检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhiliang Wu Hanyu Xuan Changchang Sun Weili Guan Kang Zhang Yan Yan School of Computer Science and Engineering Nanjing University of Science and Technology China School of Big Data and Statistics Anhui University China Department of Computer Science Illinois Institute of Technology USA School of Information Technology Monash University Australia Peng Cheng Laboratory China

Deep learning-based video inpainting has yielded promising results and gained increasing attention from re-searchers. Generally, these methods assume that the cor-rupted region masks of each frame are known and easily ob-tained. However, the annotation of these masks are labor-intensive and expensive, which limits the practical application of current methods. Therefore, we expect to relax this assumption by defining a new semi-supervised inpainting setting, making the networks have the ability of completing the corrupted regions of the whole video using the anno-tated mask of only one frame. Specifically, in this work, we propose an end-to-end trainable framework consisting of completion network and mask prediction network, which are designed to generate corrupted contents of the current frame using the known mask and decide the regions to be filled of the next frame, respectively. Besides, we introduce a cycle consistency loss to regularize the training parameters of these two networks. In this way, the completion network and the mask prediction network can constrain each other, and hence the overall performance of the trained model can be maximized. Furthermore, due to the natural existence of prior knowledge (e.g., corrupted contents and clear bor-ders), current video inpainting datasets are not suitable in the context of semi-supervised video inpainting. Thus, we create a new dataset by simulating the corrupted video of real-world scenarios. Extensive experimental results are reported to demonstrate the superiority of our model in the video inpainting task. Remarkably, although our model is trained in a semi-supervised manner, it can achieve compa-rable performance as fully-supervised methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distilling Script Knowledge from Large Language Models for Constrained Language Planning

arXiv

引用

arXiv 2023年

作者： Yuan, Siyu Chen, Jiangjie Fu, Ziquan Ge, Xuyang Shah, Soham Jankowski, Charles Robert Xiao, Yanghua Yang, Deqing School of Data Science Fudan University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China System Inc. Brain Technologies Inc. Fudan-Aishu Cognitive Intelligence Joint Research Center China

In everyday life, humans often plan their actions by following step-by-step instructions in the form of goal-oriented scripts. Previous work has exploited language models (LMs) to plan for abstract goals of stereotypical activities (e.g., "make a cake"), but leaves more specific goals with multi-facet constraints understudied (e.g., "make a cake for diabetics"). In this paper, we define the task of constrained language planning for the first time. We propose an over-generate-then-filter approach to improve large language models (LLMs) on this task, and use it to distill a novel constrained language planning dataset, CoScript, which consists of 55,000 scripts. Empirical results demonstrate that our method significantly improves the constrained language planning ability of LLMs, especially on constraint faithfulness. Furthermore, CoScript is demonstrated to be quite effective in endowing smaller LMs with constrained language planning ability. 1 © 2023, CC BY-NC-SA.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Invisible Watermark and Hypothesis Testing for Multi-Ownership Verification Framework of Deep Neural Network

Invisible Watermark and Hypothesis Testing for Multi-Ownersh...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Ruoxi Wang Yujia Zhu Daoxun Xia School of Big Data and Computer Science Guizhou Normal University Key Laboratory of Information and Computing Science Guizhou Province Guizhou Normal University Engineering Laboratory for Applied Technology of Big Data in Education Guizhou Normal University Guiyang China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

With the rapid development of information technology, artificial intelligence models have become the core asset of tech giants, highlighting the importance of copyright protection. Black-box watermarking has gained attention due to its ability to verify the legality of models remotely without relying on internal model information. The challenges lie in embedding and verifying watermarks without accessing internal model parameters, while ensuring the robustness and stealth of the watermark. This paper focuses on discussing effective ways to protect the copyright of black-box watermarking models and detect and prevent unauthorized user behavior that infringes on model ownership. Therefore, this paper proposes a multi-ownership verification framework based on invisible watermark and hypothesis testing, which mainly consists of two parts: watermark generation and copyright verification. The watermark generation uses a dynamic watermarking method to generate invisible backdoor watermark and verifies copyright through hypothesis testing. This framework has high assurance and effectiveness under various models of CIFAR-10 and MNIST datasets and shows strong robustness in VGG and Resnet model pruning attacks. This research provides new ideas and methods for the protection of model copyrights in deep neural networks.

关键词： Deep learning Education Closed box Watermarking Artificial neural networks Copyright protection Benchmark testing Robustness Protection Information technology

来源：评论

学校读者我要写书评

暂无评论

MPC-based Motion Control of Underwater Vehicle with Fixed Depth 4

MPC-based Motion Control of Underwater Vehicle with Fixed De...

引用

2022 4th International Conference on Electronic Engineering and Informatics, EEI 2022

作者： Yu, Wenjie Liang, Quan Xiong, Neng Hong, Chuanbo School of Computer Science and Mathematics Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China

ISBN: (纸本)9783800759231

Aiming at the underactuated and nonlinear system of underwater vehicle, this paper studies the control of depth-fixing motion. The first is to analyze the kinematics and dynamics of the underwater vehicle, so as to establish the corresponding depth-fixing motion control model. Secondly, the controller based on the model predictive control algorithm is designed in the Simulink platform to realize the depth-fixing motion control and anti-disturbance test of the underwater vehicle. At the same time, the PID algorithm is introduced to compare the step response of the two. Finally, according to the simulation results, it can be concluded that the controller based on the MPC algorithm can effectively reduce the overshoot of the underwater vehicle, the control system can converge to the target value faster, and has strong anti-interference ability. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-guided Mutual Consistency Training for Semi-supervised Biomedical Relation Extraction

Uncertainty-guided Mutual Consistency Training for Semi-supe...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Mao, Bing Jia, Chang Huang, Yucheng He, Kai Wu, Jialun Gong, Tieliang Li, Chen Xi'an Jiaotong University School of Computer Science and Technology Xi'an China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an China

ISBN: (纸本)9781665468190

Biomedical relation extraction seeks to automatically extract biomedical relations from biomedical text, which plays an important role in biomedical studies. However, constructing high-quality biomedical annotation data is not only time-consuming but also requires a high level of knowledge in the biomedical field. To alleviate this problem, Semi-supervised Biomedical Relation Extraction aims to extract relation facts from the limited labeled data and the more readily available unlabeled samples. Existing works can be roughly categorized as self-training methods and self-ensembling methods. The former aims to generate pseudo labels, which may lead to the gradual drift problem. The latter aims to encourage the output of one model to be consistent with the other model, where the acquisition of the model is tedious. To alleviate these issues, we propose a novel Uncertainty-Guided Mutual Consistency Training framework(UG-MCT) for semi-supervised Biomedical relation extraction. Specifically, our framework consists of two models with the same structure, which differ only when updating their weights, and then an intersecting pseudo-label mechanism is designed to convert the prediction discrepancies of the two models into mutual consistency training loss, thus promoting the consistency of model predictions. In addition, we utilize uncertainty as guided information to assist the model in focusing on the confident pseudo labels and mitigate the noise of inaccurate pseudo labeling during training. Thus, our model is very simple and efficient while mitigating the noise introduced by pseudo-labels. UG-MCT is evaluated on multiple datasets in different settings and the experimental results demonstrate that our method is highly effective in semi-supervised biomedical relation extraction compared to the state-of-the-art. © 2022 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Exploring the Privacy Protection Capabilities of Chinese Large Language Models

arXiv

引用

arXiv 2024年

作者： Yang, Yuqi Huang, Xiaowen Sang, Jitao School of Computer Science and Technology Beijing Jiaotong University Beijing China School of Computer Science and Technology Beijing Jiaotong University Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Key Laboratory of Big Data Artificial Intelligence in Transportation Beijing Jiaotong University Ministry of Education Beijing China

Large language models (LLMs), renowned for their impressive capabilities in various tasks, have significantly advanced artificial intelligence. Yet, these advancements have raised growing concerns about privacy and security implications. To address these issues and explain the risks inherent in these models, we have devised a three-tiered progressive framework tailored for evaluating privacy in language systems. This framework consists of progressively complex and in-depth privacy test tasks at each tier. Our primary objective is to comprehensively evaluate the sensitivity of large language models to private information, examining how effectively they discern, manage, and safeguard sensitive data in diverse scenarios. This systematic evaluation helps us understand the degree to which these models comply with privacy protection guidelines and the effectiveness of their inherent safeguards against privacy breaches. Our observations indicate that existing Chinese large language models universally show privacy protection shortcomings. It seems that at the moment this widespread issue is unavoidable and may pose corresponding privacy risks in applications based on these models. © 2024, CC BY.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Enhancing Real-time Facial Sentiment Recognition Systems through Deep Learning Architectures

Enhancing Real-time Facial Sentiment Recognition Systems thr...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： K Geetha Rani Rajkumar Selvaraj Aravind Swaminathan R Surendran Department of Computer Science and Engineering Jain (Deemed to be University) Bangalore India Department of Data Science Middlesex University (Dubai Campus) Dubai United Arab Emirates Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Facial Emotion Recognition (FER) has emerged as a pivotal domain within computer vision, with applications spanning diverse fields such as human-computer interaction, mental health monitoring, and security systems. While significant strides have been made in recent years, accurate recognition of nuanced emotions, particularly fear, remains a challenging task. This research contributes to the advancement of FER technology, paving the way for more sophisticated and empathetic human-computer interactions. By discussing about the reliable and efficient methods for real-time fear detection, this study enables the potential to revolutionize various applications, including mental health monitoring, security surveillance, and autonomous vehicles.

关键词： Human computer interaction Emotion recognition Accuracy Face recognition Surveillance Transfer learning Mental health Real-time systems Security Videos

来源：评论

学校读者我要写书评

暂无评论

Cloud-magnetic resonance imaging system:In the era of 6G and artificial intelligence

引用

Magnetic Resonance Letters 2025年第1期5卷 52-63页

作者： Yirong Zhou Yanhuang Wu Yuhan Su Jing Li Jianyu Cai Yongfu You Jianjun Zhou Di Guo Xiaobo Qu Department of Electronic Science Intelligent Medical Imaging R&D CenterFujian Provincial Key Laboratory of Plasma and Magnetic ResonanceNational Institute for Data Science in Health and MedicineXiamen UniversityXiamen361104China Department of Electronic Science Key Laboratory of Digital Fujian on IoT CommunicationXiamen UniversityXiamen361104China Shanghai Electric Group Co. LtdShanghai200002China China Telecom Group Quanzhou362018China China Mobile Group Xiamen361009China Department of Radiology Zhongshan Hospital(Xiamen)Fudan UniversityXiamen Municipal Clinical Research Center for Medical ImagingFujian Province Key Clinical Specialty Construction Project(Medical Imaging Department)Xiamen Key Laboratory of Clinical Transformation of Imaging Big Data and Artificial IntelligenceXiamen361006China School of Computer and Information Engineering Xiamen University of TechnologyXiamen361024China

Magnetic resonance imaging(MRI)plays an important role in medical diagnosis,generating petabytes of image data annually in large *** voluminous data stream requires a significant amount of network bandwidth and extensive storage ***,local data processing demands substantial manpower and hardware *** isolation across different healthcare institutions hinders crossinstitutional collaboration in clinics and *** this work,we anticipate an innovative MRI system and its four generations that integrate emerging distributed cloud computing,6G bandwidth,edge computing,federated learning,and blockchain *** system is called Cloud-MRI,aiming at solving the problems of MRI data storage security,transmission speed,artificial intelligence(AI)algorithm maintenance,hardware upgrading,and collaborative *** workflow commences with the transformation of k-space raw data into the standardized Imaging Society for Magnetic Resonance in Medicine Raw data(ISMRMRD)***,the data are uploaded to the cloud or edge nodes for fast image reconstruction,neural network training,and automatic ***,the outcomes are seamlessly transmitted to clinics or research institutes for diagnosis and other *** Cloud-MRI system will save the raw imaging data,reduce the risk of data loss,facilitate inter-institutional medical collaboration,and finally improve diagnostic accuracy and work efficiency.

关键词： Magnetic resonance imaging Cloud computing 6G bandwidth Artificial intelligence Edge computing Federated learning Blockchain

来源：评论

学校读者我要写书评

暂无评论

Green Energy AI Cloud: Intelligent Community-Based Electricity Management System 8

Green Energy AI Cloud: Intelligent Community-Based Electrici...

引用

8th IEEE International Conference on Energy Internet, ICEI 2024

作者： Mehta, Yukta Lo, Vincent Mehta, Vijen Agarwal, Kunal Madabathula, Charan Teja Gao, Jerry San Jose State University Department of Applied Data Science San JoseCA United States Evergreen Valley High School Department of Analysis San JoseCA United States San Jose State University Department of Computer Engineering San JoseCA United States

ISBN: (纸本)9798331523558

According to the U.S. Energy Information Administration, 60 percent of the world's electricity is generated from fossil fuels, 18 percent from nuclear power, and only 21 percent from green energy resources. These statistics highlight the pressing need to transition to renewable energy for a sustainable future. However, a major challenge that arises from this increased demand for green energy is the risk of electricity shortage. Overcoming this challenge requires a shift from conventional energy management to an AI-based electricity management system that can more efficiently balance supply and demand. In this paper, we have developed a comprehensive cloud-based Green AI service Management System to accommodate three important aspects of green energy services: electricity consumption, electricity generation, and shortage analysis. In this system, we propose using a community-based model that manages and analyzes multiple buildings' energy usage, allowing the model to be trained further via distributed and aggregated training. The models developed for these components use three approaches: deep learning, machine learning, and reinforcement algorithms, and achieved a shortage analysis accuracy of 98.2 percent. The model is deployed on the cloud and results are accessible from the user interface. Overall, we provide a unique Green AI solution to the market using a system that can handle various aspects of green energy and gives better accuracy than existing systems. © 2024 IEEE.

关键词： Consumption prediction Electricity Management System Electricity shortage forecasting Green AI Usage prediction

来源：评论

学校读者我要写书评

暂无评论

A label-guided contrastive capsule network for few-shot text classification

引用

Neural Computing and Applications 2025年 1-26页

作者： Xu, Yang Xu, Xiaolong Jiangsu Key Laboratory of Big Data Security Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210023 China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China

Few-shot text classification involves transferring knowledge from a limited dataset to perform classification tasks in unseen domains. Existing metric-based meta-learning models, such as prototypical networks, have shown to be effective. However, these models fail to separate embeddings of similar classes, resulting in performance stagnation. Meanwhile, traditional text classification recently has succeeded with the support of extensive prior knowledge from large language models. However, in few-shot scenarios, it is challenging to generate discriminative sentence embeddings using pre-trained models, often leading to overfitting issues. Furthermore, random support set sampling adversely affects prototype quality, resulting in inaccurate category representations. In this paper, we propose the label-guided contrastive capsule network (LGCCN) to address these issues. LGCCN introduces label information as external knowledge for each category, comprising a label-guided contrastive clustering module (LGCCM) and a label-guided prototype enhancement module (LGPEM). LGCCM employs label information to guide a contrastive clustering process, using labels as anchors to enhance the process, yielding discriminative sentence embeddings from the pre-trained model. LGPEM iteratively generates a robust prototype with label guidance, significantly reducing the impact of random support set sampling. The proposed LGCCN was thoroughly evaluated on seven benchmark datasets from diverse application domains. Experimental results demonstrate that LGCCN outperforms the state-of-the-art (SOTA) method by 9.7% in 1-shot tasks and 1.1% in 5-shot tasks on news datasets. Additionally, on intent recognition datasets, LGCCN surpasses the SOTA with a 3.3% improvement in 1-shot tasks and a 1.4% improvement in 5-shot tasks, highlighting its superior performance in few-shot text classification. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Contrastive Learning

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：