AAAI Conference on Artificial Intelligence,February27–March2,2025.(PDF文件)https://github.com/stu-xsy/VSCNet
Zhuang Qi, Lei Meng*, Zhaochuan Li, Han Hu, Xiangxu Meng. “Cross-Silo Feature Space Alignment for Federated Learning on Clients with Imbalanced Data.” AAAI Conference on Artificial Intelligence,February27–March2,2025.(PDF文件)https://github.com/qizhuang-qz/FedFSA
Chang Shuo Wang, Lei Wu*, Mingzhe Yu, Xiang Li, Lei Meng*,Xiangxu Meng. “InstantAS: Minimum Coverage Sampling for Arbitrary-Size Image Generation”, ACM Multimedia 2024, October28–November1,2024,Melbourne,Australia.(PDF文件)https://github.com/BanishedKnight/InstantAS
Yuqing Wang, Lei Meng*, Haokai Ma, Yuging Wang, Haibei Huang, Xiangxu Meng. "Modeling Event-level Causal Representation for Video Classification", ACM Multimedia 2024, October28–November1,2024,Melbourne,Australia,Oral(174/1149)(PDF文件)https://github.com/wyqcrystal/ECRL
Yuze Zheng, Zixuan Li, Xiangxian Li, Jinxing Liu, Yuging Wang, Xiangxu Meng, Lei Meng*. "Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment", International Conference on Artificial Neural Networks (ICANN '24),Lugano, Switzerland,September 17 - September 20,2024.(PDF文件)
Xiang Li, Lei Meng, Lei Wu*, Manyi Li, Xiangxu Meng. "DreamFont3D: Personalized Text-to-3D Artistic Font Generation", The Special Interest Group on Computer Graphics and Interactive Techniques Conference (SIGGRAPH '24), Denver, Colorado, USA, July 28 - August 1,2024.(PDF文件)
Mingzhe Yu, Yunshan Ma, Lei Wu*, Kai Cheng, Xue Li, Lei Meng, Tat-Seng Chua, "Smart Fitting Room: A One-stop Framework for Matching-aware Virtual Try-On", Proceedings of the 2024 International Conference on Multimedia Retrieval, 184-192, 2024.(PDF文件)
Haokai Ma, Yimeng Yang, Lei Meng*, Ruobing Xie, Xiangxu Meng."Multimodal Conditioned Diffusion Model for Recommendation", Proceedings of the ACM on Web Conference 2024, 1733-1740, 2024.(PDF文件)
Haokai Ma, Ruobing Xie*, Lei Meng*, Yimeng Yang, Xingwu Sun and Zhanhui Kang, "SeeDRec: Sememe-based Diffusion for Sequential Recommendation", The 33rd International Joint Conference on Artificial Intelligence (IJCAI '24),Jeju Island, South Korea, pp.2270-2278, 2024.(PDF文件)
Zhuang Qi, Weihao He, Xiangxu Meng, Lei Meng*. “Attentive Modeling and Distillation for Out-of-Distribution Generalization of Federated Learning.” IEEE International Conference on Multimedia and Expo,10:648-653.Niagra Falls,Canada,7.15 - 7.19,2024.(PDF文件)
Haokai Ma, Ruobing Xie, Lei Meng*, Xin Chen, Xu Zhang, Leyu Lin and Zhanhui Kang, “Plug-in Diffusion Model for Sequential Recommendation”, 38th AAAI Conference on Artificial Intelligence (AAAI 2024),2024,38(8):8886-8894.Vancouver,British Columbia,2.20-2.27,2024(PDF文件)
Zitan Chen, Zhuang Qi, Xiangxian Li, Yuqing Wang, Lei Meng*,Xiangxu Meng. “Class-aware Convolution and Attentive Aggregation for Image Classification”,ACM MM Asia,1-7.Tainan Taiwan,12.06-12.08,2023.(PDF文件)
Chang Shuo Wang, Lei Wu*, XiaoLe Liu, Xiang Li, Lei Meng*,Xiangxu Meng. “Anything to Glyph: Artistic Font Synthesis via Text-to-Image Diffusion Model”,SIGGRAPH Asia (SA Conference Papers'23), December 12–15, 2023, Sydney, NSW, Australia. ACM, New York,NY, USA.(PDF文件)
Zitan Chen, Zhuang Qi, Xiao Cao, Xiangxian Li, Xiangxu Meng, Lei Meng*.“Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning”, ACM International Conference on Multimedia, Ottawa, October 29-November 3,2023.(PDF文件)
Zhuang Qi, Lei Meng*, Zitan Chen, Han Hu, Hui Lin,Xiangxu Meng. “Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Data.” ACM International Conference on Multimedia, Ottawa, October 29-November 3, 2023.(PDF文件)
Haokai Ma, Ruobing Xie, Lei Meng*, Xin Chen, Xu Zhang, Leyu Lin, Jie Zhou, “Exploring False Hard Negative Sample in Cross-Domain Recommendation”,ACM Conference on Recommender Systems (RecSys ’23), pp. 502–514, Singapore, September 18–22, 2023.(PDF文件)https://github.com/hulkima/RealHNS
Ran Wang, Zhuang Qi, Xiangxu Meng, Lei Meng*, “Learning to Fuse Residual and Conditional Information for Video Compression and Reconstruction”, Image and Graphics : 12th International Conference, ICIG 2023,pp.360-372, Nanjing, China, September 22–24, 2023.(PDF文件)
Jingyu Li, Haokai Ma, Xiangxian Li, Zhuang Qi, Xiangxu Meng, Lei Meng*, “Unsupervised Segmentation of Haze Regions as Hard Attention for Haze Classification”, International Conference on Image and Graphics, ICIG 2023,pp.346-359, Nanjing, China, September 22–24, 2023.(PDF文件)
Xiang Li, Lei Wu*, Changshuo Wang, Lei Meng*, Xiangxu Meng,"Compositional Zero-Shot Artistic Font Synthesis", International Joint Conferences on Artificial Intelligence(IJCAI), pp 1098-1106, Macao SAR, China, August 19-25, 2023.(PDF文件)https://moonlight03.github.io/CAFS-GAN/
Changshuo Wang, Lei Wu*, Xu Chen, Xiang Li, Lei Meng*, Xiangxu Meng,.“Letter Embedding Guidance Diffusion Model for Scene Text Editing”, IEEE International Conference on Multimedia and Expo (ICME), Brisbane, Australia July 10-14, 2023.(PDF文件)
Haokai Ma, Zhuang Qi, Xinxin Dong, Xiangxian Li, Yuze Zheng, Xiangxu Meng, Lei Meng*, “Cross-Modal Content Inference and Feature Enrichment for Cold-Start Recommendation”, International Joint Conference on Neural Networks, pp. 1-8, Gold Coast, Australia, June 18-23, 2023.(PDF文件)
Yuqing Wang, Zhuang Qi, Xiangxian Li, Jinxing Liu, Xiangxu Meng, Lei Meng*, “Multi-Channel Attentive Weighting of Visual Frames for Multimodal Video Classification”, IJCNN International Joint Conference on Neural Networks, pp. 1-8, Gold Coast, Australia, June 18-23, 2023.(PDF文件)
Tianhan Liu, Zhuang Qi, Zitan Chen, Xiangxu Meng, Lei Meng*, “Cross-Training with Prototypical Distillation for improving the generalization of Federated Learning”, International Conference on Multimedia and Expo 2023 (ICME'2023),pp. 648-653, Brisbane, Australia, July 10-14, 2023. (PDF文件)
Xiangxian Li, Yuze Zheng, Haokai Ma, Zhuang Qi, Lei Meng*, Xiangxu Meng,“Cross-modal Learning Using Privileged Information for Long-tailed Image Classification,”Computational Visual Media Conference (CVM), Shenzhen, China, April 6-8, 2023.(PDF文件)
Yuqing Wang, Xiangxian Li, Zhuang Qi, Jingyu Li, Xuelong Li, Xiangxu Meng, Lei Meng*, “MetaCausal Feature Learning for Out-of-Distribution Generalization”,European Conference on Computer Vision, pp. 530-545, Tel Aviv, Israel, October 23–27, 2022.(PDF文件)
Jinxing Liu , Junjin Xiao , Haokai Ma , Xiangxian Li , Zhuang Qi , Xiangxu Meng , and Lei Meng* , “Prompt Learning with Cross-Modal Feature Alignment for Visual Domain Adaptation”,CAAI International Conference on Artificial Intelligence(CAAI) ,pp 416-428, Beijing, China, August 27–28, 2022.(PDF文件)
Zhuang Qi,Yuqing Wang, Zitan Chen, Ran Wang, Xiangxu Meng, and Lei Meng*, " Clustering-based curriculum construction forsample-balanced Federated learning," CAAI International Conference on Artificial Intelligence(CAAI) ,pp 155-166, Beijing, China, August 27–28, 2022.(PDF文件)
Hang Wu, Xi Chen, Xuelong Li, Haokai Ma, Yuze Zheng, Xiangxian Li, Xiangxu Meng, Lei Meng*. “VAFA: a Visually-Aware Food Analysis System for Socially-Engaged Diet Management”, CAAI International Conference on Artificial Intelligence(CAAI) ,pp 554-558, Beijing, China, August 27–28, 2022.(PDF文件)
Yuqing Wang, Xiangxian Li, Haokai Ma, Zhuang Qi, Xiangxu Meng, Lei Meng*, “Causal lnference with Sample Balancing for Out-Of-Distribution Detection in Visual Classification”, CAAI International Conference on Artificial Intelligence(CAAI) ,pp 572-583, Beijing, China, August 27–28, 2022.(PDF文件)
Weilin Sun, Xiangxian Li, Manyi Li, Yuqing Wang, Yuze Zheng, Xiangxu Meng, and Lei Meng*,“Sequential Fusion of Multi-view Video Frames for 3D Scene Generation,” CAAI International Conference on Artificial Intelligence(CAAI) ,pp 597-608, Beijing, China, August 27–28, 2022.(PDF文件)
Hang Wu, Xi Chen, Xuelong Li, Haokai Ma, Yuze Zheng, Xiangxian Li, Xiangxu Meng, Lei Meng*, “A Visually-Aware Food Analysis System for Diet Management,” IEEE International Conference on Multimedia & Expo (ICME’22), Taipei, Taiwan, 2022-7-18至2022-7-22.(PDF文件)
Jingyu Li, Haokai Ma, Xiangxian Li, Zhuang Qi, Lei Meng*, Xiangxu Meng, “Unsupervised Contrastive Masking for Visual Haze Classification,” ACM International Conference on Multimedia Retrieval (ICMR’22),pp 426-434,Newark NJ USA June 27-30, 2022(PDF文件)
Pei Dong, Lei Wu*, Xiangxu Meng, Lei Meng, “Disentangled Representations and Hierarchical Refinement of Multi-Granularity Features for Text-to-Image Synthesis,” ACM International Conference on Multimedia Retrieval (ICMR’22),pp 268-276,Newark NJ USA June 27-30, 2022.(PDF文件)
Xiang Li, Lei Wu, Xu Chen, Lei Meng*, Xiangxu Meng, “DSE-NET: Artistic Font Image Synthesis Via Disentangled Style Encoding,” IEEE International Conference on Multimedia & Expo (ICME’22), Taipei, Taiwan, 2022-7-18至2022-7-22.(PDF文件)
Xiangxian Li, Haokai Ma, Lei Meng*, Xiangxu Meng, “Comparative Study of Adversarial Training Methods for Long-tailed Classification,” International Workshop on Adversarial Learning for Multimedia (ADVM ’21), Chengdu, China, 2021-10-20至2021-10-24.(PDF文件)
Haokai Ma, Xiangxian Li, Lei Meng*, Xiangxu Meng, “Comparative Study of Adversarial Training Methods for Cold-Start Recommendation,” International Workshop on Adversarial Learning for Multimedia (ADVM ’21), Chengdu, China, 2021-10-20至2021-10-24.(PDF文件)
Xu Chen, Lei Wu*, Minggang He, Lei Meng*, Xiangxu Meng, “MLFont: Few-Shot Chinese Font Generation via Deep Meta-Learning,” ACM International Conference on Multimedia Retrieval(ICMR), Taipei, Taiwan, 2021-11-16至2021-11-19.(PDF文件)
Lei Meng, Fuli Feng, Xiangnan He, Xiaoyan Gao, Tat-Seng Chua, “Heterogeneous Fusion of Semantic and Collaborative Information for Visually-Aware Food Recommendation,” ACM International Conference on Multimedia (MM), pp. 3460-3468, Oct. 15, 2020.(PDF文件)
Lei Wu, Xi Chen, Lei Meng*, Xiangxu Meng, “Multitask Adversarial Learning for Chinese Font Style Transfer,” International Joint Conference on Neural Networks (IJCNN), accepted, 2020.(PDF文件)
Chuang Lin#, Sicheng Zhao#, Lei Meng*, Tat-Seng Chua, “Multi-Source Domain Adaptation for Visual Sentiment Classification,” AAAI Conference on Artificial Intelligence (AAAI), vol. 34, no. 3, pp. 2661-2668, Feb. 12, 2020.(PDF文件)
Lei Meng, Long Chen, Xun Yang, Dacheng Tao, Hanwang Zhang, Chunyan Miao, Tat-Seng Chua, “Learning Using Privileged Information for Food Recognition,” ACM International Conference on Multimedia (MM), pp. 557-565, 2019.(PDF文件)
Lei Meng, Ah-Hwee Tan, Cyril Leung, Liqiang Nie, Tat-Seng Chua, and Chunyan Miao, “Online Multimodal Co-indexing and Retrieval of Weakly Labeled Web Image Collections,” ACM International Conference on Multimedia Retrieval (ICMR), pp. 219-226, 2015.(PDF文件)
Lei Meng and Ah-Hwee Tan, “Community Discovery in Social Networks via Heterogeneous Link Association and Fusion,” SIAM International Conference on Data Mining (SDM), pp. 803-811, 2014.(PDF文件)
Lei Meng, Ah-Hwee Tan and Donald C. Wunsch II, “Vigilance Adaptation in Adaptive Resonance Theory,” International Joint Conference on Neural Networks, pp. 1-7, 2013.(PDF文件)
Lei Meng and Ah-Hwee Tan, “Semi-supervised Hierarchical Clustering for Personalized Web Image Organization,” International Joint Conference on Neural Networks, pp. 252-258, 2012.(PDF文件)
专利
孟雷,孙玮琳,王宇,李曼祎,李雪龙,孟祥旭, “基于大语言模型的开放域室内场景层级生成方法及系统”,专利号:ZL 2025 1 0019290.2,专利申请日:2025年1月7日,授权公告日:2025年7月11日,授权公告号:CN 119416330 B.
孟雷,齐壮,王宇,张若涵,李照川,孟祥旭, “基于原型引导的联邦一致性表示学习系统及方法”,专利号:ZL 2024 1 1764345.4,专利申请日:2024年11月12日,授权公告日:2025年5月30日,授权公告号:CN 119229223 B.
孟雷,陈子坦,王宇,齐壮,张若涵,李照川,孟祥旭, “类级关系约束与结构化图增强方法、系统、介质及终端”,专利号:ZL 2024 1 1577879.6,专利申请日:2024年11月12日,授权公告日:2025年2月25日,授权公告号:CN 119068272 B.
孟雷,马浩凯,谢若冰,杨一萌,孙兴武,康战辉, “一种基于义原泛化扩散模型的序列推荐方法及系统”,专利号:ZL 2024 1 0455873.5,专利申请日:2024年4月16日,授权公告日:2025年3月18日,授权公告号:CN 118364376 B.
马浩凯,谢若冰,孟雷,陈鑫,张旭,康战辉, “基于扩散模型的模型优化方法、装置、设备、介质及产品”,申请号: 202311341583X, 2023.6.12.
孟雷,孙玮琳,李曼祎,武蕾,盖伟,孟祥旭, “一种多视角室外三维场景重建方法及系统”,申请号: 202310797147.7, 2023.6.30.
孟雷,王雨晴,李象贤,刘彦男,孟祥旭, “基于样本平衡因果推理的分布外图像分类方法及系统”,申请号: 202310761382.9, 2023.6.26.
马浩凯,谢若冰,孟雷,陈鑫,张旭,林乐宇,周杰, “跨域推荐模型的样本处理方法、装置、设备及存储介质”,申请号: 2023106944044, 2023.6.12.
孟雷,齐壮,刘天涵,孟祥旭, “基于原型引导交叉训练机制的联邦学习系统及方法”,申请号: 2023103105396, 2023.3.23.
马浩凯,谢若冰,孟雷,陈鑫,张旭,林乐宇,“信息推荐方法、装置、电子设备、存储介质及程序产品” 申请号:202211652477.9, 2022.12.21.
孟雷,马浩凯,齐壮,李象贤,郑裕泽,孟祥旭,“基于跨模态语义推理和融合的视觉感知推荐方法及系统” 专利号:ZL 2022 1 0558907.4,专利申请日:2022年5月21日,授权公告日:2024年5月28日,授权公告号:CN 114936901 B.
孟雷,李象贤,郑裕泽,马浩凯,齐壮,孟祥旭,“基于跨模态语义表征学习和融合的图像分类方法及系统” 专利号:ZL 2022 1 0558899.3,专利申请日:2022年5月21日,授权公告日:2024年6月4日,授权公告号:CN 114898156 B.
武蕾,高琳,孟雷,孟祥旭,“基于深度学习的从布局到场景图像的自动生成方法及系统” 专利号: ZL 2022 1 0372997.8, 专利申请日:2022年4月11日,授权公告日:2024年06月28日,授权公告号:CN 114943322 B.
武蕾,陈旭,孟雷,孟祥旭,“一种基于深度元学习的汉字字库生成方法及系统” 专利号: ZL 2021 1 0297468.1,专利申请日:2021年3月19日,授权公告日:2022年8月30日,授权公告号:CN 113011337 B.
武蕾,董沛,孟雷,孟祥旭,“基于深度学习的剧本到故事板序列自动生成方法及系统,” 专利号:ZL 2021 1 0297471.3,专利申请日:2021年4月1日,授权公告日:2024年7月23日,授权公告号:CN 114610893 B.
武蕾,孟雷,孟祥旭,陈曦,“基于多任务对抗学习网络的汉字风格迁移方法及系统”专利号:ZL 2020 1 0333081.2,专利申请日:2020年4月24日,授权公告日:2022年4月1日,授权公告号:CN 11153246 B.
Lei Meng, Zhaoyan Ming, Tat-Seng Chua, “Food Recognition Enhanced Using Privileged Information” ILO Ref: 2019-243-01, SG Non-Provisional Application No. 10201907991T, Singapore, 29 Aug. 2019.
Lei Meng, Fuli Feng, Xiangnan He, Tat-Seng Chua, “A Visually-aware Food Recommender based on Dual-gating Multi-task Learning” ILO Ref: 2020-286-01, SG Non-Provisional Application No. 10202009048R, Singapore, 15 Sep. 2020.
[回到首页]
项目
项目: “ERP合同审核大语言模型研发”,1100-100-一般横向项目 (资金总额: 35万元) 职责: 项目负责人
项目: “基于深度学习的多维情感分析系统的研发及应用”,山东省重点研发计划 (资金总额: 350万元) 职责: 项目负责人
项目: “数字媒体技术专业一流课程建设研究与实践:以多媒体计算课程为例”,山东省本科高校教学改革研究项目 (资金总额: 5万元) 职责: 项目负责人
项目: “多媒体计算实践条件与实践基地建设”, 教育部产学合作协同育人项目 (资金总额: 20万元) 职责: 项目负责人
项目: “智能媒体分析与生成”, 研究生核心课程教材出版专项 (时间: 2024.1–2025.12,资金总额: 7万元) 职责: 项目负责人
项目: “多媒体计算理论与实践”, 山东大学高质量教材出版专项 (时间: 2023.12–2024.12,资金总额: 5万元) 职责: 项目负责人
2021年12月 –2024年11月 : 项目: “面向社会治理复杂系统的体系设计方法与应用研究”, 国家重点研发计划“社会治理与智慧社会科技支撑”重点专项(时间: 2021.12–2024.9,资金总额: 380万元) 职责: 课题负责人
2021年10月 –2022年12月 : 项目: “基于跨模态内容对齐的多模态视频分类”, CCF-腾讯犀牛鸟创意基金(时间: 2021.10–2022.12,资金总额: 5万人民币) 职责: 项目负责人
2021年1月 –2021年12月 : 项目: “特权信息赋能的深度学习及其可解释性研究”,山东省软件工程重点实验室科技创新基地专项拨款管理(时间: 2021.1–2021.12,资金总额: 20万元) 职责: 项目负责人
2021年1月 –2023年12月 : 项目: “面向医养健康的个性化饮食推荐方法研究”,国家自然科学基金委员会 (NSFC) 拨款管理(时间: 2021.1–2023.12, 资金总额: 30万元) 职责: 项目负责人
饮食健康管理系统
基于视觉感知深度识别和推荐算法的饮食健康管理系统是由孟雷教授团队研发的一款面向中餐的饮食健康管理系统,主要针对市面上产品面临的缺乏基于多媒体数据的饮食分析、缺乏支撑深度学习的大规模数据集、系统社交元素缺乏等问题。团队运用面向用户饮食细粒度分析和膳食营养知识融合的人工智能深度学习方法,结合互联网资源构建了学术界最大的公开中餐饮食数据集,该数据集涵盖了超过30万的用户、40万的食谱以及1000万的交互信息;该系统采用了团队自主研发的基于人工智能技术的饮食识别和推荐算法,利用用户、食谱、营养等多源数据来分析和建模用户的饮食习惯,根据用户健康需求和营养搭配实现个性化的健康饮食推荐。结合膳食营养知识, 以非打扰、潜移默化的方式引导居民形成科学的膳食习惯,推进健康饮食文化建设,为人工智能走入人们日常生活和健康管理提供理论和技术支撑。 系统访问入口
|