List of High Quality Papers

1. Communications and Network

[1] Yin Zhang, R. Wang, M. S. Hossain, M. F. Alhamid and M. Guizani, “Heterogeneous Information Network-based Content Caching in the Internet of Vehicles”, IEEE Transactions on Vehicular Technology, vol. 68, no. 10, pp. 10216-10226, 2019.

Contribution: This paper proposes an approach can greatly reduce the network traffic load and effective improve the user experience, while the popular content can be automatically cached in real time.

[2] Y. Zhang, Y. Li, R. Wang, J. Lu, X. Ma and M. Qiu, “PSAC: Proactive Sequence-aware Content Caching via Deep Learning at the Network Edge,” IEEE Transactions on Network Science and Engineering, doi: 10.1109/TNSE.2020.2990963, 2020.

Contribution: This paper proposes a proactive content caching strategy based on deep learning at the network edge, creatively considering the sequential features.

[3] Yin Zhang, X. Ma, J. Zhang, M. S. Hossain, G. Muhammad and S. U. Amin, “Edge Intelligence in the Cognitive Internet of Things: Improving Sensitivity and Interactivity”, IEEE Network, vol. 33, no. 3, pp. 58-64, 2019.

Contribution: As a pioneer work, this paper develops a Cognitive Internet of Things based on edge intelligence, which is expected to extensively improve the sensory capacity, quality of service and quality of experience.

[4] Yin Zhang, Y. Qian, D. Wu, M. S. Hossain, A. Ghoneim and M. Chen, “Emotion-aware Multimedia System Security”, IEEE Transactions on Multimedia, vol. 21, no. 3, pp. 617-624, 2019.

Contribution: This paper proposes a novel security policy based on identity authentication and access control to ensure the security certificate through an interactive robot or edge devices, while the access control of private data stored in the edge cloud is adequately protected.

[5] Y. Zhang, Y. Li, R. Wang, M. S. Hossain and H. Lu, “MASR: Multi-aspect-aware Session-based Recommendation for Intelligent Transportation Services,” IEEE Transactions on Intelligent Transportation Systems, doi: 10.1109/TITS.2020.2990214, 2020.

Contribution: In this paper, the authors developed a novel session-based recommendation for intelligent transportation services, which comprehensively considers the drivers’ and passengers’ personalized behavior from multiple aspects.

[6] H. Lu, Y. Zhang, Y. Li, C. Jiang, H. Abbas, “User-Oriented Virtual Mobile Network Resource Management for Vehicle Communications”, IEEE Transactions on Intelligent Transportation Systems, 10.1109/TITS.2020.2991766, 2020.

Contributions: This paper proposes a virtual network resource management based on user behavior to further optimize the existing vehicle communications.

[7] H. Lu, T. Yu, Y. Sun, “DRRS-BC: Decentralized Routing Registration System Based on Blockchain”, IEEE/CAA Journal of Automatica Sinica, 2020.

Contributions: This paper proposes the decentralized blockchain-based route registration framework-Decentralized Route Registration System based on Blockchain.

[8] Song Deng, Xiangpeng Xie, Changan Yuan, Lechan Yang, Xindong Wu. Numerical sensitive data recognition based on hybrid gene expression programming for active distribution networks. Applied Soft Computing, 2020, 91:1-14.

Contributions: To address security of numerical data in active distribution networks, we proposed a new numerical sensitive data recognition algorithm by using rough set and improved gene expression programming.

[9] Deng S, Yuan C, Yang LC, Qin X, Zhou A. Data Recovery Algorithm under Intrusion Attack for Energy Internet. Future Generation Computer Systems, 2019, 100:109-121.

Contributions: To solve data security under the condition that the data is attacked, this paper addressed optimal data partition and recovery considering attacks for the Energy Internet.

2. Computer Vision

[1] Bin Yan, Haojie Zhao, Dong Wang, Huchuan Lu, Xiaoyun Yang. ‘Skimming-Perusal’ Tracking: A Framework for Real-Time and Robust Long-Term Tracking. ICCV, 2385-2393, 2019.

Contribution: This work presents a novel robust and real-time long-term tracking framework based on skimming and perusal modules. The perusal module focuses on accurate object localization, and the skimming module aims to speed up the tracking process.

[2] Kenan Dai, Yunhua Zhang, Dong Wang, Jianhua Li, Huchuan Lu, Xiaoyun Yang.  High-Performance Long-Term Tracking with Meta-Updater. CVPR, 6297-6306, 2020.

Contribution: This work introduces a long-term tracking framework consisting of an online local tracker, an online verifier, a SiamRPN-based re-detector, and a meta-updater.

3. Multimedia

[1] Xing Xu, Kaiyi Lin, Lianli Gao, Huimin Lu and Heng Tao Shen. “Learning Cross-Modal Common Representations by Private-Shared Subspaces Separation”. IEEE Transactions on Cybernetics, 2020 (Early access)

Contributions: This paper explores a novel cross-modal representation learning approach via two separate subspaces (private and shared) for cross-modal retrieval, which achieves the state-of-the-art performance.

[2] Huimin Lu, Ming Zhang, Xing Xu, Yujie Li and Heng Tao Shen. “Deep Fuzzy Hashing Network for Efficient Image Retrieval”. IEEE Transactions on Fuzzy Systems, 2020 (Early access)

Contributions: This paper proposes a fuzzy learning based approach named Deep Fuzzy Hashing Network for the image retrieval problem, which is a new and promising way that considers the retrieval task.

[3] Xing Xu, Huimin Lu, Jingkuan Song, Yang Yang, Heng Tao Shen and Xuelong Li, “Ternary Adversarial Networks with Self-supervision for Zero-shot Cross-modal Retrieval”, IEEE Transactions on Cybernetics (TCYB), 50(6): 2400-2413 (2020)

Contributions: This paper explores the new retrieval scenario of zero-shot cross-modal retrieval and proposes a novel model named Ternary Adversarial Networks with Self-supervision. It obtains more effective retrieval performance compared with the traditional retrieval methods on the new retrieval task.

[4] Xing Xu, Tan Wang, Yang Yang, Lin Zuo, Fumin Shen and Heng Tao Shen. “Cross-Modal Attention with Semantic Consistence for Image-Text Matching”. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020 (Early access)

Contributions: This paper focuses on the image-text matching task and develops a novel model using the cross-modal attention with semantic consistence. It obtains more accurate image-text similarity measurement via the attended local alignments between image regions and words.

[5] Xing Xu, Jialin Tian, Kaiyi Lin, Huimin Lu, Jie Shao and Heng Tao Shen, “Zero-Shot Cross-Modal Retrieval by Assembling AutoEncoder and Generative Adversarial Network”, ACM Transactions on Multimedia Computing Communications and Applications (TOMM), 2020 (Early access)

Contributions: This paper focuses on the novel retrieval task of zero-shot cross-modal retrieval and proposes a novel model by assembling two generative models of autoencoder and generative adversarial network. It facilitates the knowledge transfer of different classes in the learned common embedding space.

[6] Wenpeng Lu, Yuteng Zhang, Shoujin Wang, Heyan Huang, Qian Liu, and Sheng Luo. 2021. Concept representation by learning explicit and implicit concept couplings. IEEE Intelligent System. (2021).

Contributions: In human consciousness, a concept is always associated with various couplings that exist within descriptive texts and knowledge networks. Inspired by this, we propose a neural coupled concept representation framework and its instantiation: a coupled concept embedding model.

[7] Wenpeng Lu, Xu Zhang, Huimin Lu, and Fangfang Li. Deep hierarchical encoding model for sentence semantic matching. Journal of Visual Communication and Image Representation, 2020, 71: 102794.

Contributions: To capture more semantic context features and interactions for sentence semantic matching, we propose a hierarchical encoding model (HEM), further enhanced by a hierarchical matching mechanism for sentence interaction. Given two sentences, HEM generates intermediate and final representations in encoding layer, which are further handled by a novel hierarchical matching mechanism to capture more multi-view interactions in matching layer.

4. Pattern Recognition

[1] Xiao Ma, Qiao Liu, Weihua Ou*, Quan Zhou:Visual object tracking via coefficients constrained exclusive group LASSO. Mach. Vis. Appl. 29(5): 749-763 (2018)

Contributions: Proposed a template dictionary learning algorithm considering the group sparsity, which can deal with different occlusions in object tracking.

[2]Weihua Ou, Xiao Luan, Jianping Gou, Quan Zhou, Wenjun Xiao, Xiangguang Xiong, Wu Zeng: Robust discriminative nonnegative dictionary learning for occluded face recognition. Pattern Recognition Letters 107: 41-49 (2018)

Contributions: Proposed a discriminavie nonnegative dictionary learning algorithm, which can learn dictionary without any prior of occlusions.

[3] Weihua Ou, Fei Long, Yi Tan, Shujian Yu, Pengpeng Wang: Co-regularized multiview nonnegative matrix factorization with correlation constraint for representation learning. Multimedia Tools Appl. 77(10): 12955-12978 (2018)

Contributions: Proposed a multiview common representation learning algorithm considering the correlation between different views, which can learn discriminative representation.

[4] Jiaxing Deng, Weihua Ou*, Jianping Gou,Heping Song, Anzhi Wang,Xing Xu. Representation separation adversarial networks for cross-modal retrieval. Wireless Networks (early access)

Contributions: Proposed an adversarial common representation learning algorithm, which can learn discriminative representation for cross-modal retrieval.

[6] Rushi Lan, Long Sun, Zhenbing Liu*, Huimin Lu, Cheng Pang, and Xiaonan Luo, “MADNet: A Fast and Lightweight Network for Single Image Super-Resolution,” accepted by IEEE Transactions on Cybernetics, 2020, DOI: 10.1109/TCYB.2020.2970104.

Contributions: This paper proposes a dense lightweight network, called MADNet, for single image super-resolution. MADNet has stronger multiscale feature expression and feature correlation learning capacities.

[7] Rushi Lan, Long Sun, Zhenbing Liu*, Huimin Lu, Zhixun Su, Cheng Pang, and Xiaonan Luo, “Cascading and Enhanced Residual Networks for Accurate Single Image Super-resolution,” accepted by IEEE Transactions on Cybernetics, DOI: 10.1109/TCYB.2019.2952710, 2019.

Contributions: Based on novel local wider residual blocks (LWRBs) that effectively extract the image features, this paper develops two methods, cascading and enhanced residual networks, for accurate single image super-resolution.

[9] Rushi Lan, Yicong Zhou*, Zhenbing Liu, and Xiaonan Luo, “Prior Knowledge-Based Probabilistic Collaborative Representation for Visual Recognition,” IEEE Transactions on Cybernetics, Vol. 50, 1498–1508, 2020, DOI, 10.1109/TCYB.2018.2880290.

Contributions: This paper proposes a novel classifier, called PKPCRC, for visual recognition. Compared with existing classifiers, the proposed PKPCRC further includes characteristics of training samples of each class as prior knowledge.

5. Robotics

[1] H. Lu, Y. Li, S. Mu, D. Wang, H. Kim, S. Serikawa, “Motor anomaly detection for unmanned aerial vehicles using reinforcement learning”, IEEE Internet of Things Journal, 10.1109/JIOT.2017.2737479, vol.5, no.4, pp.2315-2322, 2018.

Contributions: This paper is to develop an anomaly detection system to prevent the motor of the drone from operating at abnormal temperatures using reinforcement learning.

[2] X. Yang, H. Wu, Y. Li, S. Kang, B. Chen, H. Lu, C. Lee, P. Ji, “Dynamics and Isotropic Control of Parallel Mechanisms for Vibration Isolation”, IEEE/ASME Transactions on Mechatronics, 10.1109/TMECH.2020.2996641, vol.25, no.4, pp.2027-2034, 2020.

Contributions: This paper proposes a novel concept; namely, isotropic control, to solve isotropic mechanism design problem.

[3] P. Wang, D. Wang, X. Zhang, X. Li, T. Peng, H. Lu, X. Tian, “Numerical and Experimental Study on the Maneuverability of an Active Propeller Control based Wave Glider”, Applied Ocean Research, 10.1016/j.apor.2020.102369, vol.104, 102369, 2020.

Contributions: In this paper, an 8 degree-of-freedom (DOF) mathematical model of the wave glider based on the active propeller control is developed.

%d bloggers like this: