检索结果-内蒙古大学图书馆

Learning Object Relations with Graph Neural Networks for Target-Driven Grasping in Dense Clutter

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lou, Xibai Yang, Yang Choi, Changhyun The Department of Electrical and Com Puter Engineering Univ. of Minnesota Minneapolis United States The Department of Computer Science and Engineering Univ. of Minnesota Minneapolis United States

Robots in the real world frequently come across identical objects in dense clutter. When evaluating grasp poses in these scenarios, a target-driven grasping system requires knowledge of spatial relations between scene objects (e.g., proximity, adjacency, and occlusions). To efficiently complete this task, we propose a target-driven grasping system that simultaneously considers object relations and predicts 6-DoF grasp poses. A densely cluttered scene is first formulated as a grasp graph with nodes representing object geometries in the grasp coordinate frame and edges indicating spatial relations between the objects. We design a Grasp Graph Neural Network (G2N2) that evaluates the grasp graph and finds the most feasible 6-DoF grasp pose for a target object. Additionally, we develop a shape completion-assisted grasp pose sampling method that improves sample quality and consequently grasping efficiency. We compare our method against several baselines in both simulated and real settings. In real-world experiments with novel objects, our approach achieves a 77.78% grasping accuracy in densely cluttered scenarios, surpassing the best-performing baseline by more than 15%. Supplementary material is available at https://***/***/graphgrasping. © 2022, CC BY.

关键词： Deep learning

A Critical Analysis on Cybercrimes

学校读者我要写书评

暂无评论

A Critical Analysis on Cybercrimes

Business Analytics for Technology and Security (ICBATS), International Conference on

作者： Sadaf Hussain Saher Ashraf Seep Hussam Al Hamadi Zain Ul Abideen Department of Computer Science Institute of Management Science Lahore Pakistan College of Engineering IT University of Dubai School of Com[puter Secince NCBA&E Lahore Lahore Pakistan Applied Science Research Center Applied Science Private University Amman Jordan

Network of computers and associated equipment that spans the globe is commonly known as cyberspace. Countries have grown more dependent on this interconnected system, which has permeated almost every aspect of daily life. Social media has emerged as a key factor in cybercrime, alongside other activities such as online shopping and banking. In today’s world, cyber-attacks can have significant strategic consequences by giving attackers control of networks and access to sensitive information. The recent incidents involving the Iranian and Indian nuclear infrastructure serve as prominent examples of such dangers. Various sectors such as banks, hospitals, and government websites have all been targets of cyber-attacks, resulting in identity theft and hacking. To combat this growing problem, it is essential to make dedicated efforts to address the cyber threat in an appropriate manner. It is crucial to identify the most recent cyber threats and explore the best possible means of dealing with them, which is the need of the hour. This paper provides a comprehensive discussion of cybercrime and its various forms in Pakistan, along with its outcomes. Additionally, it covers the Prevention of Electronic Act - 2016, a much- needed legislation in a society where information technology has become an integral aspect of daily life. The study also highlights the exploitation of this act and the loopholes in the existing infrastructure. Furthermore, the paper includes an analysis of the effectiveness of measures required to mitigate the latest cyber threats and explains the measures implemented, as well as additional countermeasures needed to combat this threat.

关键词： computers Unsolicited e-mail Current measurement Legislation Telecommunications Electronic commerce computer crime

CL-MASR: A Continual Learning Benchmark for Multilingual ASR

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Libera, Luca Della Mousavi, Pooneh Zaiem, Salah Subakan, Cem Ravanelli, Mirco The Gina Cody School of Engineering and Computer Science Concordia University Montreal Canada LTCI Télécom Paris Paris France The Department of Computer Science and Software Engineering Université Laval Québec Canada

Modern multilingual automatic speech recognition (ASR) systems like Whisper have made it possible to transcribe audio in multiple languages with a single model. However, current state-of-the-art ASR models are typically evaluated on individual languages or in a multi-task setting, overlooking the challenge of continually learning new languages. There is insufficient research on how to add new languages without losing valuable information from previous data. Furthermore, existing continual learning benchmarks focus mostly on vision and language tasks, leaving continual learning for multilingual ASR largely unexplored. To bridge this gap, we propose CL-MASR, a benchmark designed for studying multilingual ASR in a continual learning setting. CL-MASR provides a diverse set of continual learning methods implemented on top of large-scale pretrained ASR models, along with common metrics to assess the effectiveness of learning new languages while addressing the issue of catastrophic forgetting. To the best of our knowledge, CL-MASR is the first continual learning benchmark for the multilingual ASR task. The code is available at https://***/speechbrain/benchmarks. © 2023, CC BY.

关键词： Bridges

CL-MASR: A Continual Learning Benchmark for Multilingual ASR

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Libera, Luca Della Mousavi, Pooneh Zaiem, Salah Subakan, Cem Ravanelli, Mirco Gina Cody School of Engineering and Computer Science Concordia University Montreal Canada LTCI Télécom Paris Paris France Department of Computer Science and Software Engineering Université Laval Québec Canada

关键词： Bridges

An Integration Test Order Strategy to Consider Control Coupling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jiang, Shujuan Zhang, Miao Zhang, Yanmei Wang, Rongcun Yu, Qiao Keung, Jacky Wai Mine Digitiza-tion Engineering Research Center of Ministry of Education School of Com-puter Science and Technology China University of Mining and Technology Xu-zhou221116 China City University of Hong Kong Department of Computer Science Kowloon Hong Kong Jiangsu Normal University School of Computer Science and Technology Xu-zhou221116 China

Integration testing is a very important step in software testing. Existing methods evaluate the stubbing cost for class inte-gration test orders by considering only the interclass direct relationships such as inheritance, aggregation, and association, but they omit the interclass indirect relationship caused by control coupling, which can also affect the test orders and the stubbing cost. In this paper, we introduce an integration test order strategy to consider control coupling. We advance the concept of transitive relationship to describe this kind of interclass dependency and propose a new measurement method to estimate the complexity of control coupling, which is the complexity of stubs created for a transitive relationship. We evaluate our integration test order strategy on 10 programs on various scales. The results show that considering the transitive relationship when generating class integration test orders can significantly reduce the stubbing cost for most programs and that our integration test order strategy obtains satisfactory results more quickly than other methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Integration

A Dynamic Road Incident Information Delivery Strategy to Reduce Urban Traffic Congestion

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2018年第5期5卷 934-945页

作者： Liang Qi Mengchu Zhou Wenjing Luan IEEE Department of Computer Scicnce and Technology Shandong University of Science and TechnologyQingdao 266590China Department of Computer Science Tongji UniversityShanghai 201804China Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewark NJ 07102USA Key Laboratory of Embedded System and Service Computing Ministry of EducationShanghai Electronic Transactions and Information Service Collaborative Innovation CenterDepartment of Com-puter ScienceTongji UniversityShanghai 201804China

Advanced information and communication technolo-gies can be used to facilitate traffic incident *** an incident is detected and blocks a road link,in order to reduce the incident-induced traffic congestion,a dynamic strategy to deliver incident information to selected drivers and help them make detours in urban areas is proposed by this ***-dependent shortest path algorithms are used to generate a subnetwork where vehicles should receive such information.A simulation approach based on an extended cell transmission model is used to describe traffic flow in urban networks where path information and traffic flow at downstream road links are well *** results reveal the influences of some major parameters of an incident-induced congestion dissipation process such as the ratio of route-changing vehicles to the total vehicles,operation time interval of the proposed strategy,traffic density in the traffic network,and the scope of the area where traffic incident information is *** results can be used to improve the state of the art in preventing urban road traffic congestion caused by incidents.

关键词： Cell transmission model(CTM) intelligent transportation systems(ITS) traffic incident management(TIM) urban traffic congestion

Spectral instability of the peaked periodic wave in the reduced ostrovsky equations

学校读者我要写书评

暂无评论

arXiv 2019年

作者： GEYER, ANNA PELINOVSKY, DMITRY E. Delft Institute of Applied Mathematics Faculty Electrical Engineering Mathematics and Com-puter Science Delft University of Technology Mekelweg 4 Delft2628 CD Netherlands Department of Mathematics and Statistics McMaster University HamiltonONL8S 4K1 Canada Department of Applied Mathematics Nizhny Novgorod State Technical University 24 Minin street Nizhny Novgorod603950 Russia

We show that the peaked periodic traveling wave of the reduced Ostrovsky equations with quadratic and cubic nonlinearity is spectrally unstable in the space of square integrable periodic functions with zero mean and the same period. The main novelty of our result is that the spectrum of a linearized operator at the peaked periodic wave completely covers a closed vertical strip of the complex plane. In order to obtain this instability, we prove an abstract result on spectra of operators under compact perturbations. This justifies the truncation of the linearized operator at the peaked periodic wave to its differential part for which the spectrum is then computed explicitly. Copyright © 2019, The Authors. All rights reserved.

关键词： Linearization

The medical segmentation decathlon

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Antonelli, Michela Reinke, Annika Bakas, Spyridon Farahani, Keyvan Kopp-Schneider, Annette Landman, Bennett A. Litjens, Geert Menze, Bjoern Ronneberger, Olaf Summers, Ronald M. van Ginneken, Bram Bilello, Michel Bilic, Patrick Christ, Patrick F. Do, Richard K.G. Gollub, Marc J. Heckers, Stephan H. Huisman, Henkjan Jarnagin, William R. McHugo, Maureen K. Napel, Sandy Golia Pernicka, Jennifer S. Rhode, Kawal Tobon-Gomez, Catalina Vorontsov, Eugene Hulsmon, Hankan Meakin, James A. Ourselin, Sebastien Wiesenfarth, Manuel Arbeláez, Pablo Bae, Byeonguk Chen, Sihong Daza, Laura Feng, Jianjiang He, Baochun Isensee, Fabian Ji, Yuanfeng Jia, Fucang Kim, Namkug Kim, Ildoo Merhof, Dorit Pai, Akshay Park, Beomhee Perslev, Mathias Rezaiifar, Ramin Rippel, Oliver Sarasua, Ignacio Shen, Wei Son, Jaemin Wachinger, Christian Wang, Liansheng Wang, Yan Xia, Yingda Xu, Daguang Xu, Zhanwei Zheng, Yefeng Simpson, Amber L. Maier-Hein, Lena Cardoso, M. Jorge School of Biomedical Engineering & Imaging Sciences King’s College London London United Kingdom Heidelberg Germany Heidelberg Germany Faculty of Mathematics and Computer Science University of Heidelberg Heidelberg Germany University of Pennsylvania PhiladelphiaPA United States BethesdaMD United States Heidelberg Germany Electrical Engineering and Computer Science Vanderbilt University NashvilleTN United States Radboud University Medical Center Radboud Institute for Health Sciences Nijmegen Netherlands Quantitative Biomedicine University of Zurich Zurich Switzerland DeepMind London United Kingdom School of Computing Department of Biomedical and Molecular Sciences Queen’s University KingstonON Canada Department of Surgery Memorial Sloan Kettering Cancer Center New YorkNY United States BethesdaMD United States Department of Informatics Technische Universität München Germany Department of Radiology Memorial Sloan Kettering Cancer Center New YorkNY United States Department of Psychiatry & Behavioral Sciences Vanderbilt University Medical Center NashvilleTN United States Department of Radiology Stanford University StanfordCA United States Department of Computer Science and Software Engineering École Polytechnique de Montréal Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Medical Faculty University of Heidelberg Heidelberg Germany VUNO Inc. Seoul Korea Republic of Universidad de los Andes Colombia Department of Automation Tsinghua University Beijing China Heidelberg Germany Department of Computer Science Xiamen University Xiamen361005 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Kakao Brain Korea Republic of Institute of Imaging & Computer Vision RWTH Aachen University Aachen Germany Cere

International challenges have become the de facto standard for comparative assessment of image analysis algorithms given a specific task. Segmentation is so far the most widely investigated medical image processing task, but the various segmentation challenges have typically been organized in isolation, such that algorithm development was driven by the need to tackle a single specific clinical problem. We hypothesized that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. To investigate the hypothesis, we organized the Medical Segmentation Decathlon (MSD)—a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities. The underlying data set was designed to explore the axis of difficulties typically encountered when dealing with medical images, such as small data sets, unbalanced labels, multi-site data and small objects. The MSD challenge confirmed that algorithms with a consistent good performance on a set of tasks preserved their good average performance on a different set of previously unseen tasks. Moreover, by monitoring the MSD winner for two years, we found that this algorithm continued generalizing well to a wide range of other clinical problems, further confirming our hypothesis. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms are mature, accurate, and generalize well when retrained on unseen tasks;(2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability;(3) the training of accurate AI segmentation models is now commoditized to non AI *** Codes 68T07. © 2021, CC BY-NC-SA.

关键词： Image segmentation

A Visual-attention-based Mobile 3D Mapping Method for Robots

学校读者我要写书评

暂无评论

自动化学报 2017年第7期43卷 1248-1256页

作者： Binghua Guo Hongyue Dai Zhonghua Li Department of Electrical and Information Engineering Zhaoqing University Zhaoqing 526061 China School of Data and Com- puter Science Sun Yat-sen University Guangzhou 510275. China

Human visual attention is highly *** artificial vision system that imitates this mechanism increases the efficiency,intelligence,and robustness of mobile robots in environment *** paper presents a 3-D modeling method based on visual attention for mobile *** method uses the distance-potential gradient as motion contrast and combines the visual features extracted from the scene with a mean shift segment algorithm to detect conspicuous objects in the surrounding *** method takes the saliency of objects as priori information,uses Bayes＇ theorem to fuse sensor modeling and grid priori modeling,and uses the projection method to create and update the 3-D environment *** results of the experiments and performance evaluation illustrate the capabilities of our approach in generating accurate 3-D maps.

关键词：智能移动机器人三维地图视觉系统注意力绘制方法环境建模传感器建模贝叶斯定理