检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Santina, Cosimo Della Corbato, Carlos Hernandez Sisman, Burak Leiva, Luis A. Arapakis, Ioannis Vakalellis, Michalis Vanderdonckt, Jean D’Haro, LuisFernando Manzi, Guido Becchio, Cristina Elamrani, Aïda Alirezaei, Mohsen Castellano, Ginevra Dimarogonas, Dimos V. Ghosh, Arabinda Haesaert, Sofie Soudjani, Sadegh Stroeve, Sybert Verschure, Paul Bacciu, Davide Deroy, Ophelia Bahrami, Bahador Gallicchio, Claudio Hauert, Sabine Sanz, Ricardo Lanillos, Pablo Iacca, Giovanni Sigg, Stephan Gasulla, Manel Steels, Luc Sierra, Carles Department of Cognitive Robotics Delft University of Technology Delft Netherlands Oberpfaffenhofen Germany Department of Computer Science University of Luxembourg Luxembourg 4 Telefónica I+D Spain AEGIS IT Research GmbH Germany Université catholique de Louvain Belgium Speech Technology and Machine Learning Group ETSI de Telecomunicación Universidad Politécnica de Madrid Madrid Spain Alien Venture Studio Alien Technology Transfer Rome Italy Hamburg Germany Institut Jean Nicod École Normale Supérieure Paris France Research Technology and Development Department Digital Industry Software Helmond Netherlands Department of Information Technology Uppsala University Uppsala Sweden Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Max Planck Institute for Software Systems Kaiserslautern Germany Department of Electrical Engineering Control Systems Group Eindhoven University of Technology Eindhoven Netherlands Amsterdam Netherlands Donders Centre for Neuroscience Radboud University Nijmegen Netherlands Computer Science Department University of Pisa Pisa Italy Faculty of Philosophy Philosophy of Science The Study of Religion Ludwig Maximilian University of Munich Munich Germany School of Engineering Mathematics and Technology University of Bristol Bristol United Kingdom Autonomous Systems Laboratory Universidad Politécnica de Madrid Spain Madrid Spain Department of Information Engineering and Computer Science University of Trento Trento Italy Department of Information and Communications Engineering Aalto University Espoo Finland Department of Electronic Engineering Universitat Politècnica de Catalunya Barcelona Spain Studio Stelluti Brussels Belgium Barcelona Spain

Consciousness has been historically a heavily debated topic in engineering, science, and philosophy. On the contrary, awareness had less success in raising the interest of scholars in the past. However, things are changing as more and more researchers are getting interested in answering questions concerning what awareness is and how it can be artificially generated. The landscape is rapidly evolving, with multiple voices and interpretations of the concept being conceived and techniques being developed. The goal of this paper is to summarize and discuss the ones among these voices that are connected with projects funded by the EIC Pathfinder Challenge called "Awareness Inside", a nonrecurring call for proposals within Horizon Europe that was designed specifically for fostering research on natural and synthetic awareness. In this perspective, we dedicate special attention to challenges and promises of applying synthetic awareness in robotics, as the development of mature techniques in this new field is expected to have a special impact on generating more capable and trustworthy embodied systems. © 2024, CC BY.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Open-set face recognition for small galleries using siamese networks

arXiv

引用

arXiv 2021年

作者： Salomon, Gabriel Britto, Alceu Vareto, Rafael H. Schwartz, William R. Menotti, David Vision Robotics and Imaging Laboratory Universidade Federal Do Paraná 82590300 Brazil Ppgia Pontifícia Universidade Católica Do Paraná 80215901 Brazil Smart Sense Laboratory Department of Computer Science Universidade Federal de Minas Gerais 31270901 Brazil

Face recognition has been one of the most relevant and explored fields of Biometrics. In real-world applications, face recognition methods usually must deal with scenarios where not all probe individuals were seen during the training phase (openset scenarios). Therefore, open-set face recognition is a subject of increasing interest as it deals with identifying individuals in a space where not all faces are known in advance. This is useful in several applications, such as access authentication, on which only a few individuals that have been previously enrolled in a gallery are allowed. The present work introduces a novel approach towards open-set face recognition focusing on small galleries and in enrollment detection, not identity retrieval. A Siamese Network architecture is proposed to learn a model to detect if a face probe is enrolled in the gallery based on a verification-like approach. Promising results were achieved for small galleries on experiments carried out on Pubfig83, FRGCv1 and LFW datasets. State-ofthe- art methods like HFCN and HPLS were outperformed on FRGCv1. Besides, a new evaluation protocol is introduced for experiments in small galleries on LFW. © 2021, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

EFaR 2023: Efficient Face Recognition Competition

EFaR 2023: Efficient Face Recognition Competition

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Jan Niklas Kolf Fadi Boutros Jurek Elliesen Markus Theuerkauf Naser Damer Mohamad Alansari Oussama Abdul Hay Sara Alansari Sajid Javed Naoufel Werghi Klemen Grm Vitomir Štruc Fernando Alonso-Fernandez Kevin Hernandez Diaz Josef Bigun Anjith George Christophe Ecabert Hatef Otroshi Shahreza Ketan Kotwal Sébastien Marcel Iurii Medvedev Bo Jin Diogo Nunes Ahmad Hassanpour Pankaj Khatiwada Aafan Ahmad Toor Bian Yang Fraunhofer Institute for Computer Graphics Research IGD Germany TU Darmstadt Germany Department of Electrical and Computer Engineering Khalifa University Abu Dhabi United Arab Emirates Laboratory for Machine Intelligence Faculty of Electrical Engineering University of Ljubljana Slovenia Halmstad University Sweden Idiap Research Institute Martigny Switzerland École Polytechnique Fédérale de Lausanne (EPFL) Lausanne Switzerland Université de Lausanne (UNIL) Lausanne Switzerland Institute of Systems and Robotics University of Coimbra Coimbra Portugal Department of Information Security and Communication Technology eHealth and Welfare Security Group Norwegian University of Science and Technology Norway

This paper presents the summary of the Efficient Face Recognition Competition (EFaR) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition received 17 submissions from 6 different teams. To drive further development of efficient face recognition models, the submitted solutions are ranked based on a weighted score of the achieved verification accuracies on a diverse set of benchmarks, as well as the deployability given by the number of floating-point operations and model size. The evaluation of submissions is extended to bias, cross-quality, and large-scale recognition benchmarks. Overall, the paper gives an overview of the achieved performance values of the submitted solutions as well as a diverse set of baselines. The submitted solutions use small, efficient network architectures to reduce the computational cost, some solutions apply model quantization. An outlook on possible techniques that are underrepresented in current solutions is given as well.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Geometry Constrained Weakly Supervised Object Localization

arXiv

引用

arXiv 2020年

作者： Lu, Weizeng Jia, Xi Xie, Weicheng Shen, Linlin Zhou, Yicong Duan, Jinming Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China School of Computer Science University of Birmingham United Kingdom Department of Computer and Information Science University of Macau China

We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization (WSOL). GC-Net consists of three modules: a detector, a generator and a classifier. The detector predicts the object location defined by a set of coefficients describing a geometric shape (i.e. ellipse or rectangle), which is geometrically constrained by the mask produced by the generator. The classifier takes the resulting masked images as input and performs two complementary classification tasks for the object and background. To make the mask more compact and more complete, we propose a novel multi-task loss function that takes into account area of the geometric shape, the categorical cross-entropy and the negative entropy. In contrast to previous approaches, GC-Net is trained end-to-end and predict object location without any post-processing (e.g. thresholding) that may require additional tuning. Extensive experiments on the CUB-200-2011 and ILSVRC2012 datasets show that GC-Net outperforms state-of-the-art methods by a large margin. Our source code is available at https://***/lwzeng/GC-Net. Copyright © 2020, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

CertainOdom: Uncertainty Weighted Multi-task Learning Model for LiDAR Odometry Estimation

CertainOdom: Uncertainty Weighted Multi-task Learning Model ...

引用

IEEE International Conference on robotics and Biomimetics

作者： Leyuan Sun Guanqun Ding Yusuke Yoshiyasu Fumio Kanehiro Department of Intelligent and Mechanical Interaction Systems Graduate School of Science and Technology University of Tsukuba Tsukuba Ibaraki Japan CNRS-AIST Joint Robotics Laboratory (JRL) IRL National Institute of Advanced Industrial Science and Technology (AIST). Digital Architecture Research Center (DARC) National Institute of Advanced Industrial Science and Technology (AIST) Tokyo Japan Computer Vision Research Team Artificial Intelligence Research Center (AIRC) National Institute of Advanced Industrial Science and Technology (AIST) Japan

ISBN: (纸本)9781665481106

As a basic and indispensable module, LiDAR odom-etry estimation is widely used in robotics. In recent years, learning-based modeling approaches for odometry estimation have been validated to be feasible. However, it is necessary to consider security factors as the highest priorities when we apply the learning-based model to certain high-risk real-world scenarios, such as autonomous driving. The odometry uncertainty estimation provides more valuable information for downstream tasks, such as route planning and navigation. In this paper, we propose an end-to-end neural network (namely CertainOdom) to solve odometry and uncertainty estimation tasks by applying multi-task learning. Instead of using the manually-tuned hyper-parameters, we employ the learnable uncertainties to weigh the balance between the error of translation and orientation in the loss function. We evaluate the estimated trajectory and uncertainty on KITTI dataset. We also compare the robustness against the traditional geometry-based methods on our artificially degraded KITTI LiDAR dataset. Extensive experimental results show that our model with uncertainty weighted loss achieves competitive performance in LiDAR odometry estimation. We also explain our uncertainties qualitatively and quantitatively.

关键词： Uncertainty Laser radar Biological system modeling Estimation Multitasking Robustness Trajectory

来源：评论

学校读者我要写书评

暂无评论

Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network

arXiv

引用

arXiv 2021年

作者： Wan, Jun Xi, Hui Zhou, Jie Lai, Zhihui Pedrycz, Witold Wang, Xu Sun, Hang School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan430073 China College of Computer Science and Software Engineering Shen zhen University Shenzhen518060 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Department of Electrical & Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland College of Computer and Information Technology China Three Gorges University Yichang HuBei China

Current fully-supervised facial landmark detection methods have progressed rapidly and achieved remarkable performance. However, they still suffer when coping with faces under large poses and heavy occlusions for inaccurate facial shape constraints and insufficient labeled training samples. In this paper, we propose a semi-supervised framework, i.e., a Self-Calibrated Pose Attention Network (SCPAN) to achieve more robust and precise facial landmark detection in challenging scenarios. To be specific, a Boundary-Aware Landmark Intensity (BALI) field is proposed to model more effective facial shape constraints by fusing boundary and landmark intensity field information. Moreover, a Self-Calibrated Pose Attention (SCPA) model is designed to provide a self-learned objective function that enforces intermediate supervision without label information by introducing a self-calibrated mechanism and a pose attention mask. We show that by integrating the BALI fields and SCPA model into a novel self-calibrated pose attention network, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved. The experimental results obtained for challenging benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in the literature. Copyright © 2021, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Enhance to read better: A multi-task adversarial network for handwritten document image enhancement

arXiv

引用

arXiv 2021年

作者： Jemni, Sana Khamekhem Souibgui, Mohamed Ali Kessentini, Yousri Fornés, Alicia MIR@CL: Multimedia InfoRmation systems and Advanced Computing Laboratory Computer Vision Center Computer Science Department Universitat Autònoma de Barcelona Spain Digital Research Center of Sfax B.P. 275 Sakiet Ezzit Sfax3021 Tunisia SM@RTS : Laboratory of Signals SysteMs ARtificial Intelligence and neTworkS

Handwritten document images can be highly affected by degradation for different reasons: Paper ageing, daily-life scenarios (wrinkles, dust, etc.), bad scanning process and so on. These artifacts raise many readability issues for current Handwritten Text Recognition (HTR) algorithms and severely devalue their efficiency. In this paper, we propose an end to end architecture based on Generative Adversarial Networks (GANs) to recover the degraded documents into a clean and readable form. Unlike the most well-known document binarization methods, which try to improve the visual quality of the degraded document, the proposed architecture integrates a handwritten text recognizer that promotes the generated document image to be more readable. To the best of our knowledge, this is the first work to use the text information while binarizing handwritten documents. Extensive experiments conducted on degraded Arabic and Latin handwritten documents demonstrate the usefulness of integrating the recognizer within the GAN architecture, which improves both the visual quality and the readability of the degraded document images. Moreover, we outperform the state of the art in H-DIBCO challenges, after fine tuning our pre-trained model with synthetically degraded Latin handwritten images, on this task. © 2021, CC BY.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient MedSAMs: Segment Anything in Medical Images on Laptop

arXiv

引用

arXiv 2024年

作者： Ma, Jun Li, Feifei Kim, Sumin Asakereh, Reza Le, Bao-Hiep Nguyen-Vu, Dang-Khoa Pfefferle, Alexander Wei, Muxin Gao, Ruochen Lyu, Donghang Yang, Songxiao Purucker, Lennart Marinov, Zdravko Staring, Marius Lu, Haisheng Dao, Thuy Thanh Ye, Xincheng Li, Zhi Brugnara, Gianluca Vollmuth, Philipp Foltyn-Dumitru, Martha Cho, Jaeyoung Mahmutoglu, Mustafa Ahmed Bendszus, Martin Pflüger, Irada Rastogi, Aditya Ni, Dong Yang, Xin Zhou, Guang-Quan Wang, Kaini Heller, Nicholas Papanikolopoulos, Nikolaos Weight, Christopher Tong, Yubing Udupa, Jayaram K. Patrick, Cahill J. Wang, Yaqi Zhang, Yifan Contijoch, Francisco McVeigh, Elliot Ye, Xin He, Shucheng Haase, Robert Pinetz, Thomas Radbruch, Alexander Krause, Inga Kobler, Erich He, Jian Tang, Yucheng Yang, Haichun Huo, Yuankai Luo, Gongning Kushibar, Kaisar Amankulov, Jandos Toleshbayev, Dias Mukhamejan, Amangeldi Egger, Jan Pepe, Antonio Gsaxner, Christina Luijten, Gijs Fujita, Shohei Kikuchi, Tomohiro Wiestler, Benedikt Kirschke, Jan S. de la Rosa, Ezequiel Bolelli, Federico Lumetti, Luca Grana, Costantino Xie, Kunpeng Wu, Guomin Puladi, Behrus Martín-Isla, Carlos Lekadir, Karim Campello, Victor M. Shao, Wei Brisbane, Wayne Jiang, Hongxu Wei, Hao Yuan, Wu Li, Shuangle Zhou, Yuyin Wang, Bo AI Collaborative Centre University Health Network Department of Laboratory Medicine and Pathobiology University of Toronto Vector Institute Toronto Canada Peter Munk Cardiac Centre University Health Network Toronto Canada Toronto General Hospital Research Institute University Health Network Department of Computer Science University of Toronto University Health Network Vector Institute Toronto Canada University of Science Vietnam National University Ho Chi Minh City Viet Nam Institute of Computer Science University of Freiburg Freiburg Germany School of Medicine and Health Harbin Institute of Technology Harbin China Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Department of System and Control Engineering School of Engineering Institute of Science Tokyo Formerly Tokyo Institute of Technology Tokyo Japan Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical Engineering and Computer Science University of Queensland Brisbane Australia School of Cyberspace Hangzhou Dianzi University Hangzhou China Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Division for Computational Radiology and Clinical AI Department of Neuroradiology University Hospital Bonn Germany School of Biomedical Engineering Shenzhen University Shenzhen China School of Biological Science and Medical Engineering Southeast University Nanjing China Department of Urology Cleveland Clinic Cleveland United States Department of Computer Science University of Minnesota Minneapolis United St

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications. © 2024, CC BY-NC-SA.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Robustness Metrics for Defense of Machine Learning Systems

Evaluation of Robustness Metrics for Defense of Machine Lear...

引用

International Conference on Military Communications and information Systems (ICMCIS)

作者： J. DeMarchi R. Rijken J. Melrose B. Madahar G. Fumera F. Roli E. Ledda M. Aktaş F. Kurth P. Baggenstoss B. Pelzer L. Kanestad Collaborative Engineering Systems & Aerospace Systems Information Supremacy Royal Netherlands Aerospace Centre NLR Amsterdam NLD Cyber & Information Systems Division Defence Science and Technology Laboratory Portondown GBR Department of Electrical and Electronic Engineering University of Cagliari Cagliari ITA Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa ITA Department of Computer Control and Management Engineering Sapienza University of Rome Rome ITA Defence Systems Technologies Division ASELSAN Ankara TUR Fraunhofer Institute for Communication Information Processing and Ergonomics Bonn DEU Swedish Defence Research Agency Cyber Defence and C2 Technology Division Stockholm SWE

In this paper we explore some of the potential applications of robustness criteria for machine learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator, ML robustness metrics are applied to real-world scenarios with military relevance, indicating how they might be used to help detect and handle possible adversarial attacks on ML systems. We conclude by sketching promising future avenues of research in order to: (1) help establish useful verification methodologies to facilitate ML robustness compliance assessment; (2) support development of ML accountability mechanisms; and (3) reliably detect, repel, and mitigate adversarial attack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Energy Optimization for Mobile Networks Using Potential Games

Distributed Energy Optimization for Mobile Networks Using Po...

引用

IEEE Internatonal Conference on Mobile Adhoc and Sensor Systems (MASS)

作者： Zhizongkai Wang Hanfei Wang Zhongji Wang Yilin Xiao Yunzhi Zhao Xiaowen Li Xufeng Chen Lin Gao Fen Hou Jianwei Huang School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology Shenzhen Guangdong P.R. China School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network and CSIJRI Joint Research Centre on Smart Energy Storage The Chinese University of Hong Kong Shenzhen Guangdong P.R. China Department of Electrical and Computer Engineering State Key Laboratory of IoT for Smart City University of Macau Macau SAR P.R. China Huawei Technologies P.R. China

ISBN: (数字)9798350363999

ISBN: (纸本)9798350364002

The rapid advancement of information and communication technology (ICT) has made the industry a significant contributor to global carbon emissions. As the foundation of ICT, next-generation mobile communication networks aim to be more powerful and energy-efficient. However, optimizing energy efficiency in real networks is challenging due to large-scale, multi-layer control variables and the dynamic environment. This paper addresses the energy efficiency optimization problem from a network perspective by controlling cross-layer variables including both cell activation status and cell priority, to minimize overall network energy consumption while ensuring user quality-of-experience, which poses an NP-hard mixed-integer nonlinear programming problem. To tackle this, we propose a non-cooperative game where each cell acts as a player, optimizing its activation status and reference signal transmission power (determining its priority). We show that the game is a potential game, guaranteeing the existence of Nash equilibrium and the convergence of simple distributed algorithms towards Nash equilibrium. We further show that the Nash equilibrium points of the game can (but not always) reach the global optimal energy efficiency. Simulation results show that our proposed method can reduce the total system cost (including both energy consumption cost and user experience loss) by up to 28% compared to existing methods in the literature. Moreover, the performance loss of our proposed method, compared to the global optimal solution, is less than 13.7%. In summary, this work offers a realistic network model, introduces a novel game-based method, and provides extensive performance evaluation, making a significant contribution to both industry and academia.

关键词： Industries Energy consumption Costs Simulation Games Nash equilibrium Energy efficiency information and communication technology Distributed algorithms Optimization

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：