Preprints:



In the following paper, we have theoretically answered why "going deeper, generalising better".
An Information-Theoretic View for Deep Learning. [PDF]
Jingwei Zhang, Tongliang Liu, and Dacheng Tao.



Instance-Dependent PU Learning by Bayesian Optimal Relabeling. [PDF]
Fengxiang He, Tongliang Liu, Geoff Webb, and Dacheng Tao.



Learning with Bounded Instance-and Label-dependent Label Noise. [PDF]
Jiacheng Cheng, Tongliang Liu, Kotagiri Rao, and Dacheng Tao.



Transfer Learning with Label Noise. [PDF]
Xiyu Yu, Tongliang Liu, Mingming Gong, Kun Zhang, and Dacheng Tao.



On the Rates of Convergence from Surrogate Risk Minimizers to the Bayes Optimal Classifier. [PDF]
Jingwei Zhang, Tongliang Liu, and Dacheng Tao.



Adversarial Examples for Hamming Space Search.
Erkun Yang, Tongliang Liu, Cheng Deng, and Dacheng Tao.
IEEE Transactions on Cybernetics (T-CYB), accepted.



Large-Margin Label-Calibrated Support Vector Machines for Positive and Unlabeled Learning.
Chen Gong, Tongliang Liu, Jian Yang, and Dacheng Tao
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), accepted.



Eigenfunction-Based Multi-Task Learning in a Reproducing Kernel Hilbert Space.
Xinmei Tian, Ya Li, Tongliang Liu, Xinchao Wang, and Dacheng Tao
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), accepted.



Absent Multiple Kernel Learning Algorithms.
Xinwang Liu, Lei Wang, Xinzhong Zhu, Miaomiao Li, En Zhu, Tongliang Liu, Li Liu, Yong Dou, and Jianping Yin.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), accepted.



Multiple Kernel k-means with Incomplete Kernels.
Xinwang Liu, Xinzhong Zhu, Miaomiao Li, Lei Wang, En Zhu, Tongliang Liu, Marius Kloft, Dinggagn Shen, Jianping Yin, and Wen Gao.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), accepted.



Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain.
Yong Luo, Yonggang Wen, and Tongliang Liu, Dacheng Tao.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), accepted.

Journal papers:

2019



Truncated Cauchy Non-negative Matrix Factorization.
Naiyang Guan*, Tongliang Liu*, Yangmuzi Zhang, Dacheng Tao, and Larry Steven Davis.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 41(1): 246-259, 2019.

2018



Fast Supervised Discrete Hashing. [PDF] [BibTeX]
Jie Gui*, Tongliang Liu*, Zhenan Sun, Dacheng Tao, and Tieniu Tan.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 40(2): 490-496, 2018.



Continuous Dropout.
Xu Shen, Xinmei Tian, Fang Xu, Tongliang Liu, and Dacheng Tao
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 29(9): 3926-3937, 2018.



Multi-class Learning with Partially Corrupted Labels.
Ruxin Wang, Tongliang Liu, and Dacheng Tao
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 29(6): 2568-2580, 2018.



On Better Exploring and Exploiting Task Relationship in Multi-Task Learning: Joint Model and Feature Learning.
Ya Li, Xinmei Tian, Tongliang Liu, and Dacheng Tao.
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 29(5): 1975-1985, 2018.



Supervised Discrete Hashing with Relaxation. [PDF] [BibTeX]
Jie Gui*, Tongliang Liu*, Zhenan Sun, Dacheng Tao, and Tieniu Tan.
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 29(3): 608-617, 2018.



Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks. [PDF]
Kede Ma, Huan Fu, Tongliang Liu, Zhou Wang, and Dacheng Tao.
IEEE Transactions on Image Processing (T-IP), 27(10): 5155-5166, 2018.



A Regularization Approach for Instance-Based Superset Label Learning. [PDF] [BibTeX]
Chen Gong, Tongliang Liu, Yuanyan Tang, Jian Yang, Jie Yang, and Dacheng Tao.
IEEE Transactions on Cybernetics (T-CYB), 48(3): 967-978, 2018.

2017



Algorithm-Dependent Generalization Bounds for Multi-Task Learning. [PDF] [BibTeX]
Tongliang Liu, Dacheng Tao, Mingli Song, and Stephen J. Maybank.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 39(2): 227-241, 2017.



Large Cone Non-negative Matrix Factorization. [PDF] [BibTeX]
Tongliang Liu, Mingming Gong, and Dacheng Tao.
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 28(9): 2129-2141, 2017.



dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs. [PDF] [BibTeX]
Kede Ma, Wentao Liu, Tongliang Liu, Zhou Wang, and Dacheng Tao.
IEEE Transactions on Image Processing (T-IP), 26(8): 3951-3964, 2017.



Elastic Net Hypergraph Learning for Image Clustering and Semi-supervised Classification. [PDF] [BibTeX]
Qingshan Liu, Yubao Sun, Cantian Wang, Tongliang Liu, Dacheng Tao.
IEEE Transactions on Image Processing (T-IP), 26(1): 452-463, 2017.



Spectral Ensemble Clustering via Weighted K-means: Theoretical and Practical Evidence.
Hongfu Liu, Junjie Wu, Tongliang Liu, Dacheng Tao, and Yun Fu.
IEEE Transactions on Knowledge and Data Engineering (T-KDE), vol. 29, no. 5, pp. 1129-1143, 2017.



Joint Sparse Representation and Multitask Learning for Hyperspectral Target Detection. [BibTeX]
Yuxiang Zhang, Bo Du, Liangpei Zhang, and Tongliang Liu.
IEEE Transactions on Geoscience and Remote Sensing (T-GRS), 55(2): 894-906, 2017.

2016



Classification with Noisy Labels by Importance Reweighting. [PDF] [BibTeX]
Tongliang Liu and Dacheng Tao.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 38(3): 447-461, 2016.



Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes. [PDF] [BibTeX]
Tongliang Liu, Dacheng Tao, and Dong Xu.
Neural Computation (NECO), 28(10): 2213-2249, 2016.



On the Performance of MahNMF Manhattan Non-negative Matrix Factorization. [PDF] [BibTeX]
Tongliang Liu and Dacheng Tao.
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 27(9): 1851-1863, 2016.



Local Rademacher Complexity for Multi-Label Learning. [PDF] [BibTeX]
Chang Xu, Tongliang Liu, Dacheng Tao, and Chao Xu.
IEEE Transactions on Image Processing (T-IP), 25(3): 1495-1507, 2016.



Dual Diversified Dynamical Gaussian Process Latent Variable Model for Video Repair. [PDF] [BibTeX]
Hao Xiong, Tongliang Liu, Dacheng Tao, and Heng Tao Shen.
IEEE Transactions on Image Processing (T-IP), 25(8): 3626-3637, 2016.



Representative Vector Machines: A Unified Framework for Classical Classifiers. [PDF] [BibTeX]
Jie Gui*, Tongliang Liu*, Dacheng Tao, Zhenan Sun, and Tieniu Tan.
IEEE Transactions on Cybernetics (T-CYB), 46(8): 1877-1888, 2016.



Video Face Editing Using Temporal-Spatial-Smooth Warping. [PDF] [BibTeX]
Xiaoyan Li, Tongliang Liu, Jiankang Deng, and Dacheng Tao.
ACM Transactions on Intelligent Systems and Technology (ACM-TIST), 7(3): 32, 2016.

2015



Deformed Graph Laplacian for Semisupervised Learning. [PDF] [BibTeX]
Chen Gong, Tongliang Liu and Dacheng Tao, Keren Fu, Enmei Tu, and Jie Yang.
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 26(10): 2261-2274, 2015.



Multiview Matrix Completion for Multilabel Image Classification. [PDF] [BibTeX]
Yong Luo, Tongliang Liu, Dacheng Tao, and Chao Xu.
IEEE Transactions on Image Processing (T-IP), 24(8): 2261-2274, 2015.



No Reference Quality Assessment for Multiply-Distorted Images Based on an Improved Bag-of-Words Model. [PDF] [BibTeX]
Yanan Lu, Fengying Xie, Tongliang Liu, Zhiguo Jiang, and Dacheng Tao.
IEEE Signal Processing Letters (IEEE-SPL), 22(10): 1811-1815, 2015.

2014



Decomposition-Based Transfer Distance Metric Learning for Image Classification. [PDF] [BibTeX]
Yong Luo, Tongliang Liu, Dacheng Tao, and Chao Xu.
IEEE Transactions on Image Processing (T-IP), 23(9): 3789-3801, 2014.

Conference papers:



DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs.
Erkun Yang, Tongliang Liu, Cheng Deng, Wei Liu, and Dacheng Tao.
The 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019): Accepted.



Skipping Two Layers in ResNet Making the Generalization Gap Smaller than Skipping One or No Layer.
Yasutaka Furusho, Tongliang Liu, and Kazushi Ikeda.
INNS Big Data and Deep Learning (INNS BDDL 2019), Accepted.



Robust Angular Local Descriptor Learning. [PDF]
Yanwu Xu, Mingming Gong, Tongliang Liu, Kayhan Batmanghelich, and Chaohui Wang.
Asian Conference on Computer Vision (ACCV 2018), Accepted.



Learning with Biased Complementary Labels. [PDF]
Xiyu Yu, Tongliang Liu, Mingming Gong, and Dacheng Tao.
European Conference on Computer Vision (ECCV(1) 2018), 69-85.



Deep Domain Generalization via Conditional Invariant Adversarial Networks.
Ya Li, Xinmei Tian, Mingming Gong, Yajing Liu, Tongliang Liu, Kun Zhang, and Dacheng Tao.
European Conference on Computer Vision (ECCV(15) 2018), 647-663.



Correcting the Triplet Selection Bias for Triplet Loss.
Baosheng Yu, Tongliang Liu, Mingming Gong, Changxing Ding, and Dacheng Tao.
European Conference on Computer Vision (ECCV(6) 2018), 71-86.



Online Heterogeneous Transfer Metric Learning.
Yong Luo, Tongliang Liu, Yonggang Wen, and Dacheng Tao.
The 2018 International Joint Conference on Artificial Intelligence (IJCAI 2018), 2525-2531.



Quantum Divide-and-Conquer Anchoring for Separable Non-negative Matrix Factorization. [PDF]
Yuxuan Du, Tongliang Liu, Yinan Li, Runyao Duan, and Dacheng Tao.
The 2018 International Joint Conference on Artificial Intelligence (IJCAI 2018), 2093-2099.



Semantic Structure-based Unsupervised Deep Hashing.
Erkun Yang, Cheng Deng, Tongliang Liu, Wei Liu, and Dacheng Tao.
The 2018 International Joint Conference on Artificial Intelligence (IJCAI 2018), 1064-1070.



An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption.
Xiyu Yu, Tongliang Liu, Mingming Gong, Kayhan Batmanghelich, and Dacheng Tao.
The 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018): 4480-4489.



Domain Generalization via Conditional Invariant Representations.
Ya Li, Mingming Gong, Xinmei Tian, Tongliang Liu, and Dacheng Tao.
The 32th AAAI Conference on Artificial Intelligence (AAAI 2018): 3579-3587.



General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer. [PDF] [BibTeX]
Yong Luo, Yonggang Wen, Tongliang Liu, and Dacheng Tao. [Distinguished Paper Candidate]
The 2017 International Joint Conference on Artificial Intelligence (IJCAI 2017): 2450-2456



Understanding How Feature Structure Transfers in Transfer Learning. [PDF] [BibTeX]
Tongliang Liu, Qiang Yang, and Dacheng Tao.
The 2017 International Joint Conference on Artificial Intelligence (IJCAI 2017): 2365-2371.



Algorithmic Stability and Hypothesis Complexity. [PDF] [BibTeX]
Tongliang Liu, Gábor Lugosi, Gergely Neu, and Dacheng Tao.
The 34th International Conference on Machine Learning (ICML 2017): 2159-2167.



On Compressing Deep Models by Low Rank and Sparse Decomposition. [PDF] [BibTeX]
Xiyu Yu, Tongliang Liu, Xinchao Wang, and Dacheng Tao.
The 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017): 7370-7379.



Domain Adaptation with Conditional Transferable Components. [PDF] [BibTeX]
Mingming Gong, Kun Zhang, Tongliang Liu, Dacheng Tao, Clark Glymour, and Bernhard Schölkopf.
The 33rd International Conference on Machine Learning (ICML 2016): 2839-2848.



Diversified Dynamical Gaussian Process Latent Variable Model for Video Repair. [PDF] [BibTeX]
Hao Xiong, Tongliang Liu, and Dacheng Tao.
The 30th AAAI Conference on Artificial Intelligence (AAAI 2016): 3641-3647.



Spectral Ensemble Clustering. [PDF] [BibTeX]
Hongfu Liu*, Tongliang Liu*, Junjie Wu, Dacheng Tao, and Yun Fu. [*: equally contributed]
The 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD 2015): 715-724.



Multi-Task Model and Feature Joint Learning. [PDF] [BibTeX]
Ya Li, Xinmei Tian, Tongliang Liu, and Dacheng Tao.
The 2015 International Joint Conference on Artificial Intelligence (IJCAI 2015): 3643-3649.



On the Robustness and Generalization of Cauchy Regression. [PDF] [BibTeX] [Best Paper Award]
Tongliang Liu and Dacheng Tao.
The 2014 IEEE International Conference on Information Science and Technology (ICIST 2014): 100-105.



Learning Relative Features through Adaptive Pooling for Image Classification. [PDF] [BibTeX] [Best Paper Award candidate]
Ming Shao, Sheng Li, Tongliang Liu, Dacheng Tao, Thomas S. Huang, and Yun Fu.
The 2014 IEEE International Conference on Multimedia and Expo (ICME 2014): 1-6.