检索结果-内蒙古大学图书馆

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Thumt: An open source toolkit for neural machine translation

arXiv

引用

arXiv 2017年

作者： Zhang, Jiacheng Ding, Yanzhuo Shen, Shiqi Cheng, Yong Sun, Maosong Luan, Huanbo Liu, Yang State Key Lab. of Intelligent Technol. and Syst. Tsinghua Natl. Lab. for Info. Sci. and Technology Department of Computer Science and Technology Tsinghua University Beijing China Jiangsu Collaborative Innovation Center for Language Competence Jiangsu China Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China

This paper introduces THUMT, an opensource toolkit for neural machine translation (NMT) developed by the Natural Language processing Group at Tsinghua University. THUMT implements the standard attention-based encoder-decoder framework on top of Theano and supports three training criteria: Maximum likelihood estimation, minimum risk training, and semi-supervised training. It features a visualization tool for displaying the relevance between hidden states in neural networks and contextual words, which helps to analyze the internal workings of NMT. Experiments on Chinese-English datasets show that THUMT using minimum risk training significantly outperforms GroundHog, a state-of-the-art toolkit for NMT. Copyright © 2017, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

A Novel Economical Design of Multistage Decimators for Low Latency Audio Applications

A Novel Economical Design of Multistage Decimators for Low L...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Wei Hu Chongwei Zheng Yonghao Wang Jing Liu Cen Chen Zeng Zeng College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Digital Media Technology lab Birmingham City University Birmingham UK Institute for Infocomm Research Singapore

ISBN: (纸本)9781728176499;9781728176505

The oversampling sigma-delta analog-to-digital converter (ADC) is widely used in digital audio systems for its low hardware cost and high precision. The digital filter part of the ADC is the primary source of the silicon and power cost. In this work, we proposed an economical multistage decimation filter architecture to meet the requirements of commercial ADC specifications with a further novel multi-objective optimization strategy. We took group delay and computational cost as objective functions and used annealing algorithm to readjust the stopband attenuation, stopband edge and passband ripple of each filter. Our multistage architecture combines cascaded integrator-comb (CIC) filters, compensating filters and equiripple finite impulse response (FIR) filters at the different stages to balance the overall performance. The experimental results showed that our design approach worked with multi-objective optimization strategy could achieve low group delay with lower cost compared to traditional designs.

关键词： Sigma-delta modulation Finite impulse response filters computer architecture Filtering algorithms Attenuation Linear programming Silicon

来源：评论

学校读者我要写书评

暂无评论

Efficient Design of Hybrid Half-band Multi-stage Filter Based on Simulated Annealing Algorithm

Efficient Design of Hybrid Half-band Multi-stage Filter Base...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Wei Hu Chongwei Zheng Yonghao Wang Jin Zhang Cen Chen Zeng Zeng College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Digital Media Technology lab Birmingham City University Birmingham UK Institute for Infocomm Research Singapore

ISBN: (纸本)9781728176499;9781728176505

The oversampling sigma-delta based analog-to-digital converter and digital-to-analog converter (ADC/DAC) architecture can achieve high resolution with effective low hardware cost. It normally introduces latency due to the internal high-performance finite impulse response (FIR) digital filters. In this work, we proposed a novel approach to reduce latency and accurately predict latency caused by the group delay. We propose a filter structure applied to ADC, using the infinite impulse response (IIR) filter and half-band filter (HBF) to construct a hybrid half-band filter (HHBF). A novel modified Simulated Annealing (SA) algorithm is proposed to optimize the best distribution of passband ripple and transition bandwidth that is suitable for audio processing with low latency and computation cost. The experiments show that hybrid HBF proposed in this paper improves the efficiency of the filter in terms of filter cost and group delay comparing to traditional design.

关键词： Sigma-delta modulation Finite impulse response filters IIR filters Simulated annealing Bandwidth Filtering algorithms Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Coarse to Fine: Multi-lab.l Image Classification with Global/Local Attention

Coarse to Fine: Multi-label Image Classification with Global...

引用

IEEE International Smart Cities Conference (ISC2)

作者： Fan Lyu Fuyuan Hu Victor S. Sheng Zhengtian Wu Qiming Fu Baochuan Fu School of Electronic & Information Engineering Suzhou University of Science and Technology Suzhou China Computer Science Department University of Central Arkansas Arkansas USA Jiangsu Province Key Lab Intelligent Building Energy Efficiency Suzhou China

ISBN: (纸本)9781538659601;9781538659595

In our daily life, the scenes around us are always with multiple lab.ls especially in a smart city, i.e., recognizing the information of city operation to response and control. Great efforts have been made by using Deep Neural Networks to recognize multi-lab.l images. Since multi-lab.l image classification is very complicated, people seek to use the attention mechanism to guide the classification process. However, conventional attention-based methods always analyzed images directly and aggressively. It is difficult for them to well understand complicated scenes. In this paper, we propose a global/local attention method that can recognize an image from coarse to fine by mimicking how human-beings observe images. Specifically, our global/local attention method first concentrates on the whole image, and then focuses on local specific objects in the image. We also propose a joint max-margin objective function, which enforces that the minimum score of positive lab.ls should be larger than the maximum score of negative lab.ls horizontally and vertically. This function can further improve our multi-lab.l image classification method. We evaluate the effectiveness of our method on two popular multilab.l image datasets (i.e., Pascal VOC and MS-COCO). Our experimental results show that our method outperforms state-of-the-art methods.

关键词： Feature extraction Computational modeling Data models Smart cities Image recognition Visualization Logic gates

来源：评论

学校读者我要写书评

暂无评论

Cluster-based superseding nearest neighbor queries on uncertain data

引用

Journal of Convergence information technology 2012年第17期7卷 392-401页

作者： Liu, Wenyuan Li, Wei Du, Ying Chen, Zijun He, Yourui College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China College of Economics and Management Yanshan University Qinhuangdao Hebei 066004 China The Key Lab. for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao Hebei 066004 China

Recently, query processing based on uncertain data is becoming research focuses. Cluster-based superseding nearest neighbor (CSNN) query algorithm on uncertain data is proposed in this paper. We divide the instances of each object into k clusters by applying the clustering algorithm k-means, and then store these clustered objects in R-tree like index structures. Ranked list will be retrieved through traversing R-tree, which could include instances, clusters, or objects. While unfolding the ranked list, the superseding graph G will be constructed gradually based on the superseding relationship. The final result sets will be found through pruning and validating the superseding graph G. Finally, the experimental results show that the algorithm is efficient and effective.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Dynamic layered-graph model for routing in cognitive radio network

Jiefangjun Ligong Daxue Xuebao/Journal of PLA University of ...

引用

Jiefangjun Ligong Daxue Xuebao/Journal of PLA University of Science and technology (Natural Science Edition) 2008年第6期9卷 586-590页

作者： Li, Yang Dong, Yu-Ning Zhao, Hai-Tao College of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing 210003 China Jiangsu Provincial Key Lab. of Computer Information Processing Technology Soochow University Suzhou 215006 China

To analyze routing protocol in cognitive radio(CR) networks effectively, a dynamic routing model is necessary. Dynamic layered graphic(DG) was proposed aiming at the characteristic of dynamic spectrum access in CR networks. In DG model, nodes were split into many sub-nodes, and each sub-node state could denote whether the related channel was availab.e or *** DG model, sub-node state was taken as a stochastic process and the model of cognitive radio network's dynamic topology was set up by analyzing the dynamic characteristic of sub-node state. Simulation results show that in the aspect of the adaptability to CR network's variable SOP and depiction of the topology, the DG model outperforms the layered graph(LG) model, and can adapt well to CR networks environment.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Resource allocation for chunk-based multi-carrier cognitive radio networks

Resource allocation for chunk-based multi-carrier cognitive ...

引用

International Symposium on Wireless Personal Multimedia Communications (WPMC)

作者： Ding Xu Qun Li Xiao-chuan Sun Wireless Communication Key Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science & Technology Nanjing University of Posts and Telecommunications Nanjing China College of Information Engineering Hebei United University Tangshan China

ISBN: (纸本)9781479964123

In this paper, a downlink multi-carrier cognitive radio (CR) network is considered. The CR network consists of one cognitive base station (CBS) and a set of secondary users (SUs) sharing the same spectrum with the primary user (PU). Chunk-based resource allocation is adopted where subcarriers are grouped into chunks for allocation to the SUs. The problem of chunk-based resource allocation under the interference power constraint and the transmit power constraint is investigated. The objective is to maximize the sum rate of the SUs. For this, based on Lagrange dual method, a near-optimal joint chunk and power allocation scheme is proposed. The complexity of the optimal scheme is exponential in the number of chunks, while the complexity of the proposed scheme is reduced significantly to only linear in the number of chunks, and at the same time, it is shown that the proposed scheme achieves almost the same performance that can be achieved by the optimal scheme. The impacts of the interference power constraint, the transmit power constraint, number of subcarriers within the chunk and the channel coherence bandwidth on the performance of the proposed scheme are investigated. Particularly, it is shown that increasing the channel coherence bandwidth does not always lead to improvement of the SU performance.

关键词： Resource management Interference Complexity theory Wireless communication Bandwidth Multimedia communication Coherence

来源：评论

学校读者我要写书评

暂无评论

Cell-Free Massive MIMO with Normalized Conjugate Beamforming and Channel Non-Reciprocities 13

Cell-Free Massive MIMO with Normalized Conjugate Beamforming...

引用

13th International Conference on Wireless Communications and Signal processing, WCSP 2021

作者： Zhang, Yao Xia, Wenchao Zhu, Yongxu Zheng, Gan Gao, Feifei Zhejiang Normal University College of Physics and Electronic Information Engineering Jinhua321004 China Nanjing University of Posts and Telecommunications Department of Wireless Communication Key Lab of Jiangsu Province Nanjing210003 China London South Bank University Division of Computer Science and Informatics London United Kingdom Wolfson School of Mechanical Electrical and Manufacturing Engineering Loughborough University LeicestershireLE11 3TU United Kingdom Institute for Artificial Intelligence Tsinghua University State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology Department of Automation Tsinghua University Beijing100084 China

ISBN: (纸本)9781665407854

This paper focuses on a generalized downlink cell-free massive multiple-input multiple-output (CF-mMIMO) system with normalized conjugate beamforming (NCB) and channel non-reciprocities, assuming the access points (APs) are equipped with low-resolution digital-to-analog converters (DACs). Specifically, the channel non-reciprocities consist of the amplitude and phase non-reciprocities at the APs and user equipments. Closed-form expressions of the achievable sum-rates are derived for evaluating the impacts of channel non-reciprocities and DAC resolutions and comparing against the conjugate beamforming (CB) counterpart. Simulation results reveal that the downlink sum-rates are immune to the amplitude non-reciprocity of transceivers but strongly sensitive to the AP phase non-reciprocity. In particular, a small degree of AP phase non-reciprocity can result in substantial rate degradations. Besides, 5-bit DACs are enough in CF-mMIMO systems to approach the same sum-rates as CF-mMIMO systems with high-resolution DACs. Moreover, the NCB scheme outperforms the CB scheme in terms of the downlink sum-rates for both reciprocal and non-reciprocal channels. © 2021 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Online Attentive Kernel-Based Temporal Difference Learning

arXiv

引用

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

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：