检索结果-内蒙古大学图书馆

作者： Zhenwei Wang Wei Dong Bingbing Zhang Jianxin Zhang School of Computer Science and Engineering Dalian Minzu University SEAC Key Laboratory of Big Data Applied Technology Dalian Minzu University Institute of Machine Intelligence and Bio-Computing Dalian Minzu University School of Information and Communication Engineering Dalian University of Technology

Although recurrent neural networks(RNNs) are widely leveraged to process temporal or sequential data,they have attracted too little attention in current video action recognition ***,this work attempts to model the long-term spatio-temporal information of the video based on a variant of RNN,i.e.,higher-order ***,we propose a novel long-term spatio-temporal network(LSN) for solving this video task,the core of which integrates the newly constructed high-order ConvLSTM(HO-ConvLSTM) modules with traditional2D convolutional ***,each HO-Conv LSTM module consists of an accumulated temporary state(ATS) module as well as a standard Conv LSTM module,and several previous hidden states in the ATS module are accumulated to one temporary state that will enter the standard Conv LSTM to determine the output together with the current *** HO-Conv LSTM module can be inserted into different stages of the 2D convolutional neural network(CNN) in a plug-andplay manner,thus well characterizing the long-term temporal evolution at various spatial *** results on three commonly used video benchmarks demonstrate that the proposed LSN model can achieve competitive performance with the representative models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UJN-Traffic: A Benchmark dataset for Performance Evaluation of Traffic Element Classification 7th

UJN-Traffic: A Benchmark Dataset for Performance Evaluation ...

引用

7th International Conference on Life System Modeling and Simulation, LSMS 2021, and the 7th International Conference on Intelligent computing for Sustainable Energy and Environment, ICSEE 2021

作者： Li, Yan Han, Shi-Yuan Shen, Yuan Liu, Zhen Dong, Ji-Wen Xu, Tao University of Jinan Jinan250022 China China High-Resolution Earth Observation System Shandong Center of Data and Application University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China Land Spatial Data and Remote Sensing Technology Institute of Shandong Province Jinan250002 China

ISBN: (纸本)9789811672125

The detection of traffic element in remote sensing imagesplays an important role in the construction of traffic infrastructure, and can provide dynamic monitoring and quality evaluation for traffic construction projects. The convolutional neural network (CNN)-based method has achieved good performance in object detection in computer vision, which benefits from the popularity of large-scale datasets. However, the existing dataset can only be used for object detection, and the sample size and diversity need to be improved. These problems have brought challenges to the improvement and application of existing traffic element detection methods. This paper proposes a large-scale highresolution traffic element dataset based on multi-method detection analysis, and validates it based on the CNN-based object detection method. We screened more than 100 satellite images from high-resolution satellite images with a spatial resolution of 0.8 m. Manually labeled 5 categories and 100,000 traffic element samples. In the experiment, three CNN-based detection methods were used as the experimental baseline method. The experimental results proved effectiveness of the UJN-traffic traffic element dataset and provided a useful reference for traffic construction engineering and management. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

FCSR-GAN: Joint Face Completion and Super-Resolution via Multi-Task Learning

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

引用

IEEE Transactions on Biometrics, Behavior, and Identity science 2020年第2期2卷 109-121页

作者： Cai, Jiancheng Han, Hu Shan, Shiguang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Peng Cheng Laboratory Shenzhen518055 China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing100190 China

Combined variations containing low-resolution and occlusion often present in face images in the wild, e.g., under the scenario of video surveillance. While most of the existing face image recovery approaches can handle only one type of variation per model, in this work, we propose a deep generative adversarial network (FCSR-GAN) for performing joint face completion and face super-resolution via multi-task learning. The generator of FCSR-GAN aims to recover a high-resolution face image without occlusion given an input low-resolution face image with occlusion. The discriminator of FCSR-GAN uses a set of carefully designed losses (an adversarial loss, a perceptual loss, a pixel loss, a smooth loss, a style loss, and a face prior loss) to assure the high quality of the recovered high-resolution face images without occlusion. The whole network of FCSR-GAN can be trained end-to-end using our two-stage training strategy. Experimental results on the public-domain CelebA and Helen databases show that the proposed approach outperforms the state-of-the-art methods in jointly performing face super-resolution (up to 8×) and face completion, and shows good generalization ability in cross-database testing. Our FCSR-GAN is also useful for improving face identification performance when there are low-resolution and occlusion in face images. The code of FCSR-GAN is available at: https://***/swordcheng/FCSR-GAN. © 2019 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multi-User Probabilistic Semantic Communication with Semantic Compression Ratio Optimization

Multi-User Probabilistic Semantic Communication with Semanti...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Zhouxiang Zhao Zhaohui Yang Mingzhe Chen Changsheng You Qianqian Yang Wei Xu Zhaoyang Zhang College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Zhejiang Provincial Key Laboratory of Info. Proc. Commun. & Netw. (IPCAN) Hangzhou China Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral Gables FL USA Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China National Mobile Communications Research Laboratory Southeast University Nanjing China

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

In this paper, the problem of joint transmission and computation resource allocation for a multi-user probabilistic semantic communication (PSC) network is investigated. In the considered model, users employ semantic information extraction techniques to compress their large-sized raw data before transmitting them to a multi-antenna base station (BS). Our model represents the raw data through comprehensive knowledge graphs, utilizing shared probability graphs between users and the BS for efficient semantic compression. The resource allocation problem is formulated as an optimization problem with the objective of maximizing the sum of equivalent rate of all users, considering total power budget constraint. This joint optimization problem inherently addresses the delicate balance between transmission efficiency and computational complexity. To address this optimization challenge, we present an iterative algorithm in which the optimal solution for the semantic compression ratio of a specific user is determined at each iteration. Numerical results validate the effectiveness of the proposed scheme.

关键词： Conferences Computational modeling Semantics Knowledge graphs Probabilistic logic Information retrieval data models

来源：评论

学校读者我要写书评

暂无评论

Are Neural Ranking Models Robust?

arXiv

引用

arXiv 2021年

作者： Wu, Chen Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing NO. 6 Kexueyuan South Road Haidian District Beijing100190 China

Recently, we have witnessed the bloom of neural ranking models in the information retrieval (IR) field. So far, much effort has been devoted to developing effective neural ranking models that can generalize well on new data. There has been less attention paid to the robustness perspective. Unlike the effectiveness which is about the average performance of a system under normal purpose, robustness cares more about the system performance in the worst case or under malicious operations instead. When a new technique enters into the real-world application, it is critical to know not only how it works in average, but also how would it behave in abnormal situations. So we raise the question in this work: Are neural ranking models robust? To answer this question, firstly, we need to clarify what we refer to when we talk about the robustness of ranking models in IR. We show that robustness is actually a multi-dimensional concept and there are three ways to define it in IR: 1) The performance variance under the independent and identically distributed (I.I.D.) setting;2) The out-of-distribution (OOD) generalizability;and 3) The defensive ability against adversarial operations. The latter two definitions can be further specified into two different perspectives respectively, leading to 5 robustness tasks in total. Based on this taxonomy, we build corresponding benchmark datasets, design empirical experiments, and systematically analyze the robustness of several representative neural ranking models against traditional probabilistic ranking models and learning-to-rank (LTR) models. The empirical results show that there is no simple answer to our question. While neural ranking models are less robust against other IR models in most cases, some of them can still win 2 out of 5 tasks. This is the first comprehensive study on the robustness of neural ranking models. We believe the way we study the robustness as well as our findings would be beneficial to the IR community. We will also

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Neuromodulated Meta-Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Guo, Huijie Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Xiong, Hui Hua, Gang University of Chinese Academy of Sciences Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Wormpex AI Research LLC BellevueWA98004 United States

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at https://***/WangJingyao07/NeuronML. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

User Profiling for CSDN:keyphrase Extraction,User Tagging and User Growth Value Prediction

引用

data Intelligence 2019年第2期1卷 137-159页

作者： Guoliang Xing Hao Gao Qi Cao Xinyu Yue Bingbing Xu Keting Cen Huawei Shen Key Laboratory of Network Data Science and Technology Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

The Chinese Software Developer network(CSDN)is one of the largest information technology communities and service platforms in *** paper describes the user profiling for CSDN,an evaluation track of SMP Cup *** contains three tasks:(1)user document keyphrase extraction,(2)user tagging and(3)user growth value *** the first task,we treat keyphrase extraction as a classification problem and train a Gradient-Boosting-Decision-Tree model with comprehensive *** the second task,to deal with class imbalance and capture the interdependency between classes,we propose a two-stage framework:(1)for each class,we train a binary classifier to model each class against all of the other classes independently;(2)we feed the output of the trained classifiers into a softmax classifier,tagging each user with multiple *** the third task,we propose a comprehensive architecture to predict user growth *** contributions in this paper are summarized as follows:(1)we extract various types of features to identify the key factors in user value growth;(2)we use the semi-supervised method and the stacking technique to extend labeled data sets and increase the generality of the trained model,resulting in an impressive performance in our *** the competition,we achieved the first place out of 329 teams.

关键词： User profiling keyphrase extraction User tagging Growth value prediction Word embedding

来源：评论

学校读者我要写书评

暂无评论

A User Behavior-Based Random Distribution Scheme for Adversarial Example Generated CAPTCHA

A User Behavior-Based Random Distribution Scheme for Adversa...

引用

IEEE International Conference on Big data and Cloud computing (BdCloud)

作者： Wenwen Zheng Weiqi Wang Wei Ren Shiyuan Feng Shiqin Liu Yi Ren School of Computer Science China University of Geosciences Wuhan China Henan Key Laboratory of Network Cryptography Technology Zhengzhou China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Computing Science University of East Anglia Norwich U.K

The widespread and mature application of deep learning technology on human behavior analysis leads to the possibility that the Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) may not be able to accurately determine whether or not the user is human, which makes the distributed denial-of-service (DDoS) attacks launched by deep learning-based malicious automatic computer programs become possible. The CAPTCHA generated by adversarial examples can defend against the automatic identification by the deep learning-based method, however, if the deployed CAPTCHAs are all adversarial examples solely, the adversary has the chance to collect sufficient adversarial examples, which also causes security issues. In this paper, a user behavior-based random distribution scheme for adversarial example generated CAPTCHA is proposed to tackle the above sole distribution problem. Specifically, we generated two kinds of CAPTCHAs, one is normal and the other is generated by the fast gradient signed method (FGSM), i.e., the adversarial examples. Meanwhile, user behaviors are analyzed and associated with a reasonable probability model. According to the probability selection, the normal CAPTCHAs or strong CAPTCHAs will be delivered to the users. The experimental results illustrate that our scheme has an excellent ability to distinguish computers from humans. Thus, it can protect the CAPTCHA systems from DDoS attacks.

关键词： Computers Learning systems Deep learning Analytical models Computational modeling Denial-of-service attack Security

来源：评论

学校读者我要写书评

暂无评论

A dual-channel deep learning approach to continuous prediction of acute kidney injury in the intensive care unit

A dual-channel deep learning approach to continuous predicti...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xuetong Kong Peng Zhang Yunchao Ling Daqing Lv Jun Xu Guoqing Zhang Key Laboratory of Systems Health Science of Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou China CAS Key Laboratory of Computational Biology Bio-Med Big Data Center Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences Chinese Academy of Sciences Shanghai China Shanghai Southgene Technology Co. Ltd Shanghai China Shanghai Sixth People’s Hospital Shanghai China CAS Key Laboratory of Computational Biology Bio-Med Big Data Center Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences Chinese Academy of Sciences. Shanghai Sixth People’s Hospital Shanghai China

Acute Kidney Injury (AKI) often occurs in the intensive care units (ICU), where it is associated with high morbidity and mortality. Early and continuous prediction of AKI plays a crucial role in preventing AKI events, providing timely treatment, and reducing mortality. Continuously monitoring the high dimensional vital signs and lab measurements of the patients has always been a challenging task. In this study, we proposed a novel dual-channel deep learning approach named DC-AKI to address this challenge. DC-AKI extracts feature of temporal variables at different granularity, comprehensively and accurately obtains effective information, and finally continuous predicting risks of the patients. One channel of the model calculates corresponding local interactions of the variables with convolution kernels. The other channel uses the gated recurrent units (GRU) network and attention mechanism to obtains global interactions information among the variables. Finally, the model uses full connection layer to combine the representation vectors of the two channels, and uses Sigmoid classifier for prediction. We trained and tested our model on the MIMIC IV dataset, and the AUC ROC value of DC-AKI for predicting the risk of AKI in ICU patients 48 hours in advance was 0.9527, outperforming other methods. And our model was externally validated on the eICU dataset with an AUC ROC of 0.9054. These results demonstrate the robustness and accuracy of the model on different datasets. This finding provides clinicians with an opportunity to identify and manage patients with AKI in a timely manner, thereby improving patient prognosis. The implemented code is available online at https://***/BioMedBigdataCenter/DC-AKI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Strong quantum nonlocality without entanglement in multipartite quantum systems

引用

Physical Review A 2020年第4期102卷 042228-042228页

作者： Pei Yuan Guojing Tian Xiaoming Sun CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences 100190 Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 100049 China CAS Center of Excellence in Topological Quantum Computation Beijing 100049 China

In this paper, we generalize the concept of strong quantum nonlocality from two aspects. First, in a tripartite quantum system, we present a construction of strongly nonlocal quantum states containing 6(d−1)2 orthogonal product states in Cd⊗Cd⊗Cd and build 6d2−8d+4 product states in Cd⊗Cd⊗Cd+1, which have been proved to be strongly nonlocal. Obviously, both results turn out to be one order of magnitude smaller than the number of basis states d3 for d≥3. Second, we give explicit forms of strongly nonlocal orthogonal product basis in C3⊗C3⊗C3⊗C3 and C4⊗C4⊗C4⊗C4 quantum systems, where four is the largest known number of subsystems in which there exists strong quantum nonlocality without entanglement up to now. All the results positively answer the open problems raised by Halder et al. [Phys. Rev. Lett. 122, 040403 (2019)]; that is, there do exist a small number of quantum states that can demonstrate strong quantum nonlocality without entanglement.

关键词： Nonlocality

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：