Article
Computer Science, Artificial Intelligence
Mingxin Gan, Hongfei Cui
Summary: This study explores user interest characteristics and provides dynamic movie recommendations by constructing UMIS model and proposing DIF deep learning model. Experimental results show that DIF model outperforms traditional models and other state-of-the-art deep learning models in predicting future user interests in a multi-dimensional user interest space.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Mathematics
Yongheng Mu, Yun Wu
Summary: Recommendation systems are widely used to provide personalized content and services to users efficiently. In this paper, a personalized multimodal movie recommendation system based on deep learning and multimodal data analysis was proposed. Real-world MovieLens datasets were used to test the effectiveness of the algorithm, which achieved improved accuracy in predicting movie scores compared to traditional collaborative filtering approaches. The combination of deep learning and multimodal data analysis can help alleviate the sparse data problem and enhance the performance of recommendation systems.
Article
Computer Science, Artificial Intelligence
Zahra Zamanzadeh Darban, Mohammad Hadi Valipour
Summary: This paper proposes a recommender system method that uses a graph-based model combined with users' ratings similarity, demographic, and location information. By extracting new features using Autoencoder feature extraction and clustering users based on the new set of features, the proposed approach outperformed many existing recommendation algorithms on accuracy and achieved significant results in the cold-start problem.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Yu-Jhen Wang, Anthony J. T. Lee
Summary: With the increasing popularity of social networks, businesses are implementing their branding or targeted advertising strategies through social media platforms to reach potential customers. This study proposes a framework for recommending movie accounts on Instagram using data collected from Instagram and IMDb platforms. The results show that this framework outperforms other methods in terms of precision, recall, F1-score, and NDCG, and helps movie companies or businesses reach potential audiences.
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Jia Xu, Xin Wang, Hongming Zhang, Pin Lv
Summary: Cross-Domain Recommendation (CDR) is a promising solution to address the cold-start problem in recommendation systems by transferring users' preferences from the source domain to the target domain. However, recent CDR works fail to effectively handle the core issues of "what to transfer" and "how to transfer" due to the neglect of semantic differences and the non-consideration of common characteristics among users. To tackle these challenges, we propose a novel heterogeneous and clustering-enhanced user preference transfer model (HCCDR) that computes high-quality representations of users and items based on heterogeneous relations and learns an effective personalized preference transfer function considering individual and common characteristics of a user. Experimental results demonstrate that HCCDR outperforms all baselines, achieving a maximum performance improvement of 12.69% (or 8.99%) for RMSE (or MAE) compared to the best baseline.
INFORMATION FUSION
(2023)
Article
Chemistry, Multidisciplinary
Jibing Gong, Xinghao Zhang, Qing Li, Cheng Wang, Yaxi Song, Zhiyong Zhao, Shuli Wang
Summary: By combining display information with implicit information, a new top-N recommendation method called MFDNN was proposed for Heterogeneous Information Networks (HINs), significantly improving hit ratio and normalized discounted cumulative gain in experiments.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Zhengjin Zhang, Qilin Wu, Yong Zhang, Li Liu
Summary: In recent years, recommendation systems have become crucial in major streaming video platforms. This article proposes the Hybrid AdaBoost Ensemble Method, which uses fuzzy clustering and neural network training to improve scoring prediction accuracy, and introduces the AdaBoost integration method to enhance the stability of the model.
PEERJ COMPUTER SCIENCE
(2023)
Article
Chemistry, Multidisciplinary
Tae-Gyu Hwang, Sung Kwon Kim
Summary: This study addresses the issues in recommender systems through bias analysis, introducing new methods like BBP and MBA. Experimental results demonstrate the effectiveness of these methods in improving accuracy.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Xingjian Cao, Zonghang Li, Gang Sun, Hongfang Yu, Mohsen Guizani
Summary: In this study, a novel federated learning method called CoFED is proposed, which utilizes unlabeled data pseudolabeling and cotraining to meet the requirements of heterogeneous models, tasks, and training processes in cross-silo federated learning. Experimental results show that the proposed method outperforms other methods, especially in non-IID settings and with heterogeneous models, achieving a 35% performance improvement.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Telecommunications
Dengcheng Yan, Yuchuan Zhao, Zhongxiu Yang, Ying Jin, Yiwen Zhang
Summary: The study proposed a privacy-preserving Federated framework FedCDR for Cross-Domain Recommendation, which trains recommendation models on user personal devices and uses local differential privacy to protect user data, achieving good performance in cross-domain recommendation.
DIGITAL COMMUNICATIONS AND NETWORKS
(2022)
Article
Telecommunications
Dengcheng Yan, Yuchuan Zhao, Zhongxiu Yang, Ying Jin, Yiwen Zhang
Summary: This study proposes a privacy-preserving federated framework, called FedCDR, for addressing privacy leakage risks in cross-domain recommendation. The framework trains a recommendation model on each user's personal device and adopts local differential privacy to protect user privacy. It effectively solves the privacy issues caused by centralized storage of user data.
DIGITAL COMMUNICATIONS AND NETWORKS
(2022)
Article
Computer Science, Artificial Intelligence
Renchu Guan, Haoyu Pang, Fausto Giunchiglia, Yanchun Liang, Xiaoyue Feng
Summary: The cold-start problem limits the effectiveness of recommendation systems. There are two main strategies to address this problem: cross-domain recommendation (CDR) and meta-learning. However, CDR methods lack optimization for the few-shot problem, while most meta-learning approaches ignore cross-domain information. Therefore, a novel approach called MetaCDR is proposed, which combines domain knowledge and meta-optimization to solve the cold-start problem.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Hanfei Wang, Yuan Zuo, Hong Li, Junjie Wu
Summary: This study proposes a novel framework for building cross-domain personality-based recommender systems, which effectively recognizes users' personality traits and improves recommendation performance through transfer learning.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Zafar Ali, Guilin Qi, Khan Muhammad, Siddhartha Bhattacharyya, Irfan Ullah, Waheed Abro
Summary: The large number of research articles on the Web poses challenges for researchers to find related works, leading to the development of network representation learning-based citation recommendation models. Our proposed model effectively utilizes semantic relations and contextual information within bibliographic networks, demonstrating significant improvements compared to baseline models on DBLP datasets.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Software Engineering
Hongwei Wei, Xiaohong Su, Cuiyun Gao, Weining Zheng, Wenxin Tao
Summary: Software cross-modal retrieval is a challenging direction in bug localization and code search. Previous studies used homogeneous semantic spaces, but it is difficult to accurately capture similar semantics due to the semantic gap. DeepHT proposes mapping multi-modal data into heterogeneous semantic spaces for better retrieval performance.
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Zechao Li, Jinhui Tang, Liyan Zhang, Jian Yang
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Article
Automation & Control Systems
Dong Zhang, Yunlian Sun, Qiaolin Ye, Jinhui Tang
IEEE TRANSACTIONS ON CYBERNETICS
(2020)
Article
Computer Science, Artificial Intelligence
Mengyin Wang, Xiaoyu Du, Xiangbo Shu, Xun Wang, Jinhui Tang
PATTERN RECOGNITION LETTERS
(2020)
Editorial Material
Engineering, Electrical & Electronic
Jiwen Lu, Yuxin Peng, Guo-Jun Qi, Jun Yu
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2020)
Article
Computer Science, Artificial Intelligence
Yao Luo, Zhong-Hui Duan, Jinhui Tang
Summary: The proposed bi-branch network achieves a balance between computational efficiency and restoration accuracy in dynamic scene deblurring by conducting heterogeneous transformations and incorporating a lightweight nonlocal fusion layer.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2021)
Article
Computer Science, Artificial Intelligence
Xiangbo Shu, Jinhui Tang, Guo-Jun Qi, Wei Liu, Jian Yang
Summary: This work proposes a novel Hierarchical Long Short-Term Concurrent Memory (H-LSTCM) model for recognizing human interactions in videos by combining individual dynamics and group dynamics to capture the long-term inter-related dynamics of human interactions. Experimental results validate the effectiveness of the proposed model.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Weixin Luo, Wen Liu, Dongze Lian, Jinhui Tang, Lixin Duan, Xi Peng, Shenghua Gao
Summary: This paper introduces an anomaly detection method based on Deep Neural Networks inspired by sparse coding, with a focus on Temporally-coherent Sparse Coding (TSC) and Sequential Iterative Soft-Thresholding Algorithm (SIATA). The approach utilizes a stacked Recurrent Neural Networks (sRNN) architecture for sparse coefficient optimization and further enhances it with sRNN-AE to improve efficiency and accuracy in anomaly detection. Extensive experiments have shown that sRNN-AE outperforms existing methods, making it an effective tool for anomaly detection.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Yunxiao Qin, Weiguo Zhang, Chenxu Zhao, Zezheng Wang, Xiangyu Zhu, Jingping Shi, Guojun Qi, Zhen Lei
Summary: This study introduces a novel meta-learning approach that leverages prior-knowledge and attention mechanism to reduce the few-shot cognition burden of meta-learners, while also addressing the Task-Over-Fitting issue.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Xiangbo Shu, Liyan Zhang, Yunlian Sun, Jinhui Tang
Summary: This article introduces a novel Graph LSTM-in-LSTM (GLIL) method for group activity recognition by modeling the person-level actions and group-level activity simultaneously, aiming to tackle the problem of group activity recognition in the multiple-person scene.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Xiangbo Shu, Liyan Zhang, Guo-Jun Qi, Wei Liu, Jinhui Tang
Summary: This paper proposes a novel Skeleton-Joint Co-Attention Recurrent Neural Networks (SC-RNN) framework that can capture both the spatial coherence among joints and the temporal evolution among skeletons for human motion prediction. By constructing a joint feature map, designing a Skeleton-Joint Co-Attention mechanism, and embedding an SCA-enhanced GRU variant, the experimental results demonstrate the superiority of the proposed method over competing methods.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Longquan Dai, Jinhui Tang
Summary: iFlowGAN learns an invertible flow through adversarial learning for image-to-image translation and addresses the redundancy issue between forward and backward mappings in existing generative models.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Xiangnan He, Jinhui Tang, Xiaoyu Du, Richang Hong, Tongwei Ren, Tat-Seng Chua
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Runde Li, Jinshan Pan, Min He, Zechao Li, Jinhui Tang
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Theory & Methods
Yunlian Sun, Jinhui Tang, Zhenan Sun, Massimo Tistarelli
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2020)
Article
Computer Science, Theory & Methods
Yunlian Sun, Jinhui Tang, Xiangbo Shu, Zhenan Sun, Massimo Tistarelli
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2020)