检索结果-内蒙古大学图书馆

A Second-order C-bandpass Frequency Selective Surface

学校读者我要写书评

暂无评论

A Second-order C-bandpass Frequency Selective Surface

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Shenbing Wu Mingsheng Chen Meng Kong Liang Zhang Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University School of Electronic Engineering Huainan Normal University AnHui Province Key Laboratory of Simulation and Design for Electronic Information System Hefei Normal University

ISBN: (数字)9781728157337

ISBN: (纸本)9781728157344

A novel C-bandpass frequency selective surface(FSS) exhibiting miniaturized periodic parts is developed in this study. Such FSS acts as a bandpass filter at 4.03--7.87GHz. The proposed FSS exhibits miniaturization characteristics with the unit-cell dimension 0.12λ*0.12λ and the total thickness less than λ/28. Meantime, the simulation results reveal that the second-order FSS exhibits better stability under a variety of incident directions and polarization modes.

关键词： Frequency selective surfaces Microwave technology Surface waves Simulation Millimeter wave technology Stability analysis Periodic structures

Mobile Crowd-Sensing System Based on Participant Selection 15th

学校读者我要写书评

暂无评论

Mobile Crowd-Sensing System Based on Participant Selection

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Tu, Chunyu Han, Lei Wang, Leye Yu, Zhiyong College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou China Key Lab of High Confidence Software Technologies Peking University Beijing China

ISBN: (纸本)9783030642426

Mobile Crowdsensing (MCS) is often accompanied by various adverse objectives when performing data collection, which makes it difficult to collect accurate data of the entire target area with low cost. Therefore, how to collect a small part of the data to accurately infer the other data of the entire target area is a crucial issue. People’s daily trajectories usually follow a certain pattern, for example, students go to school, company employees go to work. This pattern allows us to find participants who often pass through fixed areas within a certain time span, leading their collected partial data are near optimal for the entire data collection task. This paper models the problem and develops multiple methods to improve the participant selection and the data recovery. Particularly, we use a random method, reinforcement learning, and greedy algorithm to handle this problem and compare the differences among these methods by experiments. © 2020, Springer Nature Switzerland AG.

关键词： Reinforcement learning

Pre-trained Prompt-driven Community Search

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ni, Li Xu, Hengkai Mu, Lin Zhang, Yiwen Luo, Wenjian Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Anhui Hefei230601 China School of Computer Science and Technology Anhui University Anhui Hefei230601 China School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China

The "pre-train, prompt" paradigm is widely adopted in various graph-based tasks and has shown promising performance in community detection. Most existing semi-supervised community detection algorithms detect communities based on known ones, and the detected communities typically do not contain the given query node. Therefore, they are not suitable for searching the community of a given node. Motivated by this, we adopt this paradigm into the semi-supervised community search for the first time and propose Pre-trained Prompt-driven Community Search (PPCS), a novel model designed to enhance search accuracy and efficiency. PPCS consists of three main components: node encoding, sample generation, and prompt-driven fine-tuning. Specifically, the node encoding component employs graph neural networks to learn local structural patterns of nodes in a graph, thereby obtaining representations for nodes and communities. Next, the sample generation component identifies an initial community for a given node and selects known communities that are structurally similar to the initial one as training samples. Finally, the prompt-driven fine-tuning component leverages these samples as prompts to guide the final community prediction. Experimental results on five real-world datasets demonstrate that PPCS performs better than baseline algorithms. It also achieves higher community search efficiency than semi-supervised community search baseline methods, with ablation studies verifying the effectiveness of each component of PPCS. Copyright © 2025, The Authors. All rights reserved.

关键词： Semi-supervised learning

LightXML: Transformer with dynamic negative sampling for high-performance extreme multi-label text classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jiang, Ting Wang, Deqing Sun, Leilei Yang, Huayi Zhao, Zhengyang Zhuang, Fuzhen SKLSDE and BDBC Lab Beihang University Beijing China Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing China Beijing Advanced Innovation Center for Imaging Theory and Technology Academy for Multidisciplinary Studies Capital Normal University Beijing China

Extreme Multi-label text Classification (XMC) is a task of finding the most relevant labels from a large label set. Nowadays deep learning-based methods have shown significant success in XMC. However, the existing methods (e.g., AttentionXML and X-Transformer etc) still suffer from 1) combining several models to train and predict for one dataset, and 2) sampling negative labels statically during the process of training label ranking model, which reduces both the efficiency and accuracy of the model. To address the above problems, we proposed LightXML, which adopts end-to-end training and dynamic negative labels sampling. In LightXML, we use generative cooperative networks to recall and rank labels, in which label recalling part generates negative and positive labels, and label ranking part distinguishes positive labels from these labels. Through these networks, negative labels are sampled dynamically during label ranking part training by feeding with the same text representation. Extensive experiments show that LightXML outperforms state-of-the-art methods in five extreme multi-label datasets with much smaller model size and lower computational complexity. In particular, on the Amazon dataset with 670K labels, LightXML can reduce the model size up to 72% compared to AttentionXML. Our code is available at http://***/kongds/LightXML. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

VideoLT: Large-scale Long-tailed Video Recognition

学校读者我要写书评

暂无评论

VideoLT: Large-scale Long-tailed Video Recognition

International Conference on Computer Vision (ICCV)

作者： Xing Zhang Zuxuan Wu Zejia Weng Huazhu Fu Jingjing Chen Yu-Gang Jiang Larry Davis Academy for Engineering and Technology Fudan University Shanghai Key Lab of Intel. Info. Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Inception Institute of Artificial Intelligence University of Maryland

ISBN: (纸本)9781665428132

label distributions in real-world are oftentimes long-tailed and imbalanced, resulting in biased models towards dominant labels. While long-tailed recognition has been extensively studied for image classification tasks, limited effort has been made for the video domain. In this paper, we introduce VideoLT, a large-scale long-tailed video recognition dataset, as a step toward real-world video recognition. VideoLT contains 256,218 untrimmed videos, annotated into 1,004 classes with a long-tailed distribution. Through extensive studies, we demonstrate that state-of-the-art methods used for long-tailed image recognition do not perform well in the video domain due to the additional temporal dimension in videos. This motivates us to propose FrameStack, a simple yet effective method for long-tailed video recognition. In particular, FrameStack performs sampling at the frame-level in order to balance class distributions, and the sampling ratio is dynamically determined using knowledge derived from the network during training. Experimental results demonstrate that FrameStack can improve classification performance without sacrificing the overall accuracy. Code and dataset are available at: https://***/17Skye17/VideoLT.

关键词： Training Knowledge engineering Computer vision Adaptation models Image recognition Codes Computational modeling

VideoLT: Large-scale long-tailed video recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Xing Wu, Zuxuan Weng, Zejia Fu, Huazhu Chen, Jingjing Jiang, Yu-Gang Davis, Larry Academy for Engineering and Technology Fudan University Shanghai Key Lab of Intel. Info. Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Inception Institute of Artificial Intelligence University of Maryland

关键词： Image recognition

Clean-label Backdoor Attacks on Video Recognition Models

学校读者我要写书评

暂无评论

Clean-Label Backdoor Attacks on Video Recognition Models

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Shihao Zhao Xingjun Ma Xiang Zheng James Bailey Jingjing Chen Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University School of Computing and Information Systems The University of Melbourne

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target class for any test examples that contain the trigger pattern. As such, backdoor attacks are hard to detect, and have raised severe security concerns in real-world applications. Thus far, backdoor research has mostly been conducted in the image domain with image classification models. In this paper, we show that existing image backdoor attacks are far less effective on videos, and outline 4 strict conditions where existing attacks are likely to fail: 1) scenarios with more input dimensions (eg. videos), 2) scenarios with high resolution, 3) scenarios with a large number of classes and few examples per class (a ``sparse dataset"), and 4) attacks with access to correct labels (eg. clean-label attacks). We propose the use of a universal adversarial trigger as the backdoor trigger to attack video recognition models, a situation where backdoor attacks are likely to be challenged by the above 4 strict conditions. We show on benchmark video datasets that our proposed backdoor attack can manipulate state-of-the-art video models with high success rates by poisoning only a small proportion of training data (without changing the labels). We also show that our proposed backdoor attack is resistant to state-of-the-art backdoor defense/detection methods, and can even be applied to improve image backdoor attacks. Our proposed video backdoor attack not only serves as a strong baseline for improving the robustness of video models, but also provides a new perspective for more understanding more powerful backdoor attacks.

关键词： Training Data models Toxicology Perturbation methods Training data Image resolution Pipelines

Improving fake news detection by using an entity-enhanced framework to fuse diverse multimodal clues

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qi, Peng Cao, Juan Li, Xirong Liu, Huan Sheng, Qiang Mi, Xiaoyue He, Qin Lv, Yongbiao Guo, Chenyang Yu, Yingchao Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Institute of Artificial Intelligence Hebi China Key Lab of DEKE Renmin University of China Beijing China Zhengzhou University Zhengzhou China Hangzhou ZhongkeRuijian Technology Co. Ltd. Hangzhou China

Recently, fake news with text and images have achieved more effective diffusion than text-only fake news, raising a severe issue of multimodal fake news detection. Current studies on this issue have made significant contributions to developing multimodal models, but they are defective in modeling the multimodal content sufficiently. Most of them only preliminarily model the basic semantics of the images as a supplement to the text, which limits their performance on detection. In this paper, we find three valuable text-image correlations in multimodal fake news: entity inconsistency, mutual enhancement, and text complementation. To effectively capture these multimodal clues, we innovatively extract visual entities (such as celebrities and landmarks) to understand the news-related high-level semantics of images, and then model the multimodal entity inconsistency and mutual enhancement with the help of visual entities. Moreover, we extract the embedded text in images as the complementation of the original text. All things considered, we propose a novel entity-enhanced multimodal fusion framework, which simultaneously models three cross-modal correlations to detect diverse multimodal fake news. Extensive experiments demonstrate the superiority of our model compared to the state of the art. Copyright © 2021, The Authors. All rights reserved.

关键词： Social networking (online)

Spatio-temporal interactive network: A knowledge-guided federated learning for fault propagation path identification

学校读者我要写书评

暂无评论

Process Safety and Environmental Protection 2025年 201卷

作者： Kai Zhong Xiang Peng Ting Lan Weihua Wang Institutes of Physical Science and Information Technology Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Anhui University Hefei 230601 China Institute of Plasma Physics Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei 230031 China Institutes of Physical Science and Information Technology Anhui University Hefei 230601 China

As a cutting-edge technology, federated learning (FL) demonstrates great potential in industrial fault propagation path identification, which uncovers the intrinsic relationships between variables by collaborating across multiple clients while preserving privacy, contributing to process safety and system optimization. However, existing FL methods do not take into account the interactive fusion of multi-scale features, resulting in insufficient feature mining and low utilization. In addition, purely data-driven FL naturally interpret the analyzed causality as propagation paths. In this paper, a knowledge-guided FL method with spatio-temporal interactive network is proposed for fault propagation path identification. First, we develop a knowledge-guided comprehensive graph construction module to provide the required adjacency matrix for subsequent model. After that, spatio-temporal soft attention prediction model is designed to mine spatio-temporal interactive information and the communication efficiency and model accuracy are further reconciled by residual-wise adaptive parameter aggregation scheme. Then, the causality is accurately characterized with the collaboration of mechanism knowledge and data, which makes the fault propagation path more explainable. Finally, in order to verify the effectiveness of the method, we carried out experiments on the simulation of Tennessee Eastman process and the real-world coal mill unit dataset.

关键词：