检索结果-内蒙古大学图书馆

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Qitian Wu Rui Gao Hongyuan Zha Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University University of Texas at Austin Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University and School of Data Science Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen

ISBN: (纸本)9781713845393

There are two types of deep generative models: explicit and implicit. The former defines an explicit density form that allows likelihood inference; while the latter targets a flexible transformation from random noise to generated samples. While the two classes of generative models have shown great power in many applications, both of them, when used alone, suffer from respective limitations and drawbacks. To take full advantages of both models and enable mutual compensation, we propose a novel joint training framework that bridges an explicit (unnormalized) density estimator and an implicit sample generator via Stein discrepancy. We show that our method 1) induces novel mutual regularization via kernel Sobolev norm penalization and Moreau-Yosida regularization, and 2) stabilizes the training dynamics. Empirically, we demonstrate that proposed method can facilitate the density estimator to more accurately identify data modes and guide the generator to output higher-quality samples, comparing with training a single counterpart. The new approach also shows promising results when the training samples are contaminated or limited.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Unconstrained Ear Recognition Challenge 2023: Maximizing Performance and Minimizing Bias*

The Unconstrained Ear Recognition Challenge 2023: Maximizing...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Ž. Emeršić T. Ohki M. Akasaka T. Arakawa S. Maeda M. Okano Y. Sato A. George S. Marcel I. I. Ganapathi S. S. Ali S. Javed N. Werghi S. G. Işık E. Sarıtaş H. K. Ekenel V. Hudovernik J. N. Kolf F. Boutros N. Damer G. Sharma A. Kamboj A. Nigam D. K. Jain G. Cámara-Chávez P. Peer V. Štruc University of Ljubljana (UL SI) Shizuoka University (SU JP) Idiap Research Institute (IDIAP CH) Electrical Engineering and Computer Science Department Khalifa University (KU UAE) Department of Computer Engineering (ITU TR) Istanbul Technical University Microelectronic Guidance and Electro-Optical Group ASELSAN Fraunhofer Institute for Computer Graphics Research IGD (IGD DE) Technische Universität Darmstadt (TUD DE) Indian Institute of Technology Mandi (IIT IN) HCL Imaging and Robotics R&D Lab (HCL IN) School of Artificial Intelligence Dalian University of Technology (DLUT CN) Federal University of Ouro Preto (UFOP BR)

The paper provides a summary of the 2023 Unconstrained Ear Recognition Challenge (UERC), a benchmarking effort focused on ear recognition from images acquired in uncontrolled environments. The objective of the challenge was to evaluate the effectiveness of current ear recognition techniques on a challenging ear dataset while analyzing the techniques from two distinct aspects, i.e., verification performance and bias with respect to specific demographic factors, i.e., gender and ethnicity. Seven research groups participated in the challenge and submitted a seven distinct recognition approaches that ranged from descriptor-based methods and deep-learning models to ensemble techniques that relied on multiple data representations to maximize performance and minimize bias. A comprehensive investigation into the performance of the submitted models is presented, as well as an in-depth analysis of bias and associated performance differentials due to differences in gender and ethnicity. The results of the challenge suggest that a wide variety of models (e.g., transformers, convolutional neural networks, ensemble models) is capable of achieving competitive recognition results, but also that all of the models still exhibit considerable performance differentials with respect to both gender and ethnicity. To promote further development of unbiased and effective ear recognition models, the starter kit of UERC 2023 together with the baseline model, and training and test data is made available from: http://***/

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Human-Human Physical Interaction System for Training Handwriting

A Human-Human Physical Interaction System for Training Handw...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： S. Buscaglione A. Noccaro C. Provenzale C. Bonsignori E. Ivanova L. Sparaci F. Taffoni E. Burdet D. Formica NEXT: Neurophysiology and Neuroengineering of Human-Technology Interaction Research Unit Università Campus Bio-Medico di Roma Italy Neurorobotics Lab Newcastle University Newcastle Upon Tyne UK Advanced Robotics and Human-Centred Technologies-CREO Laboratory Università Campus Bio-Medico di Roma Italy Department of Bioengineering Imperial College of Science Technology and Medicine UK School of Electric Engineering and Computer Science Queen Mary University of London UK Institute of Cognitive Sciences and Technologies (ISTC) National Research Council of Italy (CNR) Italy

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Handwriting training in childhood is known to influence academic success, foster self-esteem, and contribute to overall development. Previous studies underscored the positive impact of haptic feedback on handwriting learning using one-way communication systems that provided the trainee with haptic feedback based on pre-recorded trainer's movements. In this study, we propose a system involving bidirectional physical coupling (haptic communication) between a trainee and a trainer to exploit the advantages of haptic communication for motor task improvement, proved in tracking tasks. The system, composed of an interactive display and a coupling spring, was tested in a handwriting task performed by a dyad of healthy adults with different cursive handwriting backgrounds. The participants' performance demonstrated the feasibility of using this system for handwriting, opening the way for further studies to assess its benefits in handwriting improvement and learning.

关键词： Training Couplings Tracking Communication systems Biomechatronics Motors Haptic interfaces Springs Robots

来源：评论

学校读者我要写书评

暂无评论

Retinal Disorder Diagnosis Based on Hybrid Deep Learning Models

SSRN

引用

SSRN 2022年

作者： Sedik, Ahmed El-Hag, Noha A. El-Hoseny, Heba M. El-Banby, Ghada M. Khalaf, Ashraf A.M. Abd El-Samie, Fathi E. El-Shafai, Walid Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Egypt Menoufia University Egypt Department of Electronics and Electrical Communication Engineering Al-Obour High Institute for Engineering and Technology Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Deptartment of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh84428 Saudi Arabia Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtainedwith several modalities such as magnetic resonance (MR) and confocal microscopy need to be classified for anomaly *** MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, braintumors are represented as areas composed of abnormal cells that need to be detected. In addition, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify © 2022, The Authors. All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

YOLOStereo3D: A step back to 2D for efficient stereo 3D detection

arXiv

引用

arXiv 2021年

作者： Liu, Yuxuan Wang, Lujia Liu, Ming Department of Electronic and Computer Engineering Robotics and Multi-Perception Laborotary Hong Kong University of Science and Technology Hong Kong Cloud Computing Lab of Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from disparity estimation, making them extremely computationally expensive. To enable real-world deployments of vision detection with binocular images, we take a step back to gain insights from 2D imagebased detection frameworks and enhance them with stereo features. We incorporate knowledge and the inference structure from real-time one-stage 2D/3D object detector and introduce a light-weight stereo matching module. Our proposed framework, YOLOStereo3D, is trained on one single GPU and runs at more than ten fps. It demonstrates performance comparable to state-of-the-art stereo 3D detection frameworks without usage of LiDAR data. The code will be published in https://***/Owen-Liuyuxuan/visualDet3D. Copyright © 2021, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

SABER: Data-driven motion planner for autonomously navigating heterogeneous robots

arXiv

引用

arXiv 2021年

作者： Schperberg, Alexander Tsuei, Stephanie Soatto, Stefano Hong, Dennis The Robotics and Mechanisms Laboratory Department of Mechanical and Aerospace Engineering University of California Los AngelesCA90095 United States The UCLA Vision Lab Department of Computer Science University of California Los AngelesCA90095 United States

We present an end-to-end online motion planning framework that uses a data-driven approach to navigate a heterogeneous robot team towards a global goal while avoiding obstacles in uncertain environments. First, we use stochastic model predictive control (SMPC) to calculate control inputs that satisfy robot dynamics, and consider uncertainty during obstacle avoidance with chance constraints. Second, recurrent neural networks are used to provide a quick estimate of future state uncertainty considered in the SMPC finite-time horizon solution, which are trained on uncertainty outputs of various simultaneous localization and mapping algorithms. When two or more robots are in communication range, these uncertainties are then updated using a distributed Kalman filtering approach. Lastly, a Deep Q-learning agent is employed to serve as a high-level path planner, providing the SMPC with target positions that move the robots towards a desired global goal. Our complete methods are demonstrated on a ground and aerial robot simultaneously (code available at: https://***/AlexS28/SABER). Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Electrical frequency discrimination by fungi Pleurotus ostreatus

arXiv

引用

arXiv 2022年

作者： Przyczyna, Dawid Szacilowski, Konrad Chiolerio, Alessandro Adamatzky, Andrew Academic Centre for Materials and Nanotechnology AGH University of Science and Technology Krakow Poland Istituto Italiano di Tecnologia Center for Converging Technologies Soft Bioinspired Robotics Via Morego 30 Genova16165 Italy Unconventional Computing Lab UWE Bristol United Kingdom Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece

We stimulate mycelian networks of oyster fungi Pleurotus ostreatus with low frequency sinusoidal electrical signals. We demonstrate that the fungal networks can discriminate between frequencies in a fuzzy or threshold based manner. Details about the mixing of frequencies by the mycelium networks are provided. The results advance the novel field of fungal electronics and pave ground for the design of living, fully recyclable, electron devices. Copyright © 2022, The Authors. All rights reserved.

关键词： Fungi

来源：评论

学校读者我要写书评

暂无评论

PCR-Pro: 3D Sparse and Different Scale Point Clouds Registration and Robust Estimation of Information Matrix for Pose Graph SLAM 8

PCR-Pro: 3D Sparse and Different Scale Point Clouds Registra...

引用

8th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, CYBER 2018

作者： Maqbool Bhutta, M. Usman Liu, Ming Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Robotics Multi-Perception Lab Hong Kong

ISBN: (纸本)9781538670569

For both indoor and outdoor environments, we propose an efficient and novel method for different scales and sparse 3D point clouds registration that cannot be handled by the current popular ICP approaches. Our algorithm efficiently detects the scale difference between point clouds and uses the keyframes to estimate the relative pose for calculating the scale difference. The algorithm applies a filter and computes the final transformation which coverages to a global minimum. The good estimation of transform and scale helps in the calculation of the covariance matrix using a closed form solution efficiently. This covariance between point clouds helps in the estimation of information matrix for pose-graph SLAM. © 2018 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Roller chain-like robot for steel bridge inspection 9

Roller chain-like robot for steel bridge inspection

引用

9th International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII 2019

作者： Nguyen, Son Thanh La, Hung Manh Advanced Robotics and Automation Lab Department of Computer Science and Engineering University of Nevada RenoNV89557 United States

This paper presents a novel design of steel bridge/structure inspection robot. Compared to most existing robots designed to work on particular surface contour of steel structures such as flat or curving, the proposed roller chain-like robot can implement and transfer smoothly on many kind of steel surfaces. The developed robot can be applied to inspection tasks for steel bridges with complicated structures. The robot is able to carry cameras, sensors for visual and specialized examination. Rigorous analysis of robot kinematics, adhesion force and turn-over failure has been conducted to demonstrate the stability of the proposed design. Mechanical and magnetic force analysis together with turn-over failure investigation can serve as an useful framework for designing various steel climbing robots in the future. Experimental results and field deployments prove the adhesion, climbing, inspection capability of the developed robot. Copyright © SHMII 2019. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

A decision aid for the port placement problem in robot-assisted hysterectomy

引用

Laparoscopic, Endoscopic and Robotic Surgery 2023年第2期6卷 43-56页

作者： Mohammad R.Maddah Jean-Marc Classe Isabelle Jaffre Keith A.Watson Katherine S.Lin Damien Chablat Cedric Dumas Caroline G.L.Cao Department of Biomedical Industrialand Human Factors EngineeringWright State University3640 Colonel Glenn HwyDaytonOHUSA Department of Automatique Productique et InformatiqueIMT Atlantique4 Rue Alfred KastlerNantesFrance Laboratoire des Sciences Du Numerique de Nantes(LS2N) 2 Chemin de La Houssini?ereNantesFrance Centre Rene Gauducheau ICO Institut de Cancerologie de L'Ouest BD Professeur Jacques MonodSaint-HerblainFrance Brethen Center for Surgical Advancement in Robotics and Minimally Invasive Surgery Miami Valley HospitalOne Wyoming StreetDaytonOHUSA Department of Computer Science IMT AtlantiqueTechnopole Brest-IroiseBrestFrance Laboratoire des Sciences et Techniques de L'information de La Communication et de La Connaissance(Lab-STICC) Technopole Brest-IroiseBrestFrance Future Industries Institute STEMUniversity of South AustraliaMawson Lakes BlvdMawson LakesAustralia

Objective:In robot-assisted minimally invasive surgery,proper port positioning ensures that surgical tools have adequate access to the surgical site and avoids mid-surgery collisions of robotic *** date,several guidelines have been proposed for more accurate port ***,challenges remain due to variations in patient morphology,anatomy,and,in particular,organ displacement due to insuf-flation in certain laparoscopic *** objective of this study was to design and develop a de-cision aid for optimal port placement in robot-assisted hysterectomy that accounts for patient variability and organ displacement due to ***:Three components were constructed:a robot model,a patient-specific model,and an opti-mization *** three components were integrated,and the system was verified using four different patients who underwent robotic *** verified,two expert surgeons were asked to evaluate the decision aid for face and construct validity.A usability test was conducted using a torso phantom with target organs located in three different *** expert surgeons performed a simulated hysterectomy task with and without the decision aid to evaluate performance and ***:The optimization algorithm was sensitive to individual differences in anatomy in the four *** surgeons successfully established face and construct *** test results showed a 28%-40% reduction in time to task completion with the optimized ports compared to expert-determined port locations without using the decision ***:The decision aid,based on an individualized patient-specific model,robot model,and optimization algorithm,was shown to be effective at addressing the challenges of displaced organs due to insufflation in robot-assisted *** face and construct validity of the decision aid was established by expert surgeons,while efficiency gains in task performance were demonstrated experim

关键词： Optimization Planning tool Patient model Robotic hysterectomy

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：