检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition 1

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Su, Yukun Lin, Guosheng Zhu, Jinhui Wu, Qingyao School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Beijing China Nanyang Technological University Singapore Singapore

ISBN: (数字)9783030585488

ISBN: (纸本)9783030585471

This paper introduces a new method for recognizing violent behavior by learning contextual relationships between related people from human skeleton points. Unlike previous work, we first formulate 3D skeleton point clouds from human skeleton sequences extracted from videos and then perform interaction learning on these 3D skeleton point clouds. A novel Skeleton Points Interaction Learning (SPIL) module, is proposed to model the interactions between skeleton points. Specifically, by constructing a specific weight distribution strategy between local regional points, SPIL aims to selectively focus on the most relevant parts of them based on their features and spatial-temporal position information. In order to capture diverse types of relation information, a multi-head mechanism is designed to aggregate different features from independent heads to jointly handle different types of relationships between points. Experimental results show that our model outperforms the existing networks and achieves new state-of-the-art performance on video violence datasets. © 2020, Springer Nature Switzerland AG.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Unique on Facebook: Formulation and evidence of (nano)targeting individual users with non-PII data

arXiv

引用

arXiv 2021年

作者： González-Cabañas, José Cuevas, Ángel Cuevas, Rubén López-Fernández, Juan García, David Universidad Carlos III de Madrid UC3M-Santander Big Data Institute GTD System & Software Engineering Graz University of Technology

The privacy of an individual is bounded by the ability of a third party to reveal their identity. Certain data items such as a passport ID or a mobile phone number may be used to uniquely identify a person. These are referred to as Personal Identifiable Information (PII) items. Previous literature has also reported that, in datasets including millions of users, a combination of several non-PII items (which alone are not enough to identify an individual) can uniquely identify an individual within the dataset. In this paper, we define a data-driven model to quantify the number of interests from a user that make them unique on Facebook. To the best of our knowledge, this represents the first study of individuals' uniqueness at the world population scale. Besides, users' interests are actionable non-PII items that can be used to define ad campaigns and deliver tailored ads to Facebook users. We run an experiment through 21 Facebook ad campaigns that target three of the authors of this paper to prove that, if an advertiser knows enough interests from a user, the Facebook Advertising Platform can be systematically exploited to deliver ads exclusively to a specific user. We refer to this practice as nanotargeting. Finally, we discuss the harmful risks associated with nanotargeting such as psychological persuasion, user manipulation, or blackmailing, and provide easily implementable countermeasures to preclude attacks based on nanotargeting campaigns on Facebook. © 2021, CC BY-NC-ND.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Research on the Improved YOLOv5 Algorithm Fall Monitoring System for Home Care for the Elderly

Research on the Improved YOLOv5 Algorithm Fall Monitoring Sy...

引用

Computer Information Science and Application Technology (CISAT), International Conference on

作者： Wanchao Xu Junchao Zhang Xinyu Zhang Fengxia Li Jinyi Tao Rongli Zhao College of Electrical and Power Engineering Taiyuan University of Technology Taiyuan Shanxi China Shanxi Provincial Engineering Research Center of Electric Drive and Internet of Things Taiyuan Shanxi College of Software Nanjing University Nanjing Jiangsu National Intelligent Lighting and Smart Wearable Technology Innovation Center Taiyuan Shanxi Province Engineering Technology Research Center of Smart City Lighting Data Sharing and Public Service Platform Based on Big DataShanxi Province Taiyuan Shanxi Province Research Institute of New Materials and Chemical Engineering Shanxi Zhejiang University Taiyuan Shanxi

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

In view of the risk of fall for the elderly in the home care environment, a surveillance video display fall detection method of the improved YOLOv5 algorithm is improved, and the Transformer module that increases the human attention mechanism is combined with the CSPDarknet structure of the backbone part of the YOLOv5 algorithm. The system collects video data through the camera, trains and verifies the video data, and then judges the action and posture of the target person. It connects the WIFI module of Orange School to send the action and posture information to the guardian’s mobile phone to remind the guardian to timely treat the person who fell down, so as to improve the rescue efficiency. On the basis of improving the algorithm structure, the loss function was improved and conducted repeated training. The experimental results showed that the improved algorithm mAP improved by 2.8%, the $F 1$ score by 2.2%, the number of processing frames per second by 10% during inference, and achieved the fall detection accuracy of 98.6%.

关键词： YOLO Training Accuracy Attention mechanisms Surveillance Transformers Inference algorithms Older adults Fall detection Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

Effects of different hormones on germination and callus induction of hemp seeds 2

Effects of different hormones on germination and callus indu...

引用

2020 2nd International Conference on Advances in Civil engineering, Energy Resources and Environment engineering, ACCESE 2020

作者： He, Bingqing Shen, Penglin Zheng, Hongjuan Chu, Yi Guan, Jinqiu Li, Lan College of Science and Life Jiamusi University Jiamusi City Heilongjiang Province154007 China College of Big Data and Software Engineering Wuzhou University Wuzhou City Guangxi Province543000 China

The purpose was to induce and treat hemp seeds and callus, compare the methods to increase the germination rate of hemp seed, obtain suitable disinfectant for hemp seed, and different hormone ratios to promote callus growth. GA3, 6-BA, and IAA were used to induce hemp seed germination, and the effects of different hormones and different concentrations on hemp seed germination were studied. Tissue culture was used to induce hemp seeds to select suitable hemp seeds disinfectant and time;callus was induced by using hemp aseptic seedling leaves. GA3 with a concentration of 20-80mg/L and IAA with a concentration of 20-40mg/L can promote the germination of hemp seeds;the best disinfection method of hemp seeds is: 70% ethanol for 1min + 10% NaClO for 18min;the most the combinations beneficial to callus growth were: 2.0mg/L 6-BA+0.5mg/L NAA. GA3 and low-concentration IAA can promote the germination of hemp seeds;the combination of 70% ethanol and 10% sodium hypochlorite has the best disinfection effect on hemp seeds;6-BA+NAA can obtain good quality hemp seeds hemp callus. © Published under licence by IOP Publishing Ltd.

关键词： Germination

来源：评论

学校读者我要写书评

暂无评论

pFedLVM: A Large Vision Model (LVM)-Driven and Latent Feature-Based Personalized Federated Learning Framework in Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Kou, Wei-Bin Lin, Qingfeng Tang, Ming Xu, Sheng Ye, Rongguang Leng, Yang Wang, Shuai Li, Guofa Chen, Zhenyu Zhu, Guangxu Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Research Institute of Electronic Science and Technology University of Electronic Science and technology Chengdu China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

Deep learning-based Autonomous Driving (AD) semantic segmentation (SSeg) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD SSeg model (known as FedAD system), conventional models often struggle with under-fitting as the amount of accumulated training data progressively increases. To address this issue, instead of conventional small models, employing Large Vision Models (LVMs) in FedAD is a viable option for better learning of representations from a vast volume of data. However, implementing LVMs in FedAD introduces three challenges: (I) the extremely high communication overheads associated with transmitting LVMs between participating vehicles and a central server;(II) lack of computing resource to deploy LVMs on each vehicle;(III) the performance drop due to LVM focusing on shared features but overlooking local vehicle characteristics. To overcome these challenges, we propose pFedLVM, a LVM-Driven, Latent Feature-Based Personalized Federated Learning framework. In this approach, the LVM is deployed only on central server, which effectively alleviates the computational burden on individual vehicles. Furthermore, the exchange between central server and vehicles are the learned features rather than the LVM parameters, which significantly reduces communication overhead. In addition, we utilize both shared features from all participating vehicles and individual characteristics from each vehicle to establish a personalized learning mechanism. This enables each vehicle’s model to learn features from others while preserving its personalized characteristics, thereby outperforming globally shared models trained in general FL. Extensive experiments demonstrate that pFedLVM outperforms the existing state-of-the-art approach by 18.47%, 25.60%, 51.03% and 14.19% in terms of mIoU, mF1, mPrecision and mRecall, respectively. © 2024, CC BY-NC-ND.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Efficient Searchable Encryption Framework with Weighted Keywords for the Internet of Medical Things (IoMT)

TechRxiv

引用

TechRxiv 2022年

作者： Wang, Haiyan Li, Yuan He, Ying Luo, Fucai Yu, F. Richard Ming, Zhong Wang, Shulan The College of Computer Science and Software Engineering Shenzhen University Shenzhen China The Department of New Networks Pengcheng Laboratory Shenzhen China The Department of Systems and Computer Engineer Carleton University OttawaON Canada The College of Big Data and Internet Shenzhen Technology University Shenzhen China

With the increasing popularity of smart terminals, the Internet of Things (IoT) vastly expands the influence of information technology and creates great values to our society. The Internet of Medical Things (IoMT) is a typical application of the IoT specifically for medical and healthcare related purposes. In IoMT, personal health records (PHRs) generated by intelligent equipment are usually stored in a cloud sever managed by a semi-trusted cloud provider. However, there is still a possibility of the exposure of private information to unauthorized parties. In order to protect a patient’s private information, and ensure that doctors can search a patient’s PHRs without decrypting all ciphertexts, an efficient searchable encryption framework with weighted keywords is proposed in this paper. In this framework, we implement a weighted keyword model to raise the accuracy of search results, and reduce the computational and storage overhead. Besides, compared with the existing schemes, the framework is supportable of multi-search mechanism, which is adaptable to more application scenarios. Finally, the efficiency and security of this framework is proved through security and performance analysis in this paper. © 2022, CC BY.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A new approach for generation of generalized basic probability assignment in the evidence theory

arXiv

引用

arXiv 2020年

作者： Wu, Dongdong Liu, Zijing Tang, Yongchuan School of Big Data and Software Engineering Chongqing University Chongqing401331 China

The process of information fusion needs to deal with a large number of uncertain information with multi-source, heterogeneity, inaccuracy, unreliability, and incompleteness. In practical engineering applications, Dempster-Shafer evidence theory is widely used in multi-source information fusion owing to its effectiveness in data fusion. Information sources have an important impact on multi-source information fusion in an environment of complex, unstable, uncertain, and incomplete characteristics. To address multi-source information fusion problem, this paper considers the situation of uncertain information modeling from the closed world to the open world assumption and studies the generation of basic probability assignment (BPA) with incomplete information. In this paper, a new method is proposed to generate generalized basic probability assignment (GBPA) based on the triangular fuzzy number model under the open world assumption. The proposed method can not only be used in different complex environments simply and flexibly, but also have less information loss in information processing. Finally, a series of comprehensive experiments basing on the UCI data sets are used to verify the rationality and superiority of the proposed method. Copyright © 2020, The Authors. All rights reserved.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

A probability distribution and location-aware ResNet approach for QoS prediction

arXiv

引用

arXiv 2020年

作者： Zhang, Wenyan Xua, Ling Yan, Meng Wang, Ziliang Fu, Chunlei School of Big Data & Software Engineering ChongQing University Chongqing400044 China

In recent years, the number of online services has grown rapidly, invoke the required services through the cloud platform has become the primary trend. How to help users choose and recommend high-quality services among huge amounts of unused services has become a hot issue in research. Among the existing QoS prediction methods, the collaborative filtering(CF) method can only learn low-dimensional linear characteristics, and its effect is limited by sparse data. Although existing deep learning methods could capture high-dimensional nonlinear features better, most of them only use the single feature of identity, and the problem of network deepening gradient disappearance is serious, so the effect of QoS prediction is unsatisfactory. To address these problems, we propose an advanced probability distribution and location-aware ResNet approach for QoS Prediction(PLRes). This approach considers the historical invocations probability distribution and location characteristics of users and services, and first use the ResNet in QoS prediction to reuses the features, which alleviates the problems of gradient disappearance and model degradation. A series of experiments are conducted on a real-world web service dataset WS-DREAM. The results indicate that PLRes model is effective for QoS prediction and at the density of 5%-30%, which means the data is sparse, it significantly outperforms a state-of-the-art approach LDCF by 12.35%-15.37% in terms of MAE. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Downlink Channel Covariance Matrix Reconstruction for FDD Massive MIMO Systems with Limited Feedback

arXiv

引用

arXiv 2022年

作者： Li, Kai Li, Ying Cheng, Lei Shi, Qingjiang Luo, Zhi-Quan The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China The College of Information Science and Electronic Engineering Zhejiang University Hangzhou310058 China The School of Software Engineering Tongji University Shanghai201804 China Pazhou Lab Guangzhou510310 China

The downlink channel covariance matrix (CCM) acquisition is the key step for the practical performance of massive multiple-input and multiple-output (MIMO) systems, including beamforming, channel tracking, and user scheduling. However, this task is challenging in the popular frequency division duplex massive MIMO systems with Type I codebook due to the limited channel information feedback. In this paper, we propose a novel formulation that leverages the structure of the codebook and feedback values for an accurate estimation of the downlink CCM. Then, we design a cutting plane algorithm to consecutively shrink the feasible set containing the downlink CCM, enabled by the careful design of pilot weighting matrices. Theoretical analysis shows that as the number of communication rounds increases, the proposed cutting plane algorithm can recover the ground-truth CCM. Numerical results are presented to demonstrate the superior performance of the proposed algorithm over the existing benchmark in CCM reconstruction. Copyright © 2022, The Authors. All rights reserved.

关键词： Covariance matrix

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：