检索结果-内蒙古大学图书馆

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bir...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liao, Hao Liu, Ming-Kai Mariani, Manuel Sebastian Zhou, Mingyang Wu, Xingtong National Engineering Laboratory for Big Data System Computing Technology Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu610051 China URPP Social Networks Universität Zürich CH-8050 Switzerland

When investigating the spreading of a piece of information or the diffusion of an innovation, we often lack information on the underlying propagation network. Reconstructing the hidden propagation paths based on the observed diffusion process is a challenging problem which has recently attracted attention from diverse research fields. To address this reconstruction problem, based on static similarity metrics commonly used in the link prediction literature, we introduce new node-node temporal similarity metrics. The new metrics take as input the time-series of multiple independent spreading processes, based on the hypothesis that two nodes are more likely to be connected if they were often infected at similar points in time. This hypothesis is implemented by introducing a time-lag function which penalizes distant infection times. We find that the choice of this time-lag strongly affects the metrics' reconstruction accuracy, depending on the network's clustering coefficient and we provide an extensive comparative analysis of static and temporal similarity metrics for network reconstruction. Our findings shed new light on the notion of similarity between pairs of nodes in complex networks. Copyright © 2019, The Authors. All rights reserved.

关键词： Information services

A Mobile Cloud-Based eHealth Scheme

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第4期63卷 31-39页

作者： Yihe Liu Aaqif Afzaal Abbasi Atefeh Aghaei Almas Abbasi Amir Mosavi Shahaboddin Shamshirband Mohammed A.A.Al-qaness Data Recovery Key Laboratory of Sichuan Province College of Computer Science and AINeijiang Normal UniversityNeijiang641100China Department of Software Engineering Foundation UniversityIslamabad44000Pakistan Department of Communication Faculty of Social SciencesUniversity of TehranTehran***Iran Department of Computer Science International Islamic UniversityIslamabad46000Pakistan Institute of Research and Development Duy Tan UniversityDa Nang550000Vietnam Kalman Kando Faculty of Electrical Engineering Obuda UniversityBudapest1034Hungary School of the Built Environment Oxford Brookes UniversityOxfordOX30BPUK Department for Management of Science and Technology Development Ton Duc Thang UniversityHo Chi Minh CityVietnam Faculty of Information Technology Ton Duc Thang UniversityHo Chi Minh CityVietnam School of Computer Science Wuhan UniversityWuhan430072China

Mobile cloud computing is an emerging field that is gaining popularity across borders at a rapid ***,the field of health informatics is also considered as an extremely important *** work observes the collaboration between these two fields to solve the traditional problem of extracting Electrocardiogram signals from trace reports and then performing *** developed system has two front ends,the first dedicated for the user to perform the photographing of the trace *** the photographing is complete,mobile computing is used to extract the *** the signal is extracted,it is uploaded into the server and further analysis is performed on the signal in the *** this is done,the second interface,intended for the use of the physician,can download and view the trace from the *** data is securely held using a password-based authentication *** system presented here is one of the first attempts at delivering the total solution,and after further upgrades,it will be possible to deploy the system in a commercial setting.

关键词： Cloud computing electrocardiograms health-care signal analysis signal processing

Experimental optimal verification of three-dimensional entanglement on a silicon chip

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xia, Lijun Lu, Liangliang Wang, Kun Jiang, Xinhe Zhu, Shining Ma, Xiaosong National Laboratory of Solid-state Microstructures School of Physics Collaborative Innovation Center of Advanced Microstructures State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing210093 China Key Laboratory of Optoelectronic Technology of Jiangsu Province School of Physical Science and Technology Nanjing Normal University Nanjing210023 China Institute for Quantum Computing Baidu Research Beijing100193 China Institute for Quantum Optics and Quantum Information Austrian Academy of Sciences Vienna1090 Austria

High-dimensional entanglement is significant for the fundamental studies of quantum physics and offers unique advantages in various quantum information processing (QIP) tasks. Integrated quantum devices have recently emerged as a promising platform for creating, processing, and detecting complex high-dimensional entangled states. A crucial step towards practical quantum technologies is to verify that these devices work reliably with an optimal strategy. In this work, we experimentally implement an optimal quantum verification strategy on a three-dimensional maximally entangled state using local projective measurements on a silicon photonic chip. A 95% confidence is achieved from 1190 copies to verify the target quantum state. The obtained scaling of infidelity as a function of the number of copies is - 0.5497±0.0002, exceeding the standard quantum limit of -0.5 with 248 standard deviations. Our results indicate that quantum state verification could serve as an efficient tool for complex quantum measurement tasks. © 2022, CC BY-NC-ND.

关键词： Quantum optics

The role of positive and negative citations in scientific evaluation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bai, Xiaomei Lee, Ivan Ning, Zhaolong Tolba, Amr Xia, Feng Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian116620 China Computing Center Anshan Normal University Anshan114007 China School of Information Technology and Mathematical Sciences University of South Australia Australia Riyadh Community College King Saud University Riyadh11437 Saudi Arabia Mathematics and Computer Science Department Faculty of Science Menoufia University Egypt

Quantifying the impact of scientific papers objectively is crucial for research output assessment, which subsequently affects institution and country rankings, research funding allocations, academic recruitment and national/international scientific priorities. While most of the assessment schemes based on publication citations may potentially be manipulated through negative citations, in this study, we explore Conflict of Interest (COI) relationships and discover negative citations and subsequently weaken the associated citation strength. PANDORA (Positive And Negative COI- Distinguished Objective Rank Algorithm) has been developed, which captures the positive and negative COI, together with the positive and negative suspected COI relationships. In order to alleviate the influence caused by negative COI relationship, collaboration times, collaboration time span, citation times and citation time span are employed to determine the citing strength;while for positive COI relationship, we regard it as normal citation relationship. Furthermore, we calculate the impact of scholarly papers by PageRank and HITS algorithms, based on a credit allocation algorithm which is utilized to assess the impact of institutions fairly and objectively. Experiments are conducted on the publication dataset from American Physical Society (APS) dataset, and the results demonstrate that our method significantly outperforms the current solutions in Recommendation Intensity of list R at top-K and Spearman’s rank correlation coefficient at top-K. Copyright © 2020, The Authors. All rights reserved.

关键词：

TEVA: Training-Efficient and Verifiable Aggregation for Federated Learning for Consumer Electronics in Industry 5.0

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2024年

作者： Xia, Yuanjun Liu, Yining Chen, Jingxue Liang, Yangfan Khan, Fazlullah Alturki, Ryan Wang, Xiaopei Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software School of Computer and Information Security Guilin541004 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325027 China University of Technology School of Mathematical and Physical Sciences SydneyNSW2007 Australia Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems The Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing314001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China Umm AI-Qura University Makkah Department of Software Engineering College of Computing Saudi Arabia Riverside Department of Computer Science and Engineering University of California CA92521 United States

Federated learning (FL) has been widely used for privacy-preserving model updates in Industry 5.0, facilitated by 6G networks. Despite FL's privacy-preserving advantages, it remains vulnerable to attacks where adversaries can infer private data from local models or manipulate the central server (CS) to deliver falsified global models. Current privacy-preserving approaches, primarily based on the FedAvg algorithm, fail to optimize training efficiency for non-independent and identically distributed (non-IID) data. This article proposes training-efficient and verifiable aggregation (TEVA) for FL to resolve these issues. This scheme combines threshold Paillier homomorphic encryption (TPHE), verifiable aggregation, and an optimized double momentum update mechanism (OdMum). TEVA not only leverages TPHE to protect the privacy of local models but also ensures the integrity of the global model through a verifiable aggregation mechanism. Additionally, TEVA integrates the OdMum algorithm to effectively address the challenges posed by non-IID data, promoting rapid model convergence and significantly enhancing overall training efficiency. Security analysis indicates that TEVA meets the requirements for privacy protection. Extensive experimental results demonstrate that TEVA can accelerate model convergence while incurring lower computational and communication overheads. © 1975-2011 IEEE.

关键词： Differential privacy

DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Maoyuan Zhang, Jing Zhao, Shanshan Liu, Juhua Liu, Tongliang Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computer Science Faculty of Engineering The University of Sydney Australia JD Explore Academy *** China College of Computing & Data Science Nanyang Technological University Singapore

End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection, recognition, and script identification simultaneously. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, our method not only performs well in English scenes but also masters the transcription with complex font structure and a thousand-level character classes, such as Chinese. On the other hand, our DeepSolo++ achieves better performance on the additionally introduced script identification task with a simpler training pipeline compared with previous methods. Extensive experiments on public benchmarks demonstrate that our simple approach achieves better training efficiency compared with Transformer-based models and outperforms the previous state-of-the-art. For example, on ICDAR 2019 ReCTS for Chinese text, our method boosts the 1-NED metric to a new record of 78.3%. On ICDAR 2019 MLT, DeepSolo++ achieves absolute 5.5% H-mean and 8.0% AP improvements on joint detection an

关键词： Semantics

GPU-based simulation of ocean water using fluid dynamics model and displacement mapping

学校读者我要写书评

暂无评论

ICIC Express Letters 2016年第6期10卷 1239-1245页

作者： Xu, Jie Fu, Jinhua Zhang, Hongtao School of Software Zhengzhou University of Light Industry No. 5 Dongfeng Road Zhengzhou450002 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450002 China School of Computer and Communication Engineering Zhengzhou University of Light Industry No. 5 Dongfeng Road Zhengzhou450002 China College of Information Engineering Zhengzhou University No. 100 Kexue Ave. Zhengzhou450000 China

Real-time realistic simulation of liquids like ocean water is an important task nowadays in the field of computer graphics. In this paper, we present a novel method to achieve plausible visual results of ocean water at higher rendering rates. Based on evolution of the density and the velocity, we establish the fluid dynamics model to express properties of the fluid and simulate ocean water efficiently. Also we implement the displacement mapping by utilizing the heightmap and design the shading shader on the GPU (Graphics Processing Unit), which gives a realistic appearance in higher rendering speed. The results show that we can acquire realistic rendering effects such as water color, light reflection, caustics and soft shadow, while achieving a relatively faster speed of rendering. © 2016 ISSN.

关键词： Graphics processing unit

Exploiting trust degree for multiple-antenna user cooperation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhao, Mingxiong Ryu, Jong Yeol Lee, Jemin Quek, Tony Q.S. Feng, Suili School of Software Yunnan University Kunming China Key Laboratory in Software Engineering of Yunnan Province Department of Information and Communication Engineering Gyeongsang National University Tongyeong Korea Republic of Daegu Korea Republic of Singapore University of Technology and Design 487372 Singapore Department of Electronics Engineering Kyung Hee University Yongin-si Gyeonggi-do17104 Korea Republic of School of Electronics and Information Engineering South China University of Technology Guangzhou China

For a user cooperation system with multiple antennas, we consider a trust degree based cooperation techniques to explore the influence of the trustworthiness between users on the communication systems. For the system with two communication pairs, when one communication pair achieves its quality of service (QoS) requirement, they can help the transmission of the other communication pair according to the trust degree, which quantifies the trustworthiness between users in the cooperation. For given trust degree, we investigate the user cooperation strategies, which include the power allocation and precoder design for various antenna configurations. For SISO and MISO cases, we provide the optimal power allocation and beamformer design that maximize the expected achievable rates while guaranteeing the QoS requirement. For a SIMO case, we resort to semidefinite relaxation (SDR) technique and block coordinate update (BCU) method to solve the corresponding problem, and guarantee the rank-one solutions at each step. For a MIMO case, as MIMO is the generalization of MISO and SIMO, the similarities among their problem structures inspire us to combine the methods from MISO and SIMO together to efficiently tackle MIMO case. Simulation results show that the trust degree information has a great effect on the performance of the user cooperation in terms of the expected achievable rate, and the proposed user cooperation strategies achieve high achievable rates for given trust degree. Copyright © 2017, The Authors. All rights reserved.

关键词： Beamforming