检索结果-内蒙古大学图书馆

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wang, Yingqian Wang, Longguang Liang, Zhengyu Yang, Jungang Timofte, Radu Guo, Yulan Jin, Kai Wei, Zeqiang Yang, Angulia Guo, Sha Gao, Mingzhi Zhou, Xiuzhuang Van Duong, Vinh Huu, Thuc Nguyen Yim, Jonghoon Jeon, Byeungwoo Liu, Yutong Cheng, Zhen Xiao, Zeyu Xu, Ruikang Xiong, Zhiwei Liu, Gaosheng Jin, Manchang Yue, Huanjing Yang, Jingyu Gao, Chen Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Xia, Wang Wang, Yan Xia, Peiqi Wang, Shunzhou Lu, Yao Cong, Ruixuan Sheng, Hao Yang, Da Chen, Rongshan Wang, Sizhe Cui, Zhenglong Chen, Yilei Lu, Yongjie Cai, Dongjun An, Ping Salem, Ahmed Ibrahem, Hatem Yagoub, Bilel Kang, Hyun-Soo Zeng, Zekai Wu, Heng National University of Defense Technology China Aviation University of Air Force China University of Würzburg Germany Eth Zürich Switzerland Sun Yat-sen University The Shenzhen Campus of Sun Yat-sen University China Bigo Technology Pte. Ltd. Singapore Smart Medical Innovation Lab Beijing University of Posts and Telecommunications China Global Explorer Ltd. Suzhou China National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of University of Science and Technology of China China School of Electrical and Information Engineering Tianjin University China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada Beijing Institute of Technology China Shenzhen MSU-BIT University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China School of Communication and Information Engineering Shanghai University China School of Information and Communication Engineering Chungbuk National University Korea Republic of Guangdong University of Technology China

ISBN: (纸本)9798350302493

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet [1]. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR [2]. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Unified Automatic Control of Vehicular systems with Reinforcement Learning

arXiv

引用

arXiv 2022年

作者： Yan, Zhongxia Kreidieh, Abdul Rahman Vinitsky, Eugene Bayen, Alexandre M. Wu, Cathy The Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Civil and Environmental Engineering University of California Berkeley BerkeleyCA94720 United States The Department of Mechanical Engineering University of California Berkeley BerkeleyCA94720 United States The Department of Electrical Engineering and Computer Science University of California Berkeley BerkeleyCA94720 United States The Laboratory for Information and Decision Systems The Department of Civil and Environmental Engineering The Institute for Data Systems and Society Massachusetts Institute of Technology CambridgeMA02139 United States

Emerging vehicular systems with increasing proportions of automated components present opportunities for optimal control to mitigate congestion and increase efficiency. There has been a recent interest in applying deep reinforcement learning (DRL) to these nonlinear dynamical systems for the automatic design of effective control strategies. Despite conceptual advantages of DRL being model-free, studies typically nonetheless rely on training setups that are painstakingly specialized to specific vehicular systems. This is a key challenge to efficient analysis of diverse vehicular and mobility systems. To this end, this article contributes a streamlined methodology for vehicular microsimulation and discovers high performance control strategies with minimal manual design. A variable-agent, multi-task approach is presented for optimization of vehicular Partially Observed Markov Decision Processes. The methodology is experimentally validated on mixed autonomy traffic systems, where fractions of vehicles are automated;empirical improvement, typically 15-60% over a human driving baseline, is observed in all configurations of six diverse open or closed traffic systems. The study reveals numerous emergent behaviors resembling wave mitigation, traffic signaling, and ramp metering. Finally, the emergent behaviors are analyzed to produce interpretable control strategies, which are validated against the learned control strategies. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Block-Structured Optimization for Subgraph Detection in Interdependent Networks

arXiv

引用

arXiv 2022年

作者： Jie, Fei Wang, Chunpai Chen, Feng Li, Lei Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Computer Science University at Albany – SUNY AlbanyNY United States Erik Jonsson School of Engineering & Computer Science The University of Texas at Dallas DallasTX United States Mininglamp Academy of Sciences Mininglamp Technologies Beijing China Institute of Big Knowledge Science Hefei University of Technology Hefei China

We propose a generalized framework for block-structured nonconvex optimization, which can be applied to structured subgraph detection in interdependent networks, such as multi-layer networks, temporal networks, networks of networks, and many others. Specifically, we design an effective, efficient, and parallelizable projection algorithm, namely Graph Block-structured Gradient Projection (GBGP), to optimize a general non-linear function subject to graph-structured constraints. We prove that our algorithm: 1) runs in nearly-linear time on the network size;2) enjoys a theoretical approximation guarantee. Moreover, we demonstrate how our framework can be applied to two very practical applications and conduct comprehensive experiments to show the effectiveness and efficiency of our proposed algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： Functions

来源：评论

学校读者我要写书评

暂无评论

Group-structured adversarial training

arXiv

引用

arXiv 2021年

作者： Farnia, Farzan Aghazadeh, Amirali Zou, James Tse, David Laboratory for Information & Decision Systems Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science University of California Berkeley United States Department of Biomedical Data Science Stanford University Department of Electrical Engineering Stanford University

Robust training methods against perturbations to the input data have received great attention in the machine learning literature. A standard approach in this direction is adversarial training which learns a model using adversarially-perturbed training samples. However, adversarial training performs suboptimally against perturbations structured across samples such as universal and group-sparse shifts that are commonly present in biological data such as gene expression levels of different tissues. In this work, we seek to close this optimality gap and introduce Group-Structured Adversarial Training (GSAT) which learns a model robust to perturbations structured across samples. We formulate GSAT as a non-convex concave minimax optimization problem which minimizes a group-structured optimal transport cost. Specifically, we focus on the applications of GSAT for group-sparse and rank-constrained perturbations modeled using group and nuclear norm penalties. In order to solve GSAT's non-smooth optimization problem in those cases, we propose a new minimax optimization algorithm called GDADMM by combining Gradient Descent Ascent (GDA) and Alternating Direction Method of Multipliers (ADMM). We present several applications of the GSAT framework to gain robustness against structured perturbations for image recognition and computational biology datasets. © 2021, CC BY.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Model for Misbehavior Detection in IoV

A Multi-objective Model for Misbehavior Detection in IoV

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Jiaqi Huang Jiahuan Lv Zhiguo Zhou Sohan Gyawali Yi Qian School of Computer Science and Mathematics University of Central Missouri MO USA School of Information and Communication Engineering Xi'an Jiaotong University Xi'an China Department of Biostatistics and Data Science University of Kansas Medical Center KS USA Department of Technology Systems East Carolina University NC USA Department of Electrical and Computer Engineering University of Nebraska-Lincoln NE USA

ISBN: (纸本)9781665435413

As the key element of the Intelligent Transportation System, Internet of Vehicles (IoV) is expected to reduce the traffic congestion and improve the road safety. For road safety, connected vehicles need to broadcast basic safety messages frequently, which contain location, speed, acceleration, steering information, etc. Due to the wireless environment and ad-hoc nature, the vehicular communications are vulnerable to various attacks. It is vital to protect the correctness of the exchanged messages, in which the misbehavior detection mechanisms play an important role. In this paper, we propose a data-centric misbehavior detection method based on a multi-objective learning model. Different from current machine learning based misbehavior detection system, our work exploits a new direction to improve the detection performance by maximizing the recall and specificity. To show the effectiveness of the proposed model, we conduct experiments on the VeReMi dataset and compare the detection results with existing approaches.

关键词： Wireless communication Machine learning Road safety Ad hoc networks Safety Internet Global communication

来源：评论

学校读者我要写书评

暂无评论

Robust Low-rank Deep Feature Recovery in CNNs: Toward Low information Loss and Fast Convergence

Robust Low-rank Deep Feature Recovery in CNNs: Toward Low In...

引用

IEEE International Conference on data Mining (ICDM)

作者： Jiahuan Ren Zhao Zhang Jicong Fan Haijun Zhang Mingliang Xu Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China School of Data Science The Chinese University of Hong Kong (Shenzhen) & Shenzhen Research Institute of Big Data Shenzhen China Harbin Institute of Technology (Shenzhen) Shenzhen China School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665423991

Convolutional Neural Networks (CNNs)-guided deep models have obtained impressive performance for image representation, however the representation ability may still be restricted and usually needs more epochs to make the model converge in training, due to the useful information loss during the convolution and pooling operations. We therefore propose a general feature recovery layer, termed Low-rank Deep Feature Recovery (LDFR), to enhance the representation ability of the convolutional features by seamlessly integrating low-rank recovery into CNNs, which can be easily extended to all existing CNNs-based models. To be specific, to recover the lost information during the convolution operation, LDFR aims at learning the low-rank projections to embed the feature maps onto a low-rank subspace based on some selected informative convolutional feature maps. Such low-rank recovery operation can ensure all convolutional feature maps to be reconstructed easily to recover the underlying subspace with more useful and detailed information discovered, e.g., the strokes of characters or the texture information of clothes can be enhanced after LDFR. In addition, to make the learnt low-rank subspaces more powerful for feature recovery, we design a fusion strategy to obtain a generalized subspace, which averages over all learnt sub-spaces in each LDFR layer, so that the convolutional feature maps in test phase can be recovered effectively via low-rank embedding. Extensive results on several image datasets show that existing CNNs-based models equipped with our LDFR layer can obtain better performance.

关键词： Training Image recognition Convolution Conferences Image representation data mining Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Neural multi-objective combinatorial optimization with diversity enhancement 23

Neural multi-objective combinatorial optimization with diver...

引用

Proceedings of the 37th International Conference on Neural information Processing systems

作者： Jinbiao Chen Zizhen Zhang Zhiguang Cao Yaoxin Wu Yining Ma Te Ye Jiahai Wang School of Computer Science and Engineering Sun Yat-sen University P.R. China School of Computing and Information Systems Singapore Management University Singapore Department of Industrial Engineering & Innovation Sciences Eindhoven University of Technology Netherlands Department of Industrial Systems Engineering & Management National University of Singapore Singapore School of Computer Science and Engineering Sun Yat-sen University P.R. China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University P.R. China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R. China

Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respective subproblems, thus a limited Pareto set. Beyond decomposition, we propose a novel neural heuristic with diversity enhancement (NHDE) to produce more Pareto solutions from two perspectives. On the one hand, to hinder duplicated solutions for different subproblems, we propose an indicator-enhanced deep reinforcement learning method to guide the model, and design a heterogeneous graph attention mechanism to capture the relations between the instance graph and the Pareto front graph. On the other hand, to excavate more solutions in the neighborhood of each subproblem, we present a multiple Pareto optima strategy to sample and preserve desirable solutions. Experimental results on classic MOCO problems show that our NHDE is able to generate a Pareto front with higher diversity, thereby achieving superior overall performance. Moreover, our NHDE is generic and can be applied to different neural methods for MOCO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Television White Space as an Alternative for Wireless Broadband Connectivity

Exploring Television White Space as an Alternative for Wirel...

引用

Multidisciplinary engineering and Applied Science (ICMEAS), International Conference on

作者： Ayodele H. Ifijeh Emmanuel Adetiba Adeyinka Adewale Surrendra Thakur Sibusiso Moyo Dare O. Emmanuel Udeme C. Ukpong Dept. of Electrical & Information Engineering Covenant Applied Informatics & Communication African Centre of Excellence (CApIC-ACE) Covenant University Nigeria HRA Institute for Systems Science Durban University of Technology Durban South Africa Dept. of Electrical & Information Engineering Covenant University Canaanland Ota Nigeria KZN e-skills CoLab Durban University of Technology Durban South Africa Department of Mathematical Sciences School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa

ISBN: (数字)9798350358834

ISBN: (纸本)9798350358841

Advancement in wireless transmission has enabled the communication among multiple devices all over the world, as well as expanding the frontiers of wireless Internet access. As a result of these advancement, numerous devices are questing for wireless connectivity thereby congesting the existing spectrum. If new measures are not taken to reduce depletion of the reserved radio resource, new allocations of wireless Internet access will be impossible, thereby risking the development of the entire wireless ecosystem. The demands for resourceful spectrum consumption have continually driven researchers and stakeholders in the wireless industry to search for spare radio spectrum to offer affordable and reliable wireless connectivity. The TV broadcasting is not fully utilizing the spectrum in some geographical zone. These TV unused spaces called TV White Spaces (TVWS), are well-thought-out to be the probable future resolutions for unavailability of spectrum. The low frequency band (470 to 694 MHz) of the unutilized TV channel has exceptional broadcast features over extensive distances and enables transmissions through high-rise buildings, trees, and mountains. These features allow the applications of TVWS in Internet of Things (IoT), wireless sensor network, wireless connectivity, wireless switching, smart grid and cities, automated transportation, and logistics as well as connectivity in cloud infrastructure. This paper presents a study on the advantages and benefits of television white space as an alternative to wireless broadband connectivity.

关键词： Wireless communication Wireless sensor networks TV Urban areas White spaces Broadband communication Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Proposal for a knowledge Map in Programming Education Curriculum for IT Talent Development in Japan

Proposal for a Knowledge Map in Programming Education Curric...

引用

IEEE International Conference on Teaching, Assessment and Learning for engineering (TALE)

作者： Hiroto Yamakawa Haruki Ueno Kana Ohashi Akihiro Matsuda Osamu Hasegawa Hiroshi Komatsugawa Department of Information Systems Engineering Chitose Institute of Science and Technology Chitose Hokkaido Japan Faculty of Science and Technology Chitose Institute of Science and Technology Chitose Hokkaido Japan Graduate School of Science and Technology Chitose Institute of Science and Technology Chitose Hokkaido Japan Chitose Hokuyou High School Chitose Hokkaido Japan Department of Data Science Musashino University Ariake Koto-Ku Tokyo

This study proposes a knowledge map for standardizing programming education across Japan and focuses on bridging the curriculum gaps between elementary, middle, and higher education. Utilizing a computer adaptive testing system for empirical validation, a pilot implementation in a high school class revealed knowledge gaps in advancing levels of comprehension and application, especially when transitioning to complex elements such as a pseudocode.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Smart Detection for Small Lung Tumor with Tumor Pattern Recognition Algorithm

An Investigation of Smart Detection for Small Lung Tumor wit...

引用

Artificial Intelligence and knowledge Discovery in Concurrent engineering (ICECONF), International Conference on

作者： G. Hariharan P. Prasanth P. Arthi Devarani T. Sajana Indhumathi C Ashok Kumar Deportment of Artificial Intelligence and Machine Learning Malla Reddy University Hyderabad Telangana India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr.Sakunthala Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering R. M K College of Engineering and Technology Thiruvallur Tamil Nadu India Department of Artificial Intelligence and Data Science KoneruLakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Computer Science and Business Systems R.M. K. Engineering College Kavaraipettai Tamil Nadu Department of Computer Science BanasthaliVidyapith Rajasthan India

The Small-cell lung tumor is the prime public concern, resulting in increased mortality. Various therapeutic approaches have made progress in the handling of small-cell lung tumor. It's considered the backbone of cytotoxic chemotherapy treatment. However, clinical research shows that because small-cell lung tumor is chemically approachable, high response rates among small-cell lung tumorinfecters are generally not translated into cure. Therefore, it is high time to make progress in small-cell lung tumor research because every success in clinical trials is fought, and every failure is a lesson. A recent study of small-cell lung tumor has improved the prognosis of patients. Some notable research areas have provided new options for patients by conducting multiple clinical trials. In this paper smart edge detection based small lung tumor identification method was proposed. This model operates with the pattern recognition algorithm model. This algorithm smartly finds the edges of the tumor cells and provides the edge results. This will helpful for the doctors to identify the tumor part exactly.

关键词： Chemotherapy Image edge detection Lung cancer Medical services Clinical trials knowledge discovery Concurrent engineering

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：