检索结果-内蒙古大学图书馆

Fake News Detection Based on Cross-Modal Ambiguity Computation and Multi-Scale Feature Fusion

computers, Materials & Continua 2025年第5期83卷 2659-2675页

作者： Jianxiang Cao Jinyang Wu Wenqian Shang Chunhua Wang Kang Song Tong Yi Jiajun Cai Haibin Zhu State Key Laboratory of Media Convergence and Communication Communication University of ChinaBeijing100024China School of Computer Science and Engineering Guangxi Normal UniversityGuilin541004China Department of Computer Science Nipissing UniversityNorth BayON P1B 8L7Canada

With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant *** social media content is often composed of both images and text,the use of multimodal approaches for fake news detection has gained significant *** solve the problems existing in previous multi-modal fake news detection algorithms,such as insufficient feature extraction and insufficient use of semantic relations between modes,this paper proposes the MFFFND-Co(Multimodal Feature Fusion Fake News Detection with Co-Attention Block)***,the model deeply explores the textual content,image content,and frequency domain ***,it employs a Co-Attention mechanism for cross-modal ***,a semantic consistency detectionmodule is designed to quantify semantic deviations,thereby enhancing the performance of fake news *** verified on two commonly used datasets,Twitter and Weibo,the model achieved F1 scores of 90.0% and 94.0%,respectively,significantly outperforming the pre-modified MFFFND(Multimodal Feature Fusion Fake News Detection with Attention Block)model and surpassing other baseline *** improves the accuracy of detecting fake information in artificial intelligence detection and engineering software detection.

关键词： Fake news detection multimodal cross-modal ambiguity computation multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

AR-Light: Enabling Fast and Lightweight Multi-User Augmented Reality via Semantic Segmentation and Collaborative View Synchronization

引用

IEEE Transactions on computers 2025年第6期74卷 2073-2086页

作者： Wen, Yu Shah, Aamir Bader Cao, Ruizhi Zhang, Chen Chen, Jiefu Wu, Xuqing Xie, Chenhao Fu, Xin University of Houston Department of Electrical and Computer Engineering HoustonTX77204 United States Beihang University School of Computer Science and Engineering Beijing100191 China University of Houston Department of Information Science Technology HoustonTX77204 United States

Multi-user Augmented Reality (MuAR) allows multiple users to interact with shared virtual objects, facilitated by exchanging environment information. Current MuAR systems rely on 3D point clouds for real-world analysis, view synchronization, object rendering, and movement tracking. However, the complexity of 3D point clouds leads to significant processing delays, with approximately 80% of overhead in commercial frameworks. This hampers usability and degrades user experience. Our analysis reveals that maintaining the facing side of the real-world scene in a stable environment provides sufficient information for virtual object placement and rendering. To address this, we introduce a lightweight quadtree structure, representing 2D scenes through semantic segmentation and geometry, as an alternative to 3D point clouds. Additionally, we propose a novel correction method to handle potential shifts in virtual object placement during view synchronization among users. Combining all designs, we implement a fast and lightweight MuAR framework named AR-Light and test our framework on commercial AR devices. The evaluation results on real-world applications demonstrate that AR-Light can achieve high performance in various real-world scenes while maintaining a comparable virtual object placement accuracy. © 1968-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Neural Regression Model for Predicting Thermal Conductivity of CNT Nanofluids with Multiple Base Fluids

引用

Journal of Thermal science 2021年第6期30卷 1908-1916页

作者： ZOU Hanying CHEN Cheng ZHA Muxi ZHOU Kangneng XIAO Ruoxiu FENG Yanhui QIU Lin ZHANG Xinxin WANG Zhiliang School of Energy and Environmental Engineering University of Science and Technology BeijingBeijing 100083China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China

High thermal conductivity of carbon nanotube nanofluids(k_(nf))has received great ***,the current researches are limited by experimental conditions and lack a comprehensive understanding of k_(nf) variation *** view of proposition of data-driven methods in recent years,using experimental data to drive prediction is an effective way to obtain k_(nf),which could clarify variation law of k_(nf) and thus greatly save experimental and time *** work proposed a neural regression model for predicting k_(nf).It took into account four influencing factors,including carbon nanotube diameter,volume fraction,temperature and base fluid thermal conductivity(k_(f)).Where,four conventional fluids with k_(f),including R113,water,ethylene glycol and ethylene glycol-water mixed liquid were considered as base fluid *** training this model,it can predict k_(nf) with different ***,change law of four influencing factors considered on the k_(nf) enhancement has discussed and the correlation between different influencing factors and k_(nf) enhancement is ***,compared with nine common machine learning methods,the proposed neural regression model shown the highest accuracy among these.

关键词： thermal conductivity CNT nanofluids Neural Regression Network multiple base fluids

来源：评论

学校读者我要写书评

暂无评论

Low-shot Video Object Segmentation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5538-5555页

作者： Yan, Kun Wei, Fangyun Dai, Shuyu Wu, Minghui Wang, Ping Xu, Chang Peking University School of Computer Science Beijing100871 China University of Sydney School of Computer Science DarlingtonNSW2008 Australia Peking University School of Software and Microelectronics Beijing100871 China Shanghai Artificial Intelligence Laboratory and Mininglamp Technology China Peking University National Engineering Research Center for Software Engineering Beijing100871 China Peking University School of Software and Microelectronics China China

Prior research in video object segmentation (VOS) predominantly relies on videos with dense annotations. However, obtaining pixel-level annotations is both costly and time-intensive. In this work, we highlight the potential of effectively training a VOS model using remarkably sparse video annotations - specifically, as few as one or two labeled frames per training video, yet maintaining near equivalent performance levels. We introduce this innovative training methodology as low-shot video object segmentation, abbreviated as low-shot VOS. Central to this method is the generation of reliable pseudo labels for unlabeled frames during the training phase, which are then used in tandem with labeled frames to optimize the model. Notably, our strategy is extremely simple and can be incorporated into the vast majority of current VOS models. For the first time, we propose a universal method for training VOS models on one-shot and two-shot VOS datasets. In the two-shot configuration, utilizing just 7.3% and 2.9% of labeled data from the YouTube-VOS and DAVIS benchmarks respectively, our model delivers results on par with those trained on completely labeled datasets. It is also worth noting that in the one-shot setting, a minor performance decrement is observed in comparison to models trained on fully annotated datasets. Code and models are available at https://***/yk-pku/Low-shot-VOS. © 1979-2012 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Improving Small License Plate Detection with Bidirectional Vehicle-Plate Relation 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Dai, Songkang Chen, Song-Lu Liu, Qi Zhu, Chao Liu, Yan Chen, Feng Yin, Xu-Cheng School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China EEasy Technology Company Ltd. Zhuhai China

ISBN: (数字)9783031533082

ISBN: (纸本)9783031533075

License plate detection is a critical component of license plate recognition systems. A challenge in this domain is detecting small license plates captured at a considerable distance. Previous researchers have proved that pre-detecting the vehicle can enhance small license plate detection. However, this approach only utilizes the one-way relation that the presence of a vehicle can enhance license plate detection, potentially resulting in error accumulation if the vehicle fails to be detected. To address this issue, we propose a unified network that can simultaneously detect the vehicle and the license plate while establishing bidirectional relationships between them. The proposed network can utilize the vehicle to enhance small license plate detection and reduce error accumulation when the vehicle fails to be detected. Extensive experiments on the SSIG-SegPlate, AOLP, and CRPD datasets prove our method achieves state-of-the-art detection performance, achieving an average detection AP0.5 of 99.5% on these three datasets, especially for small license plates. When incorporating a license plate recognizer that relies on character detection, we can achieve an average recognition accuracy of 95.9%, surpassing all comparative methods. Moreover, we have manually annotated the vehicles within the CRPD dataset and have made these annotations publicly available at https://***/kiki00007/CRPDV. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： License plates (automobile)

来源：评论

学校读者我要写书评

暂无评论

QoS-Oriented uplink OFDMA random access for the next-gen WLAN 3

QoS-Oriented uplink OFDMA random access for the next-gen WLA...

引用

2024 3rd International Conference on Electronic Information and communication engineering, EICE 2024

作者： Sun, Kexin Xie, Gang Liu, Yunbo School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing Beijing100876 China School of Measurement and Communication Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China

OFDMA, introduced by the IEEE 802.11ax standard, divides the channel into multiple resource units (RUs), enabling parallel access for multiple users. On this basis, we propose a QoS-oriented double arbitration random access (Q-DARA) scheme. This scheme ensures high-priority priority access through priority arbitration in the first phase and random code arbitration in the second phase. It can also greatly reduce collisions and effectively guarantee the QoS of high-priority traffic. Simulation shows that our proposed scheme has better performance on throughput and latency. Compared to the traditional EDCA, the throughput and latency increase by more than 70%. Compared to the PATB scheme, the throughput increases by about 20%, and the latency increases by about 23%. Moreover, our proposed scheme has almost no changes to the protocol and is suitable for 802.11ax and beyond. © Published under licence by IOP Publishing Ltd.

关键词： IEEE Standards

来源：评论

学校读者我要写书评

暂无评论

PAMC: POSTURE ALIGNMENT METHOD BASED ON CRBM FOR CAMERA ROBOT SYSTEM

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2024年第3期86卷 171-182页

作者： He, Jingjie Zhang, Wenjing Xu, Feng Artificial Intelligence Research Institute Beijing Institute of Petrochemical Technology 102600 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China

By acquiring the posture information of the rigid body with markers on the gripper frame, the camera motion on the robot flange can be controlled remotely. The essential step of posture alignment in teleoperation is to calibrate the transformation matrix of the robot base coordinate system and the world coordinate system of the optical tracking system. In this paper, a novel Posture Alignment Method Based on the Customized Rigid Body with Markers (PAMC) was proposed, which was an automatic, accurate and quick method to complete the posture alignment for related coordinate systems without non-systematic errors. PAMC was applied to teleoperation for the camera robot based on the customized rigid body with markers and optical tracking system. The comparative experiments prove that PAMC is better than manual method, with more stable, more flexible physical setting for reference coordinate system, and shorter operation time-consuming. Meanwhile, PAMC is more suitable for camera robot teleoperation than the existed automatic method due to arbitrary calibration posture and collision avoidance. © 2024, Politechnica university of Bucharest. All rights reserved.

关键词： Systematic errors

来源：评论

学校读者我要写书评

暂无评论

Automatic skin lesion classification using a novel densely connected convolutional network integrated with an attention module

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第7期14卷 8943-8956页

作者： Shan, Pufang Chen, Jialei Fu, Chong Cao, Lin Tie, Ming Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China Science and Technology on Space Physics Laboratory Beijing100076 China School of Computer Science The University of Auckland Auckland New Zealand

Automated skin lesion classification in dermoscopy images remains challenging due to the existence of artefacts and intrinsic cutaneous features, diversity of lesion morphology, insufficiency of training data, and class imbalance problem. To address these challenges, we propose a new densely connected convolutional network termed AttDenseNet-121, which is obtained by integrating the convolutional block attention module (CBAM) into DenseNet-121. CBAM is a simple yet efficient attention module, which is further improved by adding a novel pooling layer (multiscale-pooling) to effectively enhance its attention capability. The optimized CBAM strengthens the representation power of DenseNet-121 by emphasizing meaningful features and suppressing unnecessary ones, thus significantly enhancing the classification performance. Besides, to handle the imbalanced dataset, we employ an improved focal loss function rather than the traditional cross-entropy loss function to train AttDenseNet-121. The improved focal loss is calculated from a different perspective compared with the original focal loss. It makes the distribution of positive samples and negative samples in each batch the same as that in the original data, successfully mitigating the negative influence of class imbalance on this multi-class classification task. We conduct extensive experiments on the public benchmark dataset (HAM10000) and the results indicate that our proposed method achieves superior performance compared with that of the baselines and state-of-the-art algorithms. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

HASLB: Huge Page Allocation Strategy Optimized for Load-Balance in Parallel Computing Programs 20th

HASLB: Huge Page Allocation Strategy Optimized for Load-Bal...

引用

20th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2024

作者： Yue, Lei Wu, Tao Shen, Yang Zhang, Jin Zhang, Wenzhe School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410114 China College of Computer Science and Technology National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789819628292

Equitable resource allocation is currently considered as a key enabler for achieving complete parallelism in parallel computing. Optimized memory management mechanisms are crucial for load balance in parallel tasks. In some cases, the performance of Linux’s huge page management mechanism deteriorates when handling parallel tasks due to the nonhomogeneous allocation of memory resources among parallel processes. This research introduces HASLB, a huge page allocation strategy optimized for parallel programs. HASLB evaluates the status of parallel processes based on the count of huge pages acquired by each process and the number of page faults it encountered. Following the results of the analysis, huge pages are allocated using a method conducive to load balance. The problems in the Linux transparent huge page mechanism are optimized through this strategy, which limits the greedy allocation mechanism in some situations. HASLB achieves a reasonable allocation of memory resources among parallel processes with low overhead, benefiting the load balance of parallel computing programs. In addition, contiguous memory would be protected because of limiting the greedy allocation of huge pages. The parallel benchmark experiments show a maximum performance improvement of 6.4% compared to Linux in the BFS benchmark. In the IS benchmark program, huge page consumption exhibits a 9% reduction. © IFIP International Federation for Information Processing 2025.

关键词： Memory management

来源：评论

学校读者我要写书评

暂无评论

A Review of Smart Materials for the Boost of Soft Actuators,Soft Sensors,and Robotics Applications

引用

Chinese Journal of Mechanical engineering 2022年第2期35卷 12-27页

作者： Yufei Hao Shixin Zhang Bin Fang Fuchun Sun Huaping Liu Haiyuan Li School of mechanical engineering University of Science and Technology BeijingBeijing 100083China School of Engineering and Technology China University of Geosciences(Beijing)Beijing 100083China Department of Computer Science and Technology Tsinghua National Laboratory for Information Science and TechnologyTsinghua UniversityBeijing 100084China School of Automation Beijing University of Posts and TelecommunicationsBeijing 100876China

With the advance of smart material science,robotics is evolving from rigid robots to soft *** to rigid robots,soft robots can safely interact with the environment,easily navigate in unstructured fields,and be minimized to operate in narrow spaces,owning to the new actuation and sensing technologies developed by the smart *** the review,different actuation and sensing technologies based on different smart materials are analyzed and *** to the driving or feedback signals,actuators are categorized into electrically responsive actuators,thermally responsive actuators,magnetically responsive actuators,and photoresponsive actuators;sensors are categorized into resistive sensors,capacitive sensors,magnetic sensors,and optical waveguide *** introducing the principle and several robotic prototypes of some typical materials in each category of the actuators and *** advantages and disadvantages of the actuators and sensors are compared based on the categories,and their potential applications in robotics are also presented.

关键词： Smart material Soft robot Actuator Sensor

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：