检索结果-内蒙古大学图书馆

Dual Test-Time Training for Out-of-Distribution Recommender System

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3312-3326页

作者： Yang, Xihong Wang, Yiqi Chen, Jin Fan, Wenqi Zhao, Xiangyu Zhu, En Liu, Xinwang Lian, Defu National University of Defense Technology College of Computer Science and Technology Changsha410073 China The Hong Kong University of Science and Technology School of Business and Management Hong Kong Hong Kong City University of Hong Kong Department of Data Science Hong Kong University of Science and Technology of China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology Hefei Anhui230000 China

Deep learning has been widely applied in recommender systems, which has recently achieved revolutionary progress. However, most existing learning-based methods assume that the user and item distributions remain unchanged between the training phase and the test phase. However, the distribution of user and item features can naturally shift in real-world scenarios, potentially resulting in a substantial decrease in recommendation performance. This phenomenon can be formulated as an Out-Of-Distribution (OOD) recommendation problem. To address this challenge, we propose a novel Dual Test-Time-Training framework for OOD Recommendation, termed DT3OR. In DT3OR, we incorporate a model adaptation mechanism during the test-time phase to carefully update the recommendation model, allowing the model to adapt specially to the shifting user and item features. To be specific, we propose a self-distillation task and a contrastive task to assist the model learning both the user's invariant interest preferences and the variant user/item characteristics during the test-time phase, thus facilitating a smooth adaptation to the shifting features. Furthermore, we provide theoretical analysis to support the rationale behind our dual test-time training framework. To the best of our knowledge, this paper is the first work to address OOD recommendation via a test-time-training strategy. We conduct experiments on five datasets with various backbones. Comprehensive experimental results have demonstrated the effectiveness of DT3OR compared to other state-of-the-art baselines. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Efficient and fine-grained access control with fully-hidden policies for cloud-enabled IoT

引用

Digital Communications and Networks 2025年第2期11卷 473-481页

作者： Li, Qi Liu, Gaozhan Zhang, Qianqian Han, Lidong Chen, Wei Li, Rui Xiong, Jinbo School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Key Laboratory of Cryptography of Zhejiang Province Hangzhou Normal University Hangzhou311121 China Tongda College of Nanjing University of Posts and Telecommunications Yangzhou225127 China Henan Key Laboratory of Network Cryptography Technology Zhengzhou450001 China School of Computer Science and Technology Xidian University Xi'an710071 China State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Normal University Xining810008 China Faculty of Software Fujian Normal University Fuzhou350108 China

Ciphertext-Policy Attribute-Based Encryption (CP-ABE) enables fine-grained access control on ciphertexts, making it a promising approach for managing data stored in the cloud-enabled Internet of Things. But existing schemes often suffer from privacy breaches due to explicit attachment of access policies or partial hiding of critical attribute content. Additionally, resource-constrained IoT devices, especially those adopting wireless communication, frequently encounter affordability issues regarding decryption costs. In this paper, we propose an efficient and fine-grained access control scheme with fully hidden policies (named FHAC). FHAC conceals all attributes in the policy and utilizes bloom filters to efficiently locate them. A test phase before decryption is applied to assist authorized users in finding matches between their attributes and the access policy. Dictionary attacks are thwarted by providing unauthorized users with invalid values. The heavy computational overhead of both the test phase and most of the decryption phase is outsourced to two cloud servers. Additionally, users can verify the correctness of multiple outsourced decryption results simultaneously. Security analysis and performance comparisons demonstrate FHAC's effectiveness in protecting policy privacy and achieving efficient decryption. © 2024 Chongqing University of Posts and Telecommunications

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

DMPNet: A lightweight remote sensing forest wildfire detection network based on multi-scale heterogeneous attention mechanism and dynamic scaling fusion strategy

引用

Digital Signal Processing: A Review Journal 2025年 164卷

作者： Long, Yingping Ding, Hongwei Zhu, Yuanjing Yang, Zhijun Li, Bo College of Information Technology Yunnan University Chenggong District Yunnan Province Kunming China College of Science and Technology Dianchi College of Yunnan University Xishan District Yunnan Province Kunming China The Key Laboratory of Internet of Things Technology and Application in Yunnan Province China

Unmanned Aerial Vehicle (UAV)-based remote sensing technology has emerged as a critical tool for forest fire detection. However, existing methods face significant challenges in simultaneously achieving high detection accuracy and real-time performance, particularly in scenarios characterized by multi-scale variations, non-stationary behaviors, and complex occlusions. To address these issues, we propose DMPNet, a lightweight neural network specifically designed for forest fire detection. Unlike conventional approaches that sacrifice accuracy for parameter reduction, DMPNet employs an optimized feature extraction architecture (PCSPNet), which not only preserves robust feature representation but also reduces the number of parameters by 16.67% (approximately 500K) compared to YOLOv8n. Furthermore, the dynamic fusion scaling strategy (DSFNet) is integrated into the network's neck to dynamically adjust the size and weight of feature maps, overcoming the limitations of static fusion. Additionally, DMPNet incorporates a multi-scale heterogeneous attention mechanism (MSHA), which effectively addresses occlusion issues through multi-scale contextual reasoning and cross-scale feature interactions. Experimental results demonstrate that DMPNet achieves an inference speed of 1.2 ms, with mAP50 reaching 86.8% and mAP@50-95 at 59%. When compared to YOLOv10n under similar parameter constraints, DMPNet improves mAP50 by 4.2% and surpasses MobileNet, GhostNet, and EfficientNet by over 20% in accuracy. By balancing model compactness, precision, and efficiency, DMPNet provides a robust solution for real-time forest fire monitoring. © 2025 Elsevier Inc.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

USDE-Based Task-Space Bilateral Teleoperator Control Design with Time Delay 16th

USDE-Based Task-Space Bilateral Teleoperator Control Design ...

引用

16th International Conference on Modelling, Identification and Control, ICMIC 2024

作者： Luo, Xin Ma, Jun Wang, Xian Na, Jing Xing, Yashan Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Faculty of Mechanical and Electrical Engineering Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Intelligent Control and Application Kunming University of Science and Technology Kunming650500 China

ISBN: (纸本)9789819617760

In this paper, we present a control strategy for bilateral teleoperators operated in the task space, which is designed to estimate the uncertain dynamics. To implement this proposed strategy, we develop a straightforward yet robust unknown system dynamics estimator (USDE) by incorporating a low-pass filtering operation. By using the USDE, we can eliminate the impact of unmodeled system dynamics without the need to measure the acceleration signal. Furthermore, the proposed USDE offers the advantages of requiring only one tuning parameter and being easily adjustable compared to conventional estimators. The convergence of the estimation error associated with the unmodeled system dynamics and the stability of the closed-loop control system are both rigorously demonstrated through Lyapunov’s theorem. Ultimately, the superior performance of our method, as evidenced by enhancing motion synchronization and stability, is confirmed through simulation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Infrared and visible image fusion with multi-resolution enhancement and dynamic weighted

引用

Optics and Laser technology 2025年 188卷

作者： Wang, Zhongqiang Wang, Chengchao Pu, Yuanyuan Peng, Jinjiang Zhao, Zhengpeng Gu, Jinjing College of Information Science and Engineering Yunnan University Kunming650500 China The Universities Key Laboratory of Internet of Things Technology and Application in Yunnan Kunming650500 China Yunnan Key Laboratory of low-light Night Vision Technology and Intelligent Visual Navigation Kunming650500 China

Infrared and visible image fusion (IVIF) aims to generate fused images by combining intensity and detailed information from source images. Existing IVIF methods typically rely on manually defined loss function weights and lack dynamic adaptability to complex scenes. Additionally, single-resolution approaches are limited in capturing complementary information across multiple resolutions. In this study, we propose an adaptive loss-weights and multi-resolution enhancement framework for IVIF, improve adaptability to complex scenes by integrating fine-grained details and background textures. Our approach introduces a multi-resolution detail enhancement (MRDE) module that processes extracted features at three distinct scales to enhance texture details. We also present a holographic fusion strategy composed of two modules: the Structural Integration Module (SIM) and Multi-resolution Texture Fusion Modul (MTFM), which effectively integrate structural and texture information across resolutions. Moreover, we propose an adaptive weighting dynamic balancing loss function that adjusts the emphasis on texture and structure during training. Extensive experiments demonstrate that our method outperforms state-of-the-art IVIF techniques, achieving superior visual balance and improved quantitative performance. © 2025

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Efficient energy-preserving methods for the Schrödinger-Boussinesq equation

Efficient energy-preserving methods for the Schrödinger-Bou...

引用

作者： Yan, Jinliang Zheng, Lianghong Lu, Fuqiang Zhang, Qiongyue Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry College of Mathematics and Computer Fujian354300 China Department of Information and Computer Technology No.1 Middle School of Nanping Fujian353000 China Changzhou Institute of Technology Changzhou213032 China

In this paper, we present two novel energy-preserving schemes for the Schrödinger-Boussinesq system based on the second-order Adams prediction-correction method. We first introduce supplementary variables to the initial model simultaneous its invariants to obtain a consistent and structural stable system. Then, we discretize the extended system by directly using the Fourier pseudo-spectral method in space and second-order Adams prediction-correction method in time to construct conservative schemes. Numerical results show that the proposed schemes can reach second-order accuracy and can conserve the discrete invariants very well. © 2022 John Wiley & Sons, Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Lightweight Ethylene-Vinyl Acetate Copolymer/Low-density Polyethylene/Carbon Nanotube Foams via Supercritical Carbon Dioxide Foaming for Piezoresistive Sensors

引用

Chinese Journal of Polymer Science (English Edition) 2025年 1-14页

作者： Hou, Hao-Hao He, Xin Ma, Hui Zhou, Hong-Fu Wen, Bian-Ying Wang, Xiang-Dong Deng, Ya-Feng Key Laboratory of Processing and Application of Polymeric Foams of China National Light Industry Council School of Light Industry Science and Engineering Beijing Technology and Business University Beijing100048 China School of Computer and Artificial Intelligence Beijing Technology and Business University Beijing100048 China

Flexible polymer-based foam sensors have significant potential for application in wearable electronics and motion monitoring. However, these prospects are hindered by the complex and unenvironmentally friendly manufacturing processes. In this study, we employed melt blending and supercritical carbon dioxide foaming to fabricate an ethylene-vinyl acetate copolymer (EVA)/low-density polyethylene (LDPE)/carbon nanotube (CNT) piezoresistive foam sensor. The cross-linking agent bis(tert-butyldioxyisopropyl) benzene and the conductive filler CNT were incorporated into the EVA/LDPE composite, successfully achieving a chemically cross-linked and physically entangled composite structure that significantly enhanced the storage modulus and complex viscosity. Additionally, the compressive strength of EVA/LDPE/CNT foam with 10 parts per hundred rubber (phr) CNT reached 1.37 MPa at 50% compression, marking a 340% increase compared to the 0.31 MPa of the CNT-free sample. Furthermore, the EVA/LDPE/CNT composite foams, which incorporated 10 phr CNT, were prepared under specific foaming conditions, resulting in an ultra-low density of 0.11 g/cm3 and a higher sensitivity, with a gauge factor of −2.3. The piezoresistive foam sensors developed in this work could accurately detect human motion, thereby expanding their applications in the field of piezoresistive foam sensors and providing an effective strategy for the advancement of high-performance piezoresistive foam sensors. © Chinese Chemical Society Institute of Chemistry, Chinese Academy of Sciences 2025.

关键词： Crosslinking

来源：评论

学校读者我要写书评

暂无评论

GBC: Gaussian-Based Colorization and Super-Resolution for 3D Reconstruction 19

GBC: Gaussian-Based Colorization and Super-Resolution for 3D...

引用

19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its applications in Industry, VRCAI 2024

作者： Liao, Jiecheng He, Shi Yuan, Yichen Zhang, Hui Department of Computer Science and Technology BNU-HKBU United International College ZhuHai China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai China

ISBN: (纸本)9798400713484

In this paper, we introduce GBC, an advanced framework for transforming low-resolution, monochrome video sequences into high-resolution, colorized, and geometrically accurate 3D models. GBC combines Bidirectional Optical Flow Super-Resolution (BOF-SR) for temporal super-resolution with a novel colorization approach, Temporal Optical Flow-based Colorization (TOF-CO), designed to enhance frame-to-frame temporal consistency. The integration of these modules with COLMAP-based 3D Gaussian splatting further extends GBC's capability to reconstruct high-fidelity 3D scenes. Additionally, we created a custom dataset tailored to the challenges of low-light, low-quality historical footage, enabling robust evaluation alongside public datasets. This solution offers a new approach to video restoration, advancing temporal coherence, color accuracy, and 3D scene fidelity. The source code is publicly available at https://***/ffftuanxxx/GBC. © 2024 ACM.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning-Based Image Mapping-Topology Optimization for Antenna Design

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Dou, Jiangling Gong, Hao Chen, Haokang Chen, Yujie Shen, Tao Song, Jian Kunming University of Science and Technology Faculty of Information Engineering and Automation Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming Yunnan650500 China College of Mechanical and Electrical Engineering Yunnan Electromechanical Vocational and Technical College China

A Reinforcement Learning (RL)-based Image Mapping Topology (IMT) optimization approach is proposed. To enable RL to optimize antenna topology and increase the efficiency of the optimization process. Two crucial components, Stratified Sampling Balance (SSB) and IMT are introduced. SSB is utilized to balance different types of data samples. IMT is utilized to facilitate the interaction between RL and simulation software, it also pretrains the actor network within the RL algorithm. This methodology allows the RL agent to acquire knowledge from the interaction of the antenna topology with the environment. Subsequently, the agent outputs antenna topology with the maximum reward signal. Compared with other machine learning-based optimization methods, the proposed method significantly alleviates the issue of learning inefficiency and reduces the exploration time for feasible solutions. To validate the effectiveness of the optimization method, a microstrip antenna is optimized. The measurement results show that the impedance bandwidth is doubled while maintaining the realized gain with fewer simulation samples and less optimization time. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stream Algorithm for Spatio-Temporal Fusion in Remote Sensing

引用

IEEE Geoscience and Remote Sensing Letters 2025年

作者： Wang, Shiying Zou, Xuechao Wang, Wentao Liu, Yao Zhang, Shun Cao, Tengfei Tao, Pin Qinghai University School of Computer Technology and Application Xining China Qinghai University Intelligent Computing and Application Laboratory of Qinghai Province China School of Computer Science & Technology Beijing China Tsinghua University Department of Computer Science and Technology Beijing China Ministry of Education Key Laboratory of Pervasive Computing China

The spatio-temporal fusion technology can effectively solve the problem of missing time series data. However, existing algorithms often struggle to accurately capture surface feature changes and fine details. To overcome these limitations, this paper introduces FemSTF, a flexible two-stream algorithm for remote sensing spatio-temporal fusion, which consists of three main stages: image sharpening, image fusion, and edge optimization. In the first stage, techniques such as interpolation, classification, and blending are employed to address missing pixel values caused by minimal input data. In the second stage, a two-stream strategy is introduced to enhance fusion accuracy, enabling the algorithm to capture regional detail changes with high sensitivity to surface variations. The third stage focuses on edge optimization, generating high-resolution predictive images under minimal input conditions (three images) while retaining rich texture and edge details. Notably, FemSTF achieves a performance comparable to that of methods requiring five input images. Experimental results demonstrate that FemSTF outperforms mainstream algorithms across multiple datasets. Ablation experiments confirm the effectiveness of the two-stream strategy, highlighting its role in enhancing remote sensing data processing accuracy. This study offers an efficient solution for spatio-temporal fusion, demonstrating great potential in the field. © 2004-2012 IEEE.

关键词： Spatio-temporal data

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：