检索结果-内蒙古大学图书馆

International conference on Communication Technology (ICCT)

作者： Hongmei Zhang Xiaoqian Yun Xiaofang Deng Xiaoxiong Zhong School of Information and Communication Guilin University of Electronic Technology Guilin China Peng Cheng Laboratory Shenzhen China

Due to the constant updates of malware and its variants and the continuous development of malware obfuscation techniques. Malware intrusions targeting Windows hosts are also on the rise. Traditional static analysis methods such as signature matching mechanisms have been difficult to adapt to the detection of new malware. Therefore, a novel visual detection method of malware is proposed for first-time to convert the Windows API call sequence with sequential nature into feature images based on the Gramian Angular Field (GAF) idea, and train a neural network to identify malware. The experimental results demonstrate the effectiveness of our proposed method. For the binary classification of malware, the GAF visualization image of the API call sequence is compared with its original sequence. After GAF visualization, the classification accuracy of the classic machine learning model MLP is improved by 9.64%, and the classification accuracy of the deep learning model CNN is improved by 4.82%. Furthermore, our experiments show that the proposed method is also feasible and effective for the multi-class classification of malware.

关键词： Deep learning visualization Neural networks Static analysis Feature extraction Malware communications technology

来源：评论

学校读者我要写书评

暂无评论

USTC-TD: A Test Dataset and Benchmark for image and Video Coding in 2020s

arXiv

引用

arXiv 2024年

作者： Li, Zhuoyuan Liao, Junqi Tang, Chuanbo Zhang, Haotian Li, Yuqi Bian, Yifan Sheng, Xihua Feng, Xinmin Li, Yao Gao, Changsheng Li, Li Liu, Dong Wu, Feng MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition University of Science and Technology of China Hefei230027 China

image/video coding has been a remarkable research area for both academia and industry for many years. Testing datasets, especially high-quality image/video datasets are desirable for the justified evaluation of coding-related research, practical applications, and standardization activities. We put forward a test dataset namely USTC-TD, which has been successfully adopted in the practical end-to-end image/video coding challenge of the IEEE International conference on visual communications and lmage processing (VCIP) in 2022 and 2023. USTC-TD contains 40 images at 4K spatial resolution and 10 video sequences at 1080p spatial resolution, featuring various content due to the diverse environmental factors (e.g. scene type, texture, motion, view) and the designed imaging factors (e.g. illumination, lens, shadow). We quantitatively evaluate USTC-TD on different image/video features (spatial, temporal, color, lightness), and compare it with the previous image/video test datasets, which verifies its excellent compensation for the shortcomings of existing datasets. We also evaluate both classic standardized and recently learned image/video coding schemes on USTC-TD using objective quality metrics (PSNR, MS-SSIM, VMAF) and subjective quality metric (MOS), providing an extensive benchmark for these evaluated schemes. Based on the characteristics and specific design of the proposed test dataset, we analyze the benchmark performance and shed light on the future research and development of image/video coding. All the data are released online: https://***/USTC-TD . Copyright © 2024, The Authors. All rights reserved.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

A stochastic modelling framework for the reconstruction of cardiovascular signals

A stochastic modelling framework for the reconstruction of c...

引用

Annual International conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Diego Martín-Martínez Pablo Casaseca-de-la-Higuera Marcos Martín-Fernández Abbes Amira Chunbo Luo Christos Grecos Carlos Alberola-López Laboratory of Image Processing University of Valladolid Spain Audio Visual Communications and Networking Research Centre University of the West of Scotland United Kingdom

This paper presents a common stochastic modelling framework for physiological signals which allows patient simulation following a synthesis-by-analysis approach. Within this framework, we propose a general model-based methodology able to reconstruct missing or artifacted signal intervals in cardiovascular monitoring applications. The proposed model consists of independent stages which provide high flexibility to incorporate signals of different nature in terms of shape, cross-correlation and variability. The reconstruction methodology is based on model sampling and selection based on a wide range of boundary conditions, which include prior information. Results on real data show how the proposed methodology fits the particular approaches presented so far for electrocardiogram (ECG) reconstruction and how a simple extension within the framework can significantly improve their performance.

关键词： Electrocardiography Joints Autoregressive processes Vectors Stochastic processes Principal component analysis Shape

来源：评论

学校读者我要写书评

暂无评论

Detection of Motion Vector-Based Stegomalware in Video Files 1

引用

International conference on Computer Vision and Machine Intelligence, CVMI 2022

作者： Nair, Sandra V. S. Arun Raj Kumar, P. Department of Computer Science and Engineering National Institute of Technology Calicut Kozhikode India

ISBN: (数字)9789811978678

ISBN: (纸本)9789811978661

Cybercriminals are increasingly using steganography to launch attacks on devices. The cyberattack is more threatening as steganography hides the embedded malware, if any, making it harder to detect by various anti-virus tools. Such malware is called stegomalware. Since video files are larger and have a complex structure, they also have a high capacity for hiding malware. Motion vector (MV)-based steganography techniques do not cause much distortion in video files. Therefore, it remains to be one of the leading video steganography techniques. This paper deals with a lightweight solution for MV-based stegomalware detection in video files. Our model is compatible with state-of-the-art video coding standards having variable macroblock sizes and different motion vector resolutions. The proposed method obtained an accuracy of 95.8% on testing H.264 videos with various embedding rates. The 81-D spatial and temporal features result in the high performance of the proposed model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

image-Based Indoor Localization Using Smartphone Cameras In Textureless Environment

Image-Based Indoor Localization Using Smartphone Cameras In ...

引用

International conference on Information and Computer Technologies (ICICT)

作者： Ping Zheng Danyang Qin Jianan Bai Lin Ma Department of Electronics and Communication Engineering Heilongjiang University Harbin China Heilongjiang University Harbin China National Mobile Communications Research Laboratory Southeast University Nanjing China Department of Information and Communication Engineering Heilongjiang University Harbin China Department of Electronics and Information Engineering Harbin Institute of Technology Harbin China

In recent years, Location Based Services (LBS) have developed rapidly. There is an urgent need to establish a low-cost and convenient method to get precise positions indoors. Therefore, we choose an easier way of using monocular camera mounted on a mobile terminal to achieve indoor visual positioning. In this paper, two main problems are studied under this condition. Firstly, the feature extraction method is designed to minimize the loss of positioning information while processing quickly in textureless environment. Secondly, the relative direction vector obtained from the epipolar geometry cannot converge at the point to be located due to errors, so a position determination method is proposed to transform the problem of positioning into distance calculation. A WeChat mini program was built for users to obtain location information. Experimental results show that 90% positioning error was less than 0. 5m, and the average error was less than 0.32m.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Light-weight Super-Resolution Network based on Classified Measurement-domain Features 23

Light-weight Super-Resolution Network based on Classified Me...

引用

Proceedings of the 2023 6th International conference on Artificial Intelligence and Pattern Recognition

作者： Shuo Li Yinghua Li Dan Xu Ying Zhang Jinglu He School of Communications and Information Engineering Xi'an University of Posts and Telecommunications China Sichuan Jiuzhou Electric Group Co. Ltd. China

ISBN: (纸本)9798400707674

In contemporary research, natural images are frequently reconstructed using methods that are computationally intensive but highly effective. To solve this issue, we propose a light-weight super-resolution(SR) network based on classified measurement-domain features, abbreviated as SRCMF. images of nature can be divided into multiple smaller images for processing purposes. On the basis of this line of reasoning, it is possible to conclude that various image regions present unique recovery challenges and can be processed by models with differing degrees of complexity. Textured regions make supersegmentation more difficult than flat regions. To take advantage of this property, we can manage the various subgraphs of the split using an appropriate SR model, i.e. a simple small model for smooth regions and a complex large model for textured regions. With this as our starting point, we propose the SRCMF, a classification and supersegmentation integrating framework. Specifically, it employs Class Modules to categorize subgraphs based on their recovery difficulty, followed by numerous SRModules to super-score the subgraphs in each category. The computational cost can be drastically reduced because the preponderance of sub-images will travel through fewer networks. ClassSR is founded on a compression-aware image block processing method on the measurement domain, while SRModule is comprised of SR models of varying proportions. When reconstructing natural images, experimental data indicate that our SRCMF can save FLOPs and reduce the computational complexity of reconstruction. This general structure is applicable to additional simple visual duties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Point Cloud Compression for Real-Time visualization and Streaming of Large 3D Datasets

Multiresolution Point Cloud Compression for Real-Time Visual...

引用

Asilomar conference on Signals, Systems & Computers

作者： Dat Thanh Nguyen Daniel Zieger Markus Gambietz Anne D. Koelewijn Marc Stamminger André Kaup Chair of Multimedia Communications and Signal Processing Erlangen Germany Chair of Visual Computing Erlangen Germany Chair of Autonomous Systems and Mechatronics Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

In recent years, the integration of point cloud data has been observed across diverse domains such as immersive media, autonomous driving, and healthcare. However, processing and visualizing 3D point cloud data requires more computational power and processing time than typical 2D images or videos. In this paper, we present a multiresolution point cloud visualization approach that enables the encoding and reconstruction of human body point clouds at multiple quality/bitrate levels for streaming or real-time visualization applications. Specifically, we partition the 3D model into cells and build an octree structure to store the point cloud at multiple levels of detail. The hierarchical structure is encoded efficiently for fast loading times. We optimize the resolution selection for each visible node based on the camera viewpoint and the geometric error perceived by the user. We validate the proposed method using a widely known point cloud dataset from the Moving Picture Experts Group. The experiments demonstrate that the method can dynamically adapt the resolution of point clouds and provide faster rendering times compared to well-known point cloud visualization software.

关键词： Point cloud compression Three-dimensional displays image resolution Data visualization Rendering (computer graphics) Cameras Real-time systems Signal resolution Iterative decoding Videos

来源：评论

学校读者我要写书评

暂无评论

An Object Detection System for Automatic Driving: MEC-YOLO Based on "Cloud-Edge-End"

An Object Detection System for Automatic Driving: MEC-YOLO B...

引用

Natural Language processing (ICNLP), International conference on

作者： Siyuan Liang Xu Zhang School of Communications and Information Engineering Xi’an University of Posts and Telecommunications Xi’an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

The massive machine type of communication (mMTC) of 5G is the basis for IoT (Internet of Things) development, which can promote automobile industry upgrades: intelligent and green. Automatic driving (AD) is an important trend in intelligent vehicles. With the development of computer vision (CV) technology, pure vision sensor-based solutions are dominating the AD of intelligent vehicles. Due to CV hardware platform energy and cost consumption constraints, meeting the detection speed and accuracy of vehicle AD requirements have become an obvious challenge, especially for new energy vehicles. Combining the advantages of edge computing and IoT based on mMTC, this paper proposes a system called mobile edge computing-you only look once (MEC-YOLO) to solve this problem, which is an energy-efficient and low-cost instance-level vision perception system for AD. In this system, the local hardware platform uses the improved object detection (OD) network to extract features from the locally collected visual data, processes them into a feature extraction queue, uploads them to the edge network nodes to complete the OD task, and transmits the prediction results and trains weights back to the local devices. In addition, the cloud computing center resource can be invoked to supplement edge nodes when the edge computing capacity is insufficient. Furthermore, we develop an AD platform equipped with Jetson for system validation, which improved the detection speed by 93.2% and reduced the GPU resource occupation rate by 90.8% compared to YOLOv4 on the KITTI dataset. The test results verified that the MEC-YOLO proposed in this paper has the advantages of fast detection speed, high accuracy, and low resource occupation rate compared with the traditional OD scheme.

关键词： Cloud computing Accuracy Intelligent vehicles image edge detection Graphics processing units Object detection Feature extraction Hardware Internet of Things Edge computing

来源：评论

学校读者我要写书评

暂无评论

Architecture and Design of a High Definition Television Production Switcher

Architecture and Design of a High Definition Television Prod...

引用

SMPTE Technical conference

作者： Edward Hobson T. Takamori Broadcast and Professional Group Sony Electronics Vince Harradine Broadcast and Professional R&D Department Sony Broadcast and Professional Europe Image and Sound Communications Company Sony Corporation Atsugi Japan

In late 1996, the Federal communications Commission ruled the United States would migrate to a digital television broadcasting system. The Commission chose the Grand Alliance transmission scheme and left the picture scanning format to the marketplace. High Definition video, at 1920 times 1080 pixels, interlaced scanning, at a nominal 60 Hertz field rate is one format in the infamous Table 3 of the ATSC document and FCC ruling. This picture format is also well on the way to becoming a universal format. — A new series of digital systems, conforming to the interlaced scanning format of SMPTE 274M- 1995 were recently introduced by Sony. This paper deals with the architecture, enabling technologies, and capabilities of a live and post production vision mixer from this family of equipment. — A modern, digital, high definition vision mixer, and associated digital effects and editing equipment, must provide producers, directors, and the artistic and technical staff employing them with similar capabilities as existing standard definition equipment—the visual effects expected by a sophisticated audience. These requirements are detailed in this paper and the vision mixer described is compared to similar standard definition devices. — The capabilities of the switcher resulted in an architecture for crosspoints, mix effects systems, key and video processing, control and external interfaces. Operational and maintenance aspects are also key factors in an architecture and include considerations for size, mass, power consumption and heat loads. Picture size and shape may change but control room and remote broadcast vehicle designs dictate limitations on these specifications. Trade-offs in capability and architecture are enumerated. — The data rates employed in HDTV (more than 5 times the rate of SMPTE 125M and SMPTE 259M) required additional new technologies, including the development of a series of Application Specific Integrated Circuits which perform the same functions employed i

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adapting CBAM and IAL to Bayesian Loss-based Crowd Counting 23

Adapting CBAM and IAL to Bayesian Loss-based Crowd Counting

引用

Proceedings of the 2023 6th International conference on Artificial Intelligence and Pattern Recognition

作者： Huimin Du Yu Hao Xiaoyang Zhang Ying Liu Center for Image and Information Processing School of Communications and Information Engineering Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

Probability-originated crowding counting strategy has advantages of providing additional spatial information of pedestrians and smaller model scale. This paper proposes a novel Bayesian Loss-based crowd counting model which integrates the Convolutional Block Attention Module (CBAM)and Instance Attention Loss (IAL) to further address typical issues in crowd counting such as complicated background, occlusion, and uneven crowd distribution. After adapting the VGG-19 as the front-end network to efficiently extract visual features, the CBAM is implemented as the intermediate process to concentrate on the key features with the attention mechanism, before using the back-end network to output the predicted density map. To handle the deviation of manual labeled head positions in the dataset and improve the training efficiency, the IAL where only 90% of the annotation points with the smallest deviation from the prediction is adapted by the approach. Experiments results on two benchmarking datasets demonstrated the network's efficiency in enhancing headcount accuracy by significantly optimized the MAE(mean absolute error) and MSE(mean square error).

关键词： Bayesian loss CBAM IAL crowd counting density map

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：