检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation (ICRA)

作者： Changkun Liu Shuai Chen Yukun Zhao Huajian Huang Victor Prisacariu Tristan Braud Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Engineering Science Active Vision Laboratory University of Oxford United Kingdom Division of Integrated Systems Design The Hong Kong University of Science and Technology Hong Kong

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Absolute Pose Regressors (APRs) directly estimate camera poses from monocular images, but their accuracy is unstable for different queries. Uncertainty-aware APRs provide uncertainty information on the estimated pose, alleviating the impact of these unreliable predictions. However, existing uncertainty modelling techniques are often coupled with a specific APR architecture, resulting in suboptimal performance compared to state-of-the-art (SOTA) APR methods. This work introduces a novel APR-agnostic framework, HR-APR, that formulates uncertainty estimation as cosine similarity estimation between the query and database features. It does not rely on or affect APR network architecture, which is flexible and computationally efficient. In addition, we take advantage of the uncertainty for pose refinement to enhance the performance of APR. The extensive experiments demonstrate the effectiveness of our framework, reducing 27.4% and 15.2% of computational overhead on the 7Scenes and Cambridge Landmarks datasets while maintaining the SOTA accuracy in single-image APRs.

关键词： Training Uncertainty Accuracy Databases Pipelines Estimation Network architecture

来源：评论

学校读者我要写书评

暂无评论

A Test Suite and An Optimizer for Dietary Nutrition Optimization Problem: From Constrained Many-Objective Perspective

A Test Suite and An Optimizer for Dietary Nutrition Optimiza...

引用

2023 IEEE Congress on Evolutionary Computation, CEC 2023

作者： Ti, Yaqi Li, Changhe Yang, Shengxiang Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China School of Computer Science and Informatics De Montfort University Leicester United Kingdom

ISBN: (纸本)9798350314588

With increasing people who suffer from diet-related diseases, providing suggestions for personal daily nutrient-dense intake is highly expected. However, current dietary nutrition models are less precise, and dietary nutrition optimizers usually fail to give satisfactory solutions. Therefore, we construct a constrained many-objective nutrition model with more precise nutrient assessments and a scalable constrained many-objective benchmark set. This test suite has great flexibility in evaluating algorithms' performance on high dimensional search and objective spaces with some feasible region fragments. We also propose a kd-tree based dynamic constrained many-objective evolutionary algorithm to search for customized food combinations according to personal daily consumption and intake preference. Experiments show that our algorithm has better diversity maintenance ability in high dimension space. © 2023 IEEE.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification

引用

IEEE Transactions on Multimedia 2025年 27卷 3251-3265页

作者： Wang, Lei Zhan, Yibing Ma, Leilei Tao, Dapeng Ding, Liang Gong, Chen Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Jiangsu Nanjing210094 China JD Explore Academy Beijing100000 China Anhui University School of Computer Science and Technology Anhui Heifei230601 China Yunnan University FIST LAB School of Information Science and Engineering Yunnan Kunming650091 China

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this article, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice"in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias;2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also provide a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the potential of extending our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://***/zuiran/SpliceMix. © 1999-2012 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Optimal Control of Connected Automated Vehicles with Event-Triggered Control Barrier Functions: a Test Bed for Safe Optimal Merging

Optimal Control of Connected Automated Vehicles with Event-T...

引用

Control Technology and Applications (CCTA),

作者： Ehsan Sabouni H.M. Sabbir Ahmad Wei Xiao Christos G. Cassandras Wenchao Li Department of Electrical & Computer Engineering Division of Systems Engineering Boston University Boston MA USA Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA USA

We address the problem of safely coordinating a network of Connected and Automated Vehicles (CAVs) in conflict areas of a traffic network. Such problems can be solved through a combination of tractable optimal control problems and Control Barrier Functions (CBFs) that guarantee the satisfaction of all constraints. These solutions can be reduced to a sequence of Quadratic Programs (QPs) which are efficiently solved online over discrete time steps. However, guaranteeing the feasibility of the CBF-based QP method within each discretized time interval requires the careful selection of time steps which need to be sufficiently small. This creates computational requirements and communication rates between agents which may limit the controller’s application to real CAVs. We tackle this limitation by adopting an event-triggered control approach for CAVs such that the next QP is triggered by properly defined events with a safety guarantee. We present a laboratory-scale test bed developed to emulate merging roadways using mobile robots as CAVs. We present results to demonstrate how the event-triggered scheme is computationally efficient and can handle measurement uncertainties and noise compared to time-driven control while guaranteeing safety.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing Infrared Linescan Profiles of Steel Strips for Enhanced Cooling Pattern Prediction

Analyzing Infrared Linescan Profiles of Steel Strips for Enh...

引用

IEEE Industry Applications Society Annual Meeting (IAS)

作者： Rubén Usamentiaga Adrian G. Gayo Francisco J. DelaCalle Dario G. Lema Stefano Sfarra Hai Zhang Department of Computer Science and Engineering University of Oviedo Gijón Asturias Spain Department of Industrial and Information Engineering and Economics (DIIIE) University of L'Aquila L'Aquila Italy Department of Electrical and Computer Engineering Computer Vision and Systems Laboratory (CVSL) Laval University Quebec Canada

ISBN: (数字)9798350372717

ISBN: (纸本)9798350372724

Real-time temperature information is crucial for optimizing cooling processes during steel strip rolling, ensuring the attainment of desired microstructural properties and surface quality at an optimal cooling rate. Infrared line scanners emerge as the preferred choice for temperature measurement in highspeed rolling operations, delivering temperature readings with high resolution and enabling the capture of detailed temperature profiles. By analyzing these profiles, cooling systems can be finely adjusted and precisely controlled to optimize the rolling operation. However, developing effective cooling strategies becomes challenging when dealing with temperature profiles comprising numerous discrete data points, often numbering in the thousands per profile. This study presents an innovative approach that integrates the detection of steel strip boundaries within temperature profiles and subsequent temperature pattern characterization using polynomial fitting. A significant advantage is demonstrated by leveraging the coefficients of Legendre polynomials, which provide a concise description of temperature profile shapes, facilitating straightforward approaches to cooling strategies. By integrating boundary detection with temperature characterization, the system enhances its ability to predict tailored cooling patterns, optimizing cooling efficiency, and enhancing product quality in the manufacturing process. Rigorous testing using both synthetic data and real-world applications in cold and hot rolling validates the proposed system's practical utility and reliability. These results underscore its potential to enhance efficiency and quality in industrial steel manufacturing operations.

关键词： Temperature measurement Temperature sensors Strips Cooling Shape Polynomials Real-time systems Steel Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Geospatial exploration of geothermal reservoirs in the Souss Massa regions of the anti-atlas and Moroccan Sahara

引用

Materials Today: Proceedings 2022年 72卷 3911-3926页

作者： El Bouazouli, Abderrahim Baidder, Lahssen Bahi, Hicham Abdehamid, Fadil Rhouzlane, Said Moussaoui, Rabia Oukrich, Nadia Baite, Wissal Hlal, Mohammed Laboratory of Geosciences Faculty of Sciences Aïn Chock University Hassan II of Casablanca Morocco School of Architecture Planning and Design Mohammed VI Polytechnic University Benguerir Morocco Morocco Polytechnic School of Montreal Canada Laboratory of Industrial Equipe Architecture de Systems ENSEM Morocco research laboratory in computer science and education the mohammedia school of engineering Rabat Morocco Laboratory of Industrial Engineering Sciences and Technologies Faculty Sultan Moulay Slimane University Beni Mellal Morocco laboratory Dynamics of arid environments Mohamed Premier University Oujda Morocco

Geothermal reservoirs refer to any heat stored, naturally, in the earth's crust;it is considered as resource coming from a natural complex depending on the geological, geophysical aspect and territories geochemistry. Although this natural resource remains distinguished by his characters to be a renewable, ecological, universal and sustainable mining energy, it stills not, yet, sufficiently exploitable worldwide (El Bouazouli et al., 2020). The same finding was brought up in Moroccan context, despite the presence of some hot resources and capitalizable scientific research to develop this potential. Prospecting for underground geothermal resources is an expensive project that deserves to mobilize scientific and technical methods in order to overcome this risky impasse. Thus, Geomatics has been used, drawing on Remote Sensing for geo-spatial exploration in order to guide prospecting through the development of geothermal deposits potential maps at very low and medium depth on Moroccan territories (El Bouazouli et al., 2019). Furthermore, we explore smart tools to support short and long-term decision-making in terms of creating of clean energy mix and complementary mining energy as well as investment in energy exploration operations. And, as an experiment, we chose for this study, areas distributed mainly in the Moroccan Sahara and the Souss Massa Region, known, probably, by a potentially high geothermal gradient, and therefore constituting geothermal energy reservoirs. As for the exploration methodology adopted, it consists in processing of the imageries: LANDSAT 8, MODIS AND ASTER, in order to extract exploitation indices such as the surface temperature, the layer of lineaments and cracks density, and evidence of hydrothermal alteration that may indicate geothermal activity. The correlation between these three factors, will lead us to conclude that the Moroccan Sahara area is considered as one of the most potential geothermal reservoir areas in Morocco. In short, the a

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

RGB-D Salient Object Detection with Ubiquitous Target Awareness

RGB-D Salient Object Detection with Ubiquitous Target Awaren...

引用

作者： Zhao, Yifan Zhao, Jiawei Li, Jia Chen, Xiaowu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

Conventional RGB-D salient object detection methods aim to leverage depth as complementary information to find the salient regions in both modalities. However, the salient object detection results heavily rely on the quality of captured depth data which sometimes are unavailable. In this work, we make the first attempt to solve the RGB-D salient object detection problem with a novel depth-awareness framework. This framework only relies on RGB data in the testing phase, utilizing captured depth data as supervision for representation learning. To construct our framework as well as achieving accurate salient detection results, we propose a Ubiquitous Target Awareness (UTA) network to solve three important challenges in RGB-D SOD task: 1) a depth awareness module to excavate depth information and to mine ambiguous regions via adaptive depth-error weights, 2) a spatial-aware cross-modal interaction and a channel-aware cross-level interaction, exploiting the low-level boundary cues and amplifying high-level salient channels, and 3) a gated multi-scale predictor module to perceive the object saliency in different contextual scales. Besides its high performance, our proposed UTA network is depth-free for inference and runs in real-time with 43 FPS. Experimental evidence demonstrates that our proposed network not only surpasses the state-of-the-art methods on five public RGB-D SOD benchmarks by a large margin, but also verifies its extensibility on five public RGB SOD benchmarks. © 1992-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Trust-Aware Resilient Control and Coordination of Connected and Automated Vehicles

Trust-Aware Resilient Control and Coordination of Connected ...

引用

International Conference on Intelligent Transportation

作者： H.M. Sabbir Ahmad Ehsan Sabouni Wei Xiao Christos G. Cassandras Wenchao Li Department of Electrical & Computer Engineering Division of Systems Engineering Boston University Boston MA USA Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA USA

We address the security of a network of Connected and Automated Vehicles (CAVs) cooperating to navigate through a conflict area. Adversarial attacks such as Sybil attacks can cause safety violations resulting in collisions and traffic jams. In addition, uncooperative (but not necessarily adversarial) CAVs can also induce similar adversarial effects on the traffic network. We propose a decentralized resilient control and coordination scheme that mitigates the effects of adversarial attacks and uncooperative CAVs by utilizing a trust framework. Our trust-aware scheme can guarantee safe collision free coordination and mitigate traffic jams. Simulation results validate the theoretical guarantee of our proposed scheme, and demonstrate that it can effectively mitigate adversarial effects across different traffic scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Sensor Placement for Full-Set TDOA Localization Accounting for Sensor Location Errors

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Zhang, Chengjie Han, Xinyang Kong, He Ho, K.C. Southern University of Science and Technology Shenzhen Key Laboratory of Control Theory and Intelligent Systems Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology Shenzhen518055 China University of Missouri Electrical Engineering and Computer Science Department ColumbiaMO65211 United States

The positioning accuracy of a signal source is influenced by where the sensors are deployed. Studies in the literature for the optimal sensor placement (OSP) of localization often ignore the presence of sensor position errors. In practice, however, it is impossible to place the sensors precisely at the desired locations. This work designs OSP by accounting for the presence of Gaussian sensor position errors that are independent and identically distributed (IID), with the full set of Time Difference of Arrival measurements corrupted by Gaussian IID noise. The criterion is the A-optimality equal to the trace of the source position Cramer-Rao Bound (CRB). We show that the presence of sensor position errors introduces a multiplication factor to the same criterion for the case without sensor position errors. The latter factor is dependent on the ratio of the sensor position error power to the range difference noise power but independent of the sensor positions, implying that the A-optimality OSP in the presence of sensor position errors is the same as in the absence. To our knowledge, this is the first time such results have been derived. Simulation studies validate the derived OSP, show the minimal OSP performance gap with sensor positioning error and without, and illustrate the better source localization accuracy by OSP. © 1965-2011 IEEE.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

OCET: One-Dimensional Convolution Embedding Transformer for Stock Trend Prediction 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Yang, Peng Fu, Lang Zhang, Jian Li, Guiying Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Shenzhen Securities Information Co. Ltd. Shenzhen China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

Due to the strong data fitting ability of deep learning, the use of deep learning for quantitative trading has gradually sprung up in recent years. As a classical problem of quantitative trading, Stock Trend Prediction (STP) mainly predicts the movement of stock price in the future through the historical price information to better guide quantitative trading. In recent years, some deep learning work has made great progress in STP by effectively grasping long-term timing information. However, as a kind of real-time series data, short-term timing information is also very important, because stock trading is high-frequency and price fluctuates violently. And with the popularity of Transformer, there is a lack of an effective combination of feature extraction and Transformer in STP tasks. To make better use of short term information, we propose One-dimensional Convolution Embedding (OCE). Simultaneously, we introduce effective feature extraction with Transformer into STP problem to extract feature information and capture long-term timing information. By combining OCE and Transformer organically, we propose a noval STP prediction model, One-dimensional Convolution Embedding Transformer (OCET), to capture long-term and short-term time series information. Finally, OCET achieves a highest accuracy up to 0.927 in public benchmark FI-2010 When reasoning speed is twice that of SOTA models and a highest accuracy of 0.426 in HKGSAS-2020. Empirical results on these two datasets show that our OCET is significantly superior than other algorithms in STP tasks. Code are available at https://***/langgege-cqu/OCET. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

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：