检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xu, Haoran Peng, Peixi Tan, Guang Chang, Yiqian Zhao, Yisen Tian, Yonghong School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen Campus China Peng Cheng Laboratory China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China School of Computer Science and Technology Harbin Institute of Technology China School of Computer Science Peking University China

World models aim to learn or construct representations of the environment that enable the prediction of future scenes, thereby supporting intelligent motion planning. However, existing models often struggle to produce fine-grained predictions and to operate in real time. In this work, we propose T3Former, a novel 4D occupancy world model for autonomous driving. T3Former begins by pre-training a compact triplane representation that efficiently encodes 3D occupancy. It then extracts multi-scale temporal motion features from historical triplanes and employs an autoregressive approach to iteratively predict future triplane changes. Finally, these triplane changes are combined with previous states to decode future occupancy and ego-motion trajectories. Experimental results show that T3Former achieves 1.44× speedup (26 FPS), improves mean IoU to 36.09, and reduces mean absolute planning error to 1.0 meters. Demos are available in the supplementary material. Copyright © 2025, 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

DomainAdaptor: A Novel Approach to Test-time Adaptation

DomainAdaptor: A Novel Approach to Test-time Adaptation

引用

International Conference on computer Vision (ICCV)

作者： Jian Zhang Lei Qi Yinghuan Shi Yang Gao State Key Laboratory for Novel Software Technology Nanjing University National Institute of Healthcare Data Science Nanjing University School of Computer Science and Engineering Southeast University

To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test. In this paper, we investigate a more challenging task that aims to adapt a trained CNN model to unseen domains during the test. To maximumly mine the information in the test data, we propose a unified method called DomainAdaptor for the test-time adaptation, which consists of an AdaMixBN module and a Generalized Entropy Minimization (GEM) loss. Specifically, AdaMixBN addresses the domain shift by adaptively fusing training and test statistics in the normalization layer via a dynamic mixture co-efficient and a statistic transformation operation. To further enhance the adaptation ability of AdaMixBN, we design a GEM loss that extends the Entropy Minimization loss to better exploit the information in the test data. Extensive experiments show that DomainAdaptor consistently outperforms the state-of-the-art methods on four benchmarks. Furthermore, our method brings more remarkable improvement against existing methods on the few-data unseen domain. The code is available at https://***/koncle/DomainAdaptor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Watermarking of OFDM for Pseudonymetry: Analysis and Experimental Results

Watermarking of OFDM for Pseudonymetry: Analysis and Experim...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Meles G. Weldegebriel Jie Wang Greg Hellbourg Ning Zhang Neal Patwari Electrical & Systems Engineering Washington University St. Louis Computer Science & Engineering Washington University St. Louis Cahill Center for Astronomy and Astrophysics California Institute of Technology

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

This paper presents new results for pseudonymetry, a closed-loop feedback mechanism in which active transmissions are watermarked with a pseudonym that, if it interferes with a protected passive radio receiver, can be demodulated and used to force the transmitter off of the band. This paper addresses amplitude-based watermarking of orthogonal frequency division multiplexing (OFDM) packets. We quantify the ability of a passive receiver to decode the watermark at very low signal-to-noise ratio (SNR) and the impact on the intended communication link. We demonstrate, using a testbed of software-defined radios, that the experimental implementation of pseudonymetry matches the theoretical analysis very closely. Our results quantify a fundamental trade-off in the design of pseudonymetry for OFDM and provide a practical pseudonym receiver design.

关键词： Wireless communication Protocols Databases OFDM Conferences Radio transmitters Watermarking

来源：评论

学校读者我要写书评

暂无评论

A Data-Informed Analysis of Scalable Supervision for Safety in Autonomous Vehicle Fleets

arXiv

引用

arXiv 2024年

作者： Hickert, Cameron Yan, Zhongxia Wu, Cathy The Institute for Data Systems and Society Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States The Laboratory for Information & Decision Systems The Institute for Data Systems and Society The Department of Civil and Environmental Engineering Massachusetts Institute of Technology CambridgeMA02139 United States

Autonomous driving is a highly anticipated approach toward eliminating roadway fatalities. At the same time, the bar for safety is both high and costly to verify. This work considers the role of remotely-located human operators supervising a fleet of autonomous vehicles (AVs) for safety. Such a 'scalable supervision' concept was previously proposed to bridge the gap between still-maturing autonomy technology and the pressure to begin commercial offerings of autonomous driving. The present article proposes DISCES, a framework for Data-Informed Safety-Critical Event Simulation, to investigate the practicality of this concept from a dynamic network loading standpoint. With a focus on the safety-critical context of AVs merging into mixed-autonomy traffic, vehicular arrival processes at 1,097 highway merge points are modeled using microscopic traffic reconstruction with historical data from interstates across three California counties. Combined with a queuing theoretic model, these results characterize the dynamic supervision requirements and thereby scalability of the teleoperation approach. Across all scenarios we find reductions in operator requirements greater than 99% as compared to in-vehicle supervisors for the time period analyzed. The work also demonstrates two methods for reducing these empirical supervision requirements: (i) the use of cooperative connected AVs - which are shown to produce an average 3.67 orders-of-magnitude system reliability improvement across the scenarios studied - and (ii) aggregation across larger regions. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Real-World Bugs in Machine Learning Model Optimization

A Comprehensive Study of Real-World Bugs in Machine Learning...

引用

International Conference on software engineering (ICSE)

作者： Hao Guan Ying Xiao Jiaying Li Yepang Liu Guangdong Bai The University of Queensland Brisbane Australia Southern University of Science and Technology Shenzhen China UQ-SUSTech Joint Program Microsoft Software Technology Center Asia Beijing China Department of Computer Science and Engineering Research Institute of Trustworthy Autonomous Systems

Due to the great advance in machine learning (ML) techniques, numerous ML models are expanding their application domains in recent years. To adapt for resource-constrained platforms such as mobile and Internet of Things (IoT) devices, pre-trained models are often processed to enhance their efficiency and compactness, using optimization techniques such as pruning and quantization. Similar to the optimization process in other complex systems, e.g., program compilers and databases, optimizations for ML models can contain bugs, leading to severe consequences such as system crashes and financial loss. While bugs in training, compiling and deployment stages have been extensively studied, there is still a lack of systematic understanding and characterization of model optimization bugs (MOBs). In this work, we conduct the first empirical study to identify and characterize MOBs. We collect a comprehensive dataset containing 371 MOBs from TensorFlow and PyTorch, the most extensively used open-source ML frameworks, covering the entire development time span of their optimizers (May 2019 to August 2022). We then investigate the collected bugs from various perspectives, including their symptoms, root causes, life cycles, detection and fixes. Our work unveils the status quo of MOBs in the wild, and reveals their features on which future detection techniques can be based. Our findings also serve as a warning to the developers and the users of ML frameworks, and an appeal to our research community to enact dedicated countermeasures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Good is Bad: Causality Inspired Cloth-debiasing for Cloth-changing Person Re-identification

Good is Bad: Causality Inspired Cloth-debiasing for Cloth-ch...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhengwei Yang Meng Lin Xian Zhong Yu Wu Zheng Wang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science and Artificial Intelligence Wuhan University of Technology

Entangled representation of clothing and identity (ID)-intrinsic clues are potentially concomitant in conventional person Re- IDentification (ReID). Nevertheless, eliminating the negative impact of clothing on ID remains challenging due to the lack of theory and the difficulty of isolating the exact implications. In this paper, a causality-based Auto-Intervention Model, referred to as AIM 1 1 Codes will publicly available at https://***/BoomShakaY/AIM-CCReID., is first proposed to mitigate clothing bias for robust cloth-changing person ReID (CC-ReID). Specifically, we analyze the effect of clothing on the model inference and adopt a dual-branch model to simulate causal intervention. Progressively, clothing bias is eliminated automatically with model training. AIM is encouraged to learn more discriminative ID clues that are free from clothing bias. Extensive experiments on two standard CC-ReID datasets demonstrate the superiority of the proposed AIM over other state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization for Vehicular Cooperative Sensing: A Graph Attention Based Reinforcement Learning Approach

Performance Optimization for Vehicular Cooperative Sensing: ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Li, Xuefei Chen, Mingzhe Liu, Danpu Zhang, Zhilong Quek, Tony Q. S. Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL33146 United States Information Systems Technology and Design Pillar Singapore University of Technology and Design 487372 Singapore

ISBN: (纸本)9798350351255

In this paper, the problem of collaborative vehicle sensing is investigated. In the considered model, a set of cooperative vehicles provide sensing information to sensing request vehicles with limited sensing and communication resources. A base station (BS) determines the subset of sensing request vehicles that each cooperative vehicle will serve and the sub-regions that each cooperative vehicle will detect. We formulate an optimization problem aiming to maximize the number of successfully detected sub-regions of sensing request vehicles while satisfying the cooperative sensing energy requirement by jointly determining the cooperative vehicle association and the sensing sub-region selection. To solve this problem, we propose a graph attention based reinforcement learning (RL) algorithm that can generate the graph information vectors based on the correlation between each cooperative vehicle and each sensing request vehicle. Using the learned graph information, the joint cooperative vehicle association and sensing sub-region selection strategy will be determined. Simulation results show that the proposed scheme can improve the number of successfully detected sub-regions of sensing request vehicles by up to 12.5% compared to the conventional RL algorithm without using graph attention networks (GANs). © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Early Prediction and Diagnosis Cardiovascular Disease Using Deep Learning Models

Early Prediction and Diagnosis Cardiovascular Disease Using ...

引用

Emerging Technologies in computer science for Interdisciplinary Applications (ICETCS), International Conference on

作者： Rudra Yamini Rani Mudarakola Lakshmi Prasad Induru Sunnihith Reddy Iftikhar Aslam Tayubi Ghazala Sultan Pundru Chandra Shaker Reddy Department of Information Technology VNR Vignana Jyothi Institute of Engineering & Technology Hyderabad Telangana India Computer Science and Engineering Institute of Aeronautical Engineering Dundigal Telangana India Computer Science and Business Systems RMK Engineering College Tiruvallur Tamilnadu India Faculty of Computing and Information Technology Rabigh King Abdulaziz University Jeddah Saudi Arabia Department of Computer Science Aligarh Muslim University Aligarh Uttar Pradesh India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

ISBN: (数字)9798350372502

ISBN: (纸本)9798350372519

Cardiovascular disease (CVD) risk assessment and prognosis in otherwise healthy people is an important part of disease management. Early detection and diagnosis of CVD, supported by the extensive health data on the condition already stored in hospital systems, has the ability to greatly improve disease outcomes. Clinical practice for the management of Cardiovascular Diseases (CVDs) stands to benefit greatly from the use of machine learning approaches. Patients and the healthcare system can save money thanks to these methods, which can be used to create evidence-based clinical guidelines and management algorithms. This will cut down on expensive and time-consuming clinical and laboratory examinations. This study suggests creating new deep learning algorithms that can automatically identify important variables and detect early-stage heart disease; these algorithms should be resilient, effective, efficient, and unique in order to improve early anticipation and interference for CVDs. An F1-score of around 89% is produced by the suggested Catboost model. Hence, it outperformed numerous other state-of-the-art methods by maximizing classification efficiency with better correctness and precision.

关键词： Deep learning Heart Machine learning algorithms Hospitals Predictive models Prediction algorithms Robustness

来源：评论

学校读者我要写书评

暂无评论

基于边缘计算的软件定义云制造和柔性资源调度研究

引用

engineering 2023年第3期22卷 60-70页

作者：杨晨廖方茵兰舒琳王力翚沈卫明黄国全 School of Cyberspace Science and Technology Beijing Institute of TechnologyBeijing 100081China School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China School of Mathematics and Computer Science Yan'an UniversityYan'an 716000China School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Department of Production Engineering KTH Royal Institute of TechnologyStockholm 10044Sweden State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Department of Industrial and Manufacturing Systems Engineering The University of Hong KongHong Kong 999077China

本研究的重点是在云制造环境中实现快速重构、实现灵活的资源调度、开发资源潜力以应对各种变化。因此,本文首先提出了一种新的基于云和软件定义网络(SDN)的制造模型——软件定义云制造(SDCM),该模型将控制逻辑从自动化硬件转移到软件... 详细信息

本研究的重点是在云制造环境中实现快速重构、实现灵活的资源调度、开发资源潜力以应对各种变化。因此,本文首先提出了一种新的基于云和软件定义网络(SDN)的制造模型——软件定义云制造(SDCM),该模型将控制逻辑从自动化硬件转移到软件上。这种转变意义重大,因为软件可以充当制造系统的“大脑”,并且可以轻松更改或更新以支持快速系统重新配置、运营和演进。随后,边缘计算被引入,以接近终端的计算和存储能力来补充云。另一个关键问题是管理由不同服务质量(QoS)要求的大量物联网(IoT)数据传输而导致的严重网络拥塞。基于SDCM的虚拟化和灵活的网络能力,本研究形式化了面向复杂制造任务集的时间敏感性数据流量控制问题,并考虑了子任务分配和数据路由路径选择。为了解决这一优化问题,提出了一种将遗传算法(GA)、Dijkstra最短路径算法和排队算法相结合的方法。实验结果表明,该方法能有效地防止网络拥塞,减少SDCM中的总通信延迟。

关键词： Cloud manufacturing Edge computing software-defined networks Industrial Internet of Things Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

3D Gaze Estimation via Binocular Disparity and Feature Refinement

3D Gaze Estimation via Binocular Disparity and Feature Refin...

引用

International Conference on Big Data Computing and Communications (BIGCOM)

作者： Chengxin Wang Qiuxia Chen Ying Tian Jinfeng Yang School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic Shenzhen China

ISBN: (数字)9798331509538

ISBN: (纸本)9798331509545

The eyes are the windows to the soul and are crucial for studying human behavior. Therefore, gaze estimation has attracted much attention in the field of computer vision. In recent years, convolutional neural networks have driven significant progress in gaze estimation research. Despite the remarkable achievements of gaze technology based on full-face images, the inability to obtain full-face images in specific scenarios makes research based on eye images particularly important. This paper proposes a three-dimensional gaze estimation model that takes binocular images as input, using VGG16 as the backbone network for feature extraction. To enhance the feature extraction capability, we have embedded channel attention and spatial attention mechanisms. Meanwhile, to improve the stability of gaze estimation, we classify real gaze angles. First, we perform a preliminary screening of gaze direction through a classification task, and then perform linear regression with the true angle. Finally, we optimize gaze features using binocular vision differences to finetune the gaze estimator. Experiments have shown that our method performs well on three public datasets.

关键词： Solid modeling Accuracy Three-dimensional displays Linear regression Estimation Network architecture Feature extraction Data models Stability analysis Data mining

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：