检索结果-内蒙古大学图书馆

Long and Recent Preference Learning with Recent-k Items Distribution for Recommender System

IEEE Transactions on Multimedia 2025年

作者： Gao, Yongbiao Niu, Sijie Lv, Guohua Ling, Miaogen Geng, Xin Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China Southeast University Ministry of Education Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application China University of Jinan Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing School of Information Science and Engineering China Nanjing University of Information Science and Technology School of Computer Science China Southeast University School of Computer Science and Engineering China

Reinforcement learning (RL) aims to formulate the recommendation task as a Markov decision process (MDP) and trains an agent to automatically learn the optimal recommendation policy from interaction trajectories through trial-and-error and reward mechanisms. However, most existing RL-based approaches overlook the correlation between items and the dynamics of user interests implied in temporally close interactions. Therefore, in this paper, we propose a reinforcement learning method that incorporates a "recent-k items"distribution to capture users' local preferences. Specifically, we model the output layer as two distinct branches. The "recent-k items"branch, formulated with a Kullback-Leibler divergence loss, learns the recent interests of users, whereas the other branch utilizes a one-step temporal difference error to capture long-term preferences. The proposed structure is integrated into deep Q-learning and actor-critics, resulting in two enhanced methods named R k Q and R k AC, respectively. Furthermore, a novel soft inter-reward is carefully designed to enhance the proposed method, and we theoretically prove the convergence of the proposed algorithm. We perform extensive experiments on two large real-world datasets and conduct further analysis of the influences of different action sequences, time intervals, and enhancement capabilities for state-of-the-art models. The experimental results demonstrate the efficacy of our proposed methods. © 1999-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection

arXiv

引用

arXiv 2024年

作者： Mo, Qijie Gao, Yipeng Fu, Shenghao Yan, Junkai Wu, Ancong Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

In incremental object detection, knowledge distillation has been proven to be an effective way to alleviate catastrophic forgetting. However, previous works focused on preserving the knowledge of old models, ignoring that images could simultaneously contain categories from past, present, and future stages. The co-occurrence of objects makes the optimization objectives inconsistent across different stages since the definition for foreground objects differs across various stages, which limits the model's performance greatly. To overcome this problem, we propose a method called "Bridge Past and Future" (BPF), which aligns models across stages, ensuring consistent optimization directions. In addition, we propose a novel Distillation with Future (DwF) loss, fully leveraging the background probability to mitigate the forgetting of old classes while ensuring a high level of adaptability in learning new classes. Extensive experiments are conducted on both Pascal VOC and MS COCO benchmarks. Without memory, BPF outperforms current state-of-the-art methods under various settings. The code is available at https://***/iSEE-laboratory/BPF. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection 41

ESNet: Evolution and Succession Network for High-Resolution ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

Event Argument Extraction with Two-Dimensional Enhanced Fusion Mechanism

引用

Computer engineering and Applications 2025年第10期61卷 111-119页

作者： Wang, Luxiang Chen, Yanping Huang, Hui Huang, Ruizhang Qin, Yongbin Engineering Research Center of Ministry of Education for Text Computing and Cognitive Intelligence School of Computer Science and Technology Guizhou University Guiyang550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China

Addressing the lack of interaction between trigger and arguments, and the lack of interaction within channels in existing studies of event argument extraction, this paper proposes a two-dimensional enhanced fusion mechanism for event argument extraction (W2-ARG) that incorporates a 2D enhanced fusion method. It inserts identifiers on both sides of a trigger word in a sentence, which encodes information about the event type. In the learning process, it is effective to enhance the interaction between trigger and argument, and encode the trigger separately to highlight its information in the sentence. The event argument extraction is implemented as a two-dimensional representation of label prediction. It has the advantage to capture semantic interactions of words at different distances through dilated convolution. Subsequently, a channel attention module is applied to enhance the interactions within the channel to strengthen the information transfer within the channel. Finally, the Laplace operator is utilized to highlight the positional features of event arguments in the semantic space to improve the performance. The proposed model is experimented on the ACE05-EN and ERE-EN datasets. Experimental results show clear performance improvement of the proposed model compared with other event argument extraction methods. © 2025 Journal of Computer engineering and Applications Beijing Co., Ltd.;Science Press. All rights reserved.

关键词： BERT channel attention event argument extraction Laplace operator sentence planarization representation

来源：评论

学校读者我要写书评

暂无评论

Salient Foreground-Aware Network for Person Search 16th

Salient Foreground-Aware Network for Person Search

引用

16th Chinese Conference on Biometric Recognition, CCBR 2022

作者： Chen, Hongxu Zhang, Quan Lai, Jianhuang The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China The Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China The Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangzhou510006 China

ISBN: (纸本)9783031202322

Person search aims to simultaneously localize and identify a query person from realistic and uncropped images, which consists of person detection and re-identification. In existing methods, the extracted features come from the low-quality proposals generated by the structure like Region Proposal Network (RPN), and convolution is used to learn local features in the process of extracting features while the receptive field cannot grasp the global structural information. We propose an end-to-end network embedded with our Salient Foreground-Aware Module (SFAM). Self-attention mechanism in SFAM allows for better capture of global information. Our network incorporates our embedding method for person detection and person re-identification, which can effectively optimize the process of extracting features and improve feature expression capabilities. We merge the above modules into our Salient Foreground-Aware Network (SFAN). Extensive experiments have shown that our SFAN significantly improves the performance of end-to-end models with acceptable time-consuming and achieves state-of-the-art results. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Multiscale Adaptive Multifractal Cross-Correlation Analysis of Multivariate Time Series

SSRN

引用

SSRN 2023年

作者： Jiang, Huanwen Wang, Xinyao Han, Guosheng Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan Xiangtan411105 China

In the real world, most of the time series generated from complex systems are nonlinear. To effectively study its fractal properties, in this work, we first generalize the adaptive fractal analysis (AFA) to the adaptive multifractal cross-correlation analysis (AMFCCA), which can be used to study the multifractal cross-correlation between two time series. Considering the complexity of time series from complex systems, we extend AMFCCA to the case of multivariate time series, namely multivariate adaptive multifractal cross-correlation analysis (MV-AMFCCA). In order to detect the multifractality on different time scales, we propose multiscale adaptive multifractal cross-correlation analysis of multivariate time series (MMV-AMFCCA). By the numerical simulation on synthetic multivariate processes, our method shows the theoretical validity. Furthermore, we applied these methods to the multifractal analysis of three pollutants in urban and suburban areas in Beijing. After removing the seasonal trend, we find that the urban and suburban systems both have multifractality, especially the multifractality of the urban system are more evident than the suburban systems, the degree of multifractality in spring and winter stronger than that in summer and autumn. Therefore, our methods are suitable for systems with multiple outputs and provide more comprehensive methods for characterizing autocorrelation and cross-correlation in multivariate time series. © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A credible individual behavior profiling method for online payment fraud detection 21

A credible individual behavior profiling method for online p...

引用

4th International Conference on Data Storage and Data engineering, DSDE 2021

作者： Cui, Jipeng Yan, Chungang Wang, Cheng Key Laboratory of the Ministry of Education for Embedded System and Service Computing Department of Computer Science and Engineering Tongji University China

ISBN: (纸本)9781450389303

Online payment fraud detection relies on a credible characterization of individual behaviors. Existing individual behavior profiling methods have three problems in credibility. Firstly, they solely regard users as individuals to model and fail to credibly characterize the whole behavior patterns of transactions. Secondly, they cannot make full use of the general information among similar individuals due to the heterogeneity of transaction attributes. Thirdly, they are not capable of utilizing the label information of transactions credibly. Faced with these challenges, we propose a credible method for individual behavior profiling that consists of two steps. The first step is the construction of the credible individual behavior profiling framework. To begin with, the concept of individuals is generalized and the credible transaction description is given. Afterwards, based on the co-occurrence information of transaction attributes, the credible behavior condition is defined to set a limit to individual behavior patterns. The second step is the implementation of the framework. For this purpose, the original fraud detection problem is transformed into a pseudo-recommender system problem with a co-occurrence mapping process. In order to guarantee the credible behavior constraint, a credible recommendation algorithm is designed to collaboratively restore both the ranking and rating information of the pseudo-rating matrices. Besides, an embedding based approach is adopted to parameterize the proposed model. Experiments on an online payment transaction dataset demonstrate the effectiveness of our proposed method. © 2021 ACM.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection 39

Transfer Learning of Real Image Features with Soft Contrasti...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liang, Ziyou Liu, Weifeng Wang, Run Wu, Mengjie Li, Boheng Zhang, Yuyang Wang, Lina Yang, Xinyi Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Nanyang Technological University Singapore NSFOCUS China

ISBN: (纸本)157735897X

In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In our preliminary experiments, we find that the artifacts in fake images always change with the development of the generative model, while natural images exhibit stable statistical properties. In this paper, we employ natural traces shared only by real images as an additional target for a classifier. Specifically, we introduce a self-supervised feature mapping process for natural trace extraction and develop a transfer learning based on soft contrastive loss to bring them closer to real images and further away from fake ones. This motivates the detector to make decisions based on the proximity of images to the natural traces. To conduct a comprehensive experiment, we built a high-quality and diverse dataset that includes generative models comprising GANs and diffusion models, to evaluate the effectiveness in generalizing unknown forgery techniques and robustness in surviving different transformations. Experimental results show that our proposed method gives 96.2% mAP significantly outperforms the baselines. Extensive experiments conducted on popular commercial platforms reveal that our proposed method achieves an accuracy exceeding 78.4%, underscoring its practicality for real-world application deployment. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Study on Dynamic Response of a Wave Energy Converter with Two Different Mooring Systems 10th

Comparative Study on Dynamic Response of a Wave Energy Conve...

引用

10th International Conference on Coastal and Ocean engineering, ICCOE 2023

作者： Lian, Yushun Wang, Rui Zheng, Jinhai Chen, WenXing Ma, Gang Yu, Jun Key Laboratory of Ministry of Education for Coastal Disaster and Protection Hohai University Nanjing210098 China College of Harbour Coastal and Offshore Engineering Hohai University Nanjing210098 China National Engineering Laboratory for Textile Fiber Materials and Processing Technology Zhejiang Sci-Tech University Zhejiang Hangzhou310018 China Yantai Research Institute Harbin Engineering University Yantai264006 China China Ship Scientific Research Center Wuxi214082 China

ISBN: (纸本)9789819753529

As the occurrence of utilization of fiber mooring ropes for wave energy converters (WECs), dynamic response of wave energy converters with fiber mooring ropes should be investigated for the station-keeping of the WECs. However, capturing the response of mooring systems of WECs is concerned due to the material nonlinearity of mooring lines and highly nonlinear motions of WECs. To understand the dynamic response of mooring systems of WECs, in the present study, a two-body floating point absorber is chosen as the investigated example of wave energy converters. Two types of mooring lines for the mooring system of the WEC are considered by utilizing the open-source WEC-sim code. One is the mooring system, which only uses chains. The other is the hybrid mooring system, which uses chains and polyester ropes. By performing time-domain analysis for the WEC with different mooring lines, the displacements of WEC and the tensions of mooring lines are obtained, respectively. By analyzing the results, the effects of different mooring lines on the WEC’s power take-off and safety are discussed. These investigations can not only contribute to capturing the dynamic response of the WEC’s mooring systems with fiber ropes, but also aid the industry to utilize fiber ropes in the mooring systems of WECs. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Dynamic response

来源：评论

学校读者我要写书评

暂无评论

Super-Broadband Rectifier with Expanded Input Power Range for Microwave Power Transmission 5

Super-Broadband Rectifier with Expanded Input Power Range fo...

引用

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Chen, Yan Liu, Xin Li, Yingsong Huang, Zhixiang The Fifth Research Institute of Miit Guangzhou511370 China College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

A super-broadband rectifier with expended input power range(IPR) for wireless power transfer (WPT) and radio frequency energy harvesting (RFEH) is proposed and analyzed. Meanwhile, using a simple impedance compression network consisting of quadruple microstrip lines (QMLICN) with the topology of the dickson charge pump, high power conversion efficiency (PCE) and super-broadband impedance matching are achieved. In addition, the IPRs of the rectifier are also extended. The simulation results indicate that an IPR of 12 - 25 dBm with a frequency range of 0.4 - 2.5 GHz (fractional bandwidth over 144%), the PEC exceeds 50% are realized, while at an input power of 19 dBm, the rectifier reaches a peak PCE of 74.2%. The rectifier covers the GSM 900, GSM 1800, 3G 2100 and WIFI 2400 bands, which design would have significant potential applications for the development of microwave power transmission systems. © 2022 IEEE.

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：