Research Related (研究相关)

 

Research Interest(研究兴趣):

 

Fundamental problems in machine learning and computer vision, especially including:

  • Self-paced learning
  • Noise/loss modeling
  • Tensor sparsity

 

Publications (发表文章)

New:

[93] Hongwei Yong, Deyu Meng, Wangmeng Zuo, Lei Zhang. Robust Online Matrix Factorization for Dynamic Background Subtraction, arXiv:1705.10000, 2017.

[92] Lan Wang, Chenqiang Gao, Jiang Liu, Deyu Meng. A novel learning-based frame pooling method for Event Detection. Signal Processing, 2017

[91] Deyu Meng, Qian Zhao, Lu Jiang. A Theoretical Understanding of Self-paced Learning. accepted by Information Sciences, 2017 [arxiv version] [slides].

[90] Fan Ma, Deyu Meng, Qi Xie, Zina Li, Xuanyi Dong, Self-paced Cotraining, ICML, 2017 [supplementary material]

[89] Dingwen Zhang, Le Yang, Deyu Meng, Dong Xu and Junwei Han.  A Self-Paced Fine-Tuning Network for Segmenting Objects in Weakly Labelled Videos. CVPR, 2017.

[88] Zilu Ma, Shiqi Liu, Deyu Meng, On Convergence Property of Implicit Self-paced ObjectivearXiv:1703.09923, 2017.

[87] Kede Ma, Hui Li, Hongwei Yong, Zhou Wang, Deyu Meng, Lei Zhang. Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition ApproachIEEE Trans. on Image Processing, 2017. [supplementary material][code]

[86] Yang Chen, Xiangyong Cao, Qian Zhao, Deyu Meng, Zongben Xu. Denoising Hyperspectral Image with Non-i.i.d. Noise Structure. IEEE Transactions on Cybernetics. 2017. [arxiv version][Appendix][code]

[85] Liang Lin, Keze Wang, Deyu Meng, Wangmeng Zuo, Lei Zhang. Active Self-Paced Learning for Cost-Effective and Progressive Face Identification. To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017. [arxiv version][code]

[84] Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang, Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising, IEEE Trans. on Image Processing, 2017. [code]

[83] Liantao Wang, Deyu Meng, Xuelei Hu, Jianfeng Lu, Ji Zhao. Instance Annotation via Optimal BoW for Weakly Supervised Object Localization. IEEE Transactions on Cybernetics. 2017.

[82] Xiangyong Cao, Lin Xu, Deyu Meng, Qian Zhao, Zongben Xu. Integration of 3-dimensional discrete wavelet transform and Markov random field for hyperspectral image classification. Neurocomputing 226, 90-100, 2017. [code] (This paper designs a new feature leading to the state-of-the-art performance on hyperspectral image classification.)

 

[81] Nannan Gu, Mingyu Fan, Deyu Meng. Robust Semi-Supervised Classification for Noisy Labels Based on Self-Paced Learning. IEEE Signal Processing Letters 23 (12), 1806-1810, 2016.

[80] Zongsheng Yue; Deyu Meng; Juan He; Gemeng Zhang. Semi-Supervised Learning through Adaptive Laplacian Graph Trimming. Accepted by Image and Vision Computing, 2016.

[79] Xiangyong Cao, Qian Zhao, Deyu Meng, Yang Chen, Zongben Xu. Robust Low-rank Matrix Factorization under General Mixture Noise Distributions, IEEE Transactions on Image Processing, 2016.

[78] Zhaoxin Li, Kuanquan Wang, Wangmeng Zuo, Deyu Meng, Lei Zhang. Detail-Preserving and Content-Aware Variational Multi-View Stereo Reconstruction. IEEE Transactions on Image Processing 25(2): 864-877, 2016.

[77] Chenqiang Gao, Yinhe Du, Jiang Liu, Jing Lv, Luyu Yang, Deyu Meng, Alexander G Hauptmann, InfAR dataset: Infrared action recognition at different times, Neurocomputing, 2016. [InfAR Dataset]

[76] Shuhang Gu, Qi Xie, Deyu Meng, Wangmeng Zuo, Xiangchu Feng, Lei Zhang, Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision, International Journal of Computer Vision, 2016.

[75] Wenfei Cao, Yao Wang, Jian Sun, Deyu Meng, Can Yang, Andrzej Cichocki, Zongben Xu. Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements. IEEE Transactions on Image Processing, 2016.[Demo code]

[74] Dingwen Zhang, Deyu Meng, Junwei Han. Co-saliency Detection via A Self-paced Multiple-instance Learning FrameworkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016.

[73] Junwei Liang, Lu Jiang, Deyu Meng and Alex Hauptmann, Learning to Detect Concepts from Webly-Labeled Video DataInternational Joint Conference on Artificial Intelligence (IJCAI), 2016.

[72] Dingwen Zhang, Deyu Meng, Long Zhao and Junwei Han, Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning. International Joint Conference on Artificial Intelligence (IJCAI), 2016.

[71] Te Pi, Xi Li, Zhongfei Zhang, Deyu Meng, Fei Wu, Jun Xiao and Yueting Zhuang, Self-Paced Boost Learning for Classification. International Joint Conference on Artificial Intelligence (IJCAI), 2016.

[70] Shoou-I Yu, Deyu Meng, Wangmeng Zuo, Alexander G. Hauptmann, The Solution Path Algorithm for Identity-Aware Multi-Object Tracking. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[69] Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu, Shuhang Gu, Wangmeng Zuo and Lei Zhang. Multispectral images denoising by intrinsic tensor sparsity regularization. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [supplementary material[Matlab code]

[68] Xi’ai Chen, Zhi Han, Yao Wang, Qian Zhao, Deyu Meng and Yandong Tang. Robust tensor factorization with unknown noise. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

[67] Jiang Liu, Chenqiang Gao, Deyu Meng, Wangmeng Zuo, Two-Stream Contextualized CNN for Fine-Grained Image Classification. AAAI, 2016 (student paper).

[66] Hao Li, Maoguo Gong, Deyu Meng, Qiguang Miao. Multi-optimization Self-paced Learning. AAAI, 2016. 

[65] Dingwen Zhang, Deyu Meng, C. Li, Lu Jiang, Qian Zhao, and Junwei Han. A Self-paced Multiple-instance Learning Framework for Co-saliency Detection. ICCV, 2015.

[64] Xiangyong Cao, Yang Chen, Qian Zhao, Deyu Meng, Yao Wang, Dong Wang, Zongben Xu. Low-rank Matrix Factorization under General Mixture Noise Distributions. ICCV (oral), 2015.[supplementary material] [Matlab code] [arxiv version]

[63] Qian Zhao, Deyu Meng, Xu Kong, Qi Xie, Wenfei Cao, Yao Wang, Zongben Xu. A Novel Sparsity Measure for Tensor Recovery, ICCV, 2015. [supplementary material]

[62] Shuhang Gu, Wangmeng Zuo, Qi Xie, Deyu Meng, Xiangchu Feng, Lei Zhang, Convolutional Sparse Coding for Image Super-resolution, ICCV 2015. (State-of-the-art super-resolution result!)

[61] Lu Jiang, Shoou-I Yu, Deyu Meng, Yi Yang, Teruko Mitamura, Alexander Hauptmann. Fast and Accurate Content-based Semantic Search in 100M Internet Videos.  In ACM Multimedia (MM), 2015.

[60] Ji Zhao, Deyu Meng, Jiayi Ma,Density-Based Region Search with Arbitrary Shape for Object Localization. IET Computer Vision: 2015

[59] Lu Jiang, Shoou-I Yu, Deyu Meng, Teruko Mitamura, Alexander Hauptmann. Bridging the Ultimate Semantic Gap: A Semantic Search Engine for Internet Videos. In ACM International Conference on Multimedia Retrieval (ICMR). 2015. [BibTex |supplementary materials | slides | project page] Best paper runner-up 
[featured in] Pittsburgh Supercomputing Center

[58] Yan Yan, Yi Yang, Deyu Meng, Gaowen Liu, Wei Tong, Alexander G. Hauptmann, Nicu Sebe: Event Oriented Dictionary Learning for Complex Event Detection. IEEE Transactions on Image Processing, 24(6):1867-1878, 2015.

[57] Jiang-She Zhang, Nannan Ji, Junmin Liu, Jiyuan Pan, Deyu Meng: Enhancing performance of the backpropagation algorithm via sparse response regularization. Neurocomputing, 153:20-40, 2015.

[56] Yong Xu, Bo Huang, Yuyue Xu, Kai Cao, Chunlan Guo, Deyu Meng. Spatial and Temporal Image Fusion via Regularized Spatial Unmixing. IEEE Geoscience and Remote Sensing Letters, 12(6): 1362-1366, 2015. Matlab code.

[55] Ji Zhao, Deyu Meng. FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test, Neural Computation, 2015, accepted. Matlab Code. (Our proposed FastMMD method decreases the time complexity of MMD calculation from conventional O(N^2d) to O(Nlog(d))) [arxiv version]

[54] Qian Zhao, Deyu Meng, Zongben Xu, Wangmeng Zuo, Yan Yan. L1-Norm Low-Rank Matrix Factorization by Variational Bayesian Method. IEEE Transactions on Neural Networks and Learning Systems. 2015. accepted.

[53] Qian Zhao, Deyu Meng, Zongben Xu, Chenqiang Gao. A recursive divide-and-conquer approach for sparse principal component analysis. Neurocomputing, 2015. accepted

[52] Zhaoxin Li, Kuanquan Wang, Wenyan Jia, Hsin-Chen Chen, Wangmeng Zuo, Deyu Meng, Mingui Sun, Multiview Stereo and Silhouette Fusion via Minimizing Generalized Reprojection Error, Image and Vision Computing, 2015, accepted.

[51] Yan Yan, Yi Yang, Haoquan Shen, Deyu Meng, Gaowen Liu, Alexander Hauptmann, Nicu Sebe. Complex Event Detection via Event Oriented Dictionary Learning. AAAI, 2015.

[50] Qian Zhao, Deyu Meng, Lu Jiang, Qi Xie, Zongben Xu, Alexander Hauptmann. Self-paced Matrix Factorization. AAAI, 2015. Supplementary material.

[49] Lu Jiang, Deyu Meng, Qian Zhao, Shiguang Shan, Alexander Hauptmann. Self-paced Curriculum Learning. AAAI, 2015.Supplementary material, slides, code.  

[48] Faqiang Wang, Wangmeng Zuo, Lei Zhang, Deyu Meng, and David Zhang, A Kernel Classification Framework for Metric Learning, IEEE Transactions on Neural Networks and Learning Systems. 2014.

[47] Luyu Yang, Chenqiang Gao, Deyu Meng, Lu Jiang. A Novel Group-sparsity-optimization-based Feature Selection Model for Complex Interaction Recognition. ACCV, 2014.

[46] Lu Jiang, Deyu Meng, Shoou-I Yu, Zhen-Zhong Lan, Shiguang Shan, Alexander Hauptmann.Self-paced Learning with Diversity. NIPS, 2014.Supplementary material, code.

[45] Lu Jiang, Deyu Meng, Teruko Mitamura, Alexander Hauptmann. Easy Samples First: Self-paced Reranking for Zero-Example Multimedia Search. ACM MM. 2014. Slides.

[44] Haoquan Shen, Shoou-I Yu, Yi Yang, Deyu Meng, Alexander Hauptmann. Unsupervised Video Adaptation for Parsing Human Motion. ECCV, 2014. [Project Page] [Code and Dataset] [Demo Video]

[43] Qi Xie, Deyu Meng, Shuhang Gu, Lei Zhang, Wangmeng Zuo, Xiangchu Feng, Zongben Xu. On the optimal solution of weighted nuclear norm minimization, arXiv:1405.6012v1, 2014.

[42] Qian Zhao, Deyu Meng, Zongben Xu, Wangmeng Zuo, Lei Zhang. Robust principal component analysis with complex noiseSupplementary MaterialICML, 2014.

[41] Yi Peng, Deyu Meng, Zongben Xu, Chenqiang Gao, Yi Yang, Biao Zhang. Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising. Supplementary Material, CVPR, 2014. Matlab code.

[40] Zhiding Yu, Chunjing Xu, Deyu Meng, et al. Transitive Distance Clustering with K-Means Duality. CVPR, 2014. 

[39] Nannan Gu, Di Wang, Mingyu Fan, Deyu Meng. A kernel-based sparsity preserving method for semi-supervised classification, Neurocomputing, accepted, 2014.

[38] Chenqiang Gao, Deyu Meng, Wei Tong, Yi Yang, Yang Cai, Haoquan Shen, Gaowen Liu, Shicheng Xu, Alexander Hauptmann. Interactive Surveillance Event Detection through Mid-Level Discriminative Representation. ICMR, 2014.
[37] Lu Jiang, Wei Tong, Deyu Meng, Alexander G. Hauptmann.
Towards Efficient Learning of Optimal Spatial Bag-of-Words Representations. ICMR, 2014. (Best paper runner up) slides, Please download our code in JS Tiling webpage

[36] Jihua Zhu, Deyu Meng, Zhongyu Li, Shaoyi Du, Zejian Yuan. Robust registration of partially overlapping point sets via genetic algorithm with growth operator. IET Image Processing, accepted, 2014.

[35] Deyu Meng, Biao Zhang, Zongben Xu, Lei Zhang, Chenqiang Gao. Robust Low-Rank Tensor Factorization by Cyclic Weighted Median.Science in China Series F: Information Sciences, accepted, 2014.
[34] Ji Zhao, Deyu Meng. Ensemble of Circular Discrepancy for Efficient Two-Sample Test. NIPS Workshop on Randomized Methods for Machine Learning (RMML2013), Lake Tahoe, Nevada, Dec. 9, 2013.

[33] Chenqiang Gao, Yang Cai, Haoquan Shen, Wei Tong, Yi Yang, Nicolas Ballas, Deyu Meng, Yan Yan, Alex Hauptmann, CMU Informedia @TREVID 2013: Surveillance Event Detection (SED), Carnegie Mellon University, 2013.

[32] Wangmeng Zuo, Deyu Meng, Lei Zhang, Xiangchu Feng, David Zhang. A Generalized Iterated Shrinkage Algorithm for Non-convex Sparse Coding. ICCV, 2013. Supplementary materialMatlab Code.

[31] Deyu Meng, Fernando De la Torre. Robust Matrix Factorization with Unknown Noise. ICCV, 2013.Matlab code.

[30] Deyu Meng, Hengbin Cui, Zongben Xu, Kaili Jing. Following the Entire Solution Path of Sparse Principal Component Analysis by Coordinate-Pairwise Algorithm. Data & Knowledge Engineering, 88: 25-36, 2013. 

[29] Chenqiang Gao, Deyu Meng, Yi Yang, Yongtao Wang, Xiaofang Gao, Alexander G. Hauptmann. Infrared Patch-image Model for Small Target Detection in A Single Image. IEEE Transactions on Image Processing. 22(12): 4996-5009, 2013. Matlab Code 

[28] Deyu Meng, Yee Leung, Zongben Xu. The strong convergence of visual classification method and its applications. Information Sciences. DOI: 10.1016/j.ins.2013.06.028, 2013.

[27] Qian Zhao, Deyu Meng, Zongben Xu. Robust Sparse PCA. Science in China Series F: Information Sciences, accepted, 2013.

[26] Deyu Meng, Zongben Xu, Lei Zhang, Ji Zhao. A cyclic weighted median method for L1 low-rank matrix factorization with missing entries. AAAI 2013. Matlab code

[25] Wenbo Liu, Zhiding Yu, Deyu Meng. Joint recognition/segmentation with cascaded multi-level feature classification and confidence. ICME, 2013.

[24] Yee Leung, Deyu Meng, Zongben Xu. Evaluation of a spatial relationship by the concept of intrinsic spatial distance. Geograhpical Analysis, 45(4):380-400, 2013.

[23] Deyu Meng, Qian Zhao, Yee Leung, Zongben Xu. Learning Dictionary from Signals under Global Sparsity Constraint. Neurocomputing, DOI: 10.1016/j.neucom.2013.03.028. 2013.

[22] Deyu Meng, Yee Leung, Zongben Xu, Passage method for nonlinear dimensionality reduction of data on multi-cluster manifolds, Pattern Recognition. 2013, 46(8) 2175-2186.

[21] Deyu Meng, Yee Leung, Zongben Xu. Detecting intrinsic loops underlying data manifold. IEEE Transactions on Knowledge and Data Engineering. 2013, 25(2) 337-347.

[20] Deyu Meng, Qian Zhao, Zongben Xu. Improve robustness of sparse PCA by L1-norm maximization. Pattern Recognition. 2012, 45(1) 487-497. PDF 

[19] Zongben Xu, Mingwei Dai, Deyu Meng. Fast and efficient strategies for model selection of support vector machines. IEEE Transactions on Systems, Man and Cybernetics, Part B. 2009, 39(5) 1292-1307. Matlab code

[18] Deyu Meng, Yee Leung, Tung Fung, Zongben Xu. Nonlinear dimensionality reduction of data lying on the multi-cluster manifold. IEEE Transactions on Systems, Man and Cybernetics, Part B. 2008, 38(4) 1111-1122.

[17] Deyu Meng, Yee Leung, Zongben Xu. Evaluating nonlinear dimensionality reduction based on its local and global quality assessments, Neurocomputing, 2011, 74(6): 941-948. PDF Matlab code

[16] Deyu Meng, Yee Leung, Zongben Xu, Tung Fung, Qingfu Zhang. Improving geodesic distance estimation based on locally linear assumption. Pattern Recognition Letters. 2008, 29(7) 862-870. PDF Matlab code

[15] Deyu Meng, Zongben Xu, Mingwei Dai. Supervised manifold learning method. Journal of Computer Research and Development. 2007, 44(12) 2072-2077. (In Chinese) PDF Matlab code

[14] Deyu Meng, Nannan Gu, Zongben Xu, Leung Yee, Nonlinear dimensionality reduction of data on loopy manifold. Journal of Software. 2008, 19(11) 2908-2920. (In Chinese) PDF Matlab code

[13] Nannan Gu, Deyu meng, Zongben Xu. Transition curve method for nonlinear dimensionality reduction of data on disconnected manifold. Journal of Software. 2010, 21(8) 1898-1907. (In Chinese)

[12] Deyu Meng, Chen Xu, Zongben Xu, Manifold rebuilding based on Isomap. Journal of Computer. 2009, 33(3) 545-555. (In Chinese) PDF Matlab code
[11] Wenfeng Jing, Deyu Meng, Chen Qiao, Zhiming Peng. Eliminating Vertical Stripe Defects on Silicon Steel Surface by L1/2 Regularization. Mathematical Problems in Engineering, 2011, Article ID 854674, 13 pages,doi:10.1155/2011/854674.

[10] Zhi Han, Deyu Meng, Zongben Xu, Nannan Gu. Incremental alignment manifold learning. Journal of Computer Science and Technology,  2011, 26(1): 153-165.

[9] Deyu Meng, Dong Liang, Yongfa Ling. Genetic algorithm for multi2protocol label switching. Academic Journal of Xi'an Jiaotong University. 2007, 19(2): 121-123.

[8] Yongfa Ling, Deyu Meng and Jijie Zhang. New strategies for collision resolution of multi-access channel. Academic Journal of Xi'an Jiaotong University. 2007, 19(1): 56-59.

[7] Zongben Xu, Jianjin Wang and Deyu Meng. Approximation Bound of Mixture Networks in Lwp Spaces. International Symposium on Neural Networks. 2006, 3971:60-65.

[6] Deyu Meng, Zongben Xu, Nannan Gu and Mingwei Dai. Estimating geodesic distances on locally linear patches. IEEE International Symposium on Signal Processing and Information Technology. 2007: 851-854.  

[5] Wenfeng Jing, Deyu Meng, Mingwei Dai, Zongben Xu. A New Preprocessing Method for Regression Problem. International Symposium on Neural Networks. 2006, 3972:765-770.

[4] Zongben Xu, Deyu Meng and Wenfeng Jing. A new approach for classification: visual simulation point of view. International Symposium on Neural Networks. 2005, 3497: 1-7.

[3] Deyu Meng, Chen Xu and Wenfeng Jing. A New Approach for Regression: Visual Regression Approach. International Conference on Computational intelligence and security. 2005, 3801: 139-144.

[2] Deyu Meng, Wenfeng Jing, Zongben Xu. A More Efficent Preprocessing Method for Support Vector Classification. International Conference on Neural Networks and Brain Proceedings. 2005, 2: 1173-1177.

[1] Deyu Meng, Yee Leung, Tung Fung, Zongben Xu. The strong convergence of visual classification method and its applications on disease diagnosis, International Conference on Pattern Recognition in Bioinformatics, 2008: 83-94.