检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yang, Fengxiang Zhong, Zhun Luo, Zhiming Cai, Yuanzheng Lin, Yaojin Li, Shaozi Sebe, Nicu Artificial Intelligence Department Xiamen University China Department of Information Engineering and Computer Science University of Trento Italy Postdoc Center of Information and Communication Engineering Xiamen University China Minjiang University China Minnan Normal University China

This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data. One popular method is to obtain pseudo-label by clustering and use them to optimize the model. Although this kind of approach has shown promising accuracy, it is hampered by 1) noisy labels produced by clustering and 2) feature variations caused by camera shift. The former will lead to incorrect optimization and thus hinders the model accuracy. The latter will result in assigning the intra-class samples of different cameras to different pseudo-label, making the model sensitive to camera variations. In this paper, we propose a unified framework to solve both problems. Concretely, we propose a Dynamic and Symmetric Cross-Entropy loss (DSCE) to deal with noisy samples and a camera-aware meta-learning algorithm (MetaCam) to adapt camera shift. DSCE can alleviate the negative effects of noisy samples and accommodate to the change of clusters after each clustering step. MetaCam simulates cross-camera constraint by splitting the training data into meta-train and meta-test based on camera IDs. With the interacted gradient from meta-train and meta-test, the model is enforced to learn camera-invariant features. Extensive experiments on three re-ID benchmarks show the effectiveness and the complementary of the proposed DSCE and MetaCam. Our method outperforms the state-of-the-art methods on both fully unsupervised re-ID and unsupervised domain adaptive re-ID. Copyright © 2021, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

LocalViT: Analyzing Locality in Vision Transformers

LocalViT: Analyzing Locality in Vision Transformers

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Yawei Li Kai Zhang Jiezhang Cao Radu Timofte Michele Magno Luca Benini Luc Van Goo Computer Vision Lab D-ITET ETH Zurich Switzerland Center for Artificial Intelligence and Data Science (CAIDAS) University of Wurzburg Germany Center for Project-Based Learning D-ITET ETH Zurich Switzerland Integrated Systems Laboratory D-ITET ETH Zurich Switzerland Department of Electrical Electronic and Information Engineering University of Bologna Italy Processing Speech and Images (PSI) KU Leuven Belgium

The aim of this paper is to study the influence of locality mechanisms in vision transformers. Transformers originated from machine translation and are particularly good at modelling long-range dependencies within a long sequence. Although the global interaction between the token embeddings could be well modelled by the self-attention mechanism of transformers, what is lacking is a locality mechanism for infor-mation exchange within a local region. In this paper, locality mechanism is systematically investigated by carefully designed controlled experiments. We add locality to vision transformers into the feed-forward network. This seemingly simple solution is inspired by the comparison between feed-forward networks and inverted residual blocks. The importance of locality mechanisms is validated in two ways: 1) A wide range of design choices (activation function, layer placement, expansion ratio) are available for incorporating locality mechanisms and proper choices can lead to a performance gain over the baseline, and 2) The same locality mechanism is successfully applied to vision transformers with different architecture designs, which shows the generalization of the locality concept. For ImageNet2012 classification, the locality-enhanced transformers outperform the baselines Swin-T [1], DeiT-T [2] and PVT-T [3] by 1.0%, 2.6 % and 3.1 % with a negligible increase in the number of parameters and computational effort. Code is available at https://***/ofsoundof/LocalViT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

InSAR phase unwrapping with the constrained nonlinear least squares method 13th

InSAR phase unwrapping with the constrained nonlinear least ...

引用

13th International Conference on Genetic and Evolutionary Computing, ICGEC 2019

作者： Zhang, Xiaoqing Liu, Weike Zheng, Yongguo Wang, Zhiyong College of Computer Science and Engineering Shandong University of Science and Technology 579 Qianwangang Road Qingdao China Center of Information and Network Shandong University of Science and Technology 579 Qianwangang Road Qingdao China College of Geomatics Shandong University of Science and Technology 579 Qianwangang Road Qingdao China

ISBN: (纸本)9789811533075

Interferogram phase unwrapping is one of the important data processing step in InSAR applications, however, it is affected by the high slope of terrain factors. In this paper, an improved constrained nonlinear least squares InSAR phase unwrapping method is proposed. First, we estimate the phase instantaneous frequency of the interferogram by the least squares method. Then, through the transformation between the phase instantaneous frequency and the phase gradient, we pre-estimate a phase gradient model considering terrain factors. Finally, using phase instantaneous frequency estimation (PIFE) model as the constraints of the nonlinear least squares phase, we propose the improved constrained nonlinear least squares (CNLS) phase unwrapping method. When compares with the other algorithms in the interferometric phase unwrapping experiments, the improved method is shown to be the most robust to noise caused by the terrain factors and to be the most suitable for phase unwrapping of the InSAR data in rugged and varied terrain regions. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Landforms

来源：评论

学校读者我要写书评

暂无评论

Target Defense against Sequentially Arriving Intruders

Target Defense against Sequentially Arriving Intruders

引用

IEEE Conference on Decision and Control

作者： Arman Pourghorban Michael Dorothy Daigo Shishika Alexander Von Moll Dipankar Maity Department of Electrical and Computer Engineering The University of North Carolina at Charlotte NC USA Computational and Information Sciences Directorate Army Research Laboratory APG MD USA Mechanical Engineering Department George Mason University Fairfax VA USA Air Force Research Laboratory WPAFB Control Science Center OH USA

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

We consider a variant of the target defense problem where a single defender is tasked to capture a sequence of incoming intruders. The intruders’ objective is to breach the target boundary without being captured by the defender. As soon as the current intruder breaches the target or gets captured by the defender, the next intruder appears at a random location on a fixed circle surrounding the target. Therefore, the defender’s final location at the end of the current game becomes its initial location for the next game. Thus, the players pick strategies that are advantageous for the current as well as for the future games. Depending on the information available to the players, each game is divided into two phases: partial information and full information phase. Under some assumptions on the sensing and speed capabilities, we analyze the agents’ strategies in both phases. We derive equilibrium strategies for both the players to optimize the capture percentage using the notions of engagement surface and capture circle. We quantify the percentage of capture for both finite and infinite sequences of incoming intruders.

关键词： Level set Games Sensors Task analysis IEEE Regions

来源：评论

学校读者我要写书评

暂无评论

Efficient Channel Estimation for Millimeter Wave and Terahertz Systems Enabled by Integrated Super-resolution Sensing and Communication

arXiv

引用

arXiv 2024年

作者： Xu, Jingran Wang, Huizhi Zeng, Yong Xu, Xiaoli Wu, Qingqing Yang, Fei Chen, Yan Jamalipour, Abbas The National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China The Purple Mountain Laboratories Nanjing211111 China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China The Wireless Technology Lab. 2012 Lab Shanghai Huawei Technologies Co. Ltd. Shanghai201206 China The School of Electrical and Computer Engineering The University of Sydney CamperdownNSW2006 Australia

Integrated super-resolution sensing and communication (ISSAC) has emerged as a promising technology to achieve extremely high precision sensing for those key parameters, such as the angles of the sensing targets. In this paper, we propose an efficient channel estimation scheme enabled by ISSAC for millimeter wave (mmWave) and TeraHertz (THz) systems with a hybrid analog/digital beamforming architecture, where both the pilot overhead and the cost of radio frequency (RF) chains are significantly reduced. The key idea is to exploit the fact that subspace-based super-resolution algorithms such as multiple signal classification (MUSIC) can estimate channel parameters accurately without requiring dedicate a priori known pilots. In particular, the proposed method consists of two stages. First, the angles of the multi-path channel components are estimated in a pilot-free manner during the transmission of data symbols. Second, the multi-path channel coefficients are estimated with very few pilots. Compared to conventional channel estimation schemes that rely solely on channel training, our approach requires the estimation of much fewer parameters in the second stage. Furthermore, with channel multi-path angles obtained, the beamforming gain can be achieved when pilots are sent to estimate the channel path gains. To comprehensively investigate the performance of the proposed scheme, we consider both the basic line-of-sight (LoS) channels and more general multipath channels. We compare the performance of the minimum mean square error (MMSE) of channel estimation and the resulting beamforming gains of our proposed scheme with the traditional scheme that rely exclusively on channel training. It is demonstrated that our proposed method significantly outperforms the benchmarking scheme. Simulation results are presented to validate our theoretical findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Cache Compression with Golomb-Rice Code and Quantization for Convolutional Neural networks

Cache Compression with Golomb-Rice Code and Quantization for...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Seung-Hwan Bae Hyuk-Jae Lee Hyun Kim Department of Electrical and Computer Engineering Inter-University Semiconductor Research Center Seoul National University Seoul Korea Department of Electrical and Information Engineering Seoul National University of Science and Technology Seoul Korea

Cache compression schemes reduce the cache miss rate by increasing the effective cache capacity and consequently, reduce memory access and power consumption. Therefore, cache compression is beneficial for applications with heavy memory traffic, including convolutional neural network (CNN). In this paper, a new cache compression of a floatingpoint number is proposed for CNNs. The exponent is compressed using the Golomb-Rice code, instead of the Huffman code, for an efficient hardware implementation. The compression syntax is carefully designed so that the size of compressed data is not very far from the entropy, which is the theoretical limit, by distinguishing two different types of data used in CNNs. On the other hand, since the mantissa of CNNs data can be hardly compressed by entropy coding, it is simply quantized for data reduction that may not degrade the CNN performance significantly thanks to the error robustness of CNNs. The quantization reduces 23 bits of a mantissa to 4 bits. The experimental results show that the miss rate of a 1 MB compressed cache with the proposed compression method applied is almost similar to that of an uncompressed 2 MB cache without any decrease of the CNN accuracy.

关键词： Degradation Quantization (signal) Syntactics Robustness Hardware Entropy coding Entropy

来源：评论

学校读者我要写书评

暂无评论

Comparative study of quantum emitter fabrication in wide bandgap materials using localized electron irradiation

arXiv

引用

arXiv 2023年

作者： Kumar, Anand Cholsuk, Chanaprom Mishuk, Mohammad N. Hazra, Mouli Pillot, Clotilde Matthes, Tjorben Shaik, Tanveer A. Çakan, Aslı Deckert, Volker Suwanna, Sujin Vogl, Tobias Department of Computer Engineering School of Computation Information and Technology Technical University of Munich Munich80333 Germany Abbe Center of Photonics Institute of Applied Physics Friedrich Schiller University Jena Jena07745 Germany Abbe Center of Photonics Friedrich Schiller University Jena Jena07743 Germany Jena07745 Germany Optical and Quantum Physics Laboratory Department of Physics Faculty of Science Mahidol University Bangkok10400 Thailand

Quantum light sources are crucial foundational components for various quantum technology applications. With the rapid development of quantum technology, there has been a growing demand for materials with the capability of hosting quantum emitters. One such material platform uses fluorescent defects in hexagonal boron nitride (hBN) that can host deep sub-levels within the band gap. The localized electron irradiation has shown its effectiveness in generating deep sub-levels to induce single emitters in hBN. The question is whether localized (electron beam) irradiation is a reliable tool for creating emitters in other wide bandgap materials and its uniqueness to hBN. Here, we investigate and compare the fabrication of quantum emitters in hBN and exfoliated muscovite mica flakes along with other 3D crystals, such as silicon carbide and gallium nitride, which are known to host quantum emitters. We use our primary fabrication technique of localized electron irradiation using a standard scanning electron microscope. To complement our experimental work, we employ density functional theory simulations to study the atomic structures of defects in mica. While our fabrication technique allows to create hBN quantum emitters with a high yield and high single photon purity, it is unable to fabricate single emitters in the other solid-state crystals under investigation. This allows us to draw conclusions on the emitter fabrication mechanism in hBN, which could rely on activating pre-existing defects by charge state manipulation. Therefore, we provide an essential step towards the identification of hBN emitters and their formation process. © 2023, CC BY.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

arXiv

引用

arXiv 2023年

作者： Chiu, Ching-Yu Müller, Meinard Davies, Matthew E.P. Su, Alvin Wen-Yu Yang, Yi-Hsuan The Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Academia Sinica Taiwan The International Audio Laboratories Erlangen Germany The Department of Informatics Engineering Centre for Informatics and Systems of the University of Coimbra University of Coimbra Portugal The Department of Computer Science and Information Engineering National Cheng Kung University Taiwan Yating Music Team Taiwan AI Labs Taiwan Research Center for IT Innovation Academia Sinica Taiwan

To model the periodicity of beats, state-of-the-art beat tracking systems use "post-processing trackers" (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called "predominant local pulses" (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). © 2023, CC BY.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Smart Fall Detection System: Kinect Depth and CNN Integrated Approach

SSRN

引用

SSRN 2022年

作者： Su, Mu-Chun Chen, Jieh-Haur Liao, Chia-Wei Hsu, Shu-Chien Hsieh, Yi-Zeng Department of Computer Science and Information Engineering National Central University Jhongli Taoyuan320317 Taiwan Department of Civil Engineering Research Center of Smart Construction National Central University Jhongli Taoyuan320317 Taiwan Safety and Health Association of Taiwan Jhongli Taoyuan320317 Taiwan Department of Civil Engineering Hong Kong Polytechnic University Hong Kong Department of Electrical Engineering National Taiwan University of Science and Technology Taipei106335 Taiwan

This study proposes a smart fall detection system integrating Kinect depth and convolutional neural network (CNN) approaches. The system uses raw data from Kinect depth images to locate the ground, identifies the foreground pixels with a background subtraction algorithm, and tracks the foreground for analysis. This paper compares the proposed system with four neural network types for evaluation and implementation including the support vector machine (SVM), backpropagation neural network (MLP), radial basal function neural network (RBF) and deep learning neural network (DNN). The findings demonstrate an efficient and reliable system with accuracy rate approximately at 95% with KAPPA at 0.96. © 2022, The Authors. All rights reserved.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Font Generation and Keypoint Ranking for Stroke Order of Chinese Characters by Deep Neural networks

引用

SN computer science 2021年第4期2卷 1-9页

作者： Li, Hao-Ting Jiang, Ming-Xiu Huang, Tzu-Ting Chiang, Chen-Kuo Department of Computer Science and Information Engineering Advanced Institute of Manufacturing with High-Tech Innovations and Center for Innovative Research on Aging Society (CIRAS) National Chung Cheng University Chiayi Taiwan (R.O.C.)

Determining the stroke order of a Chinese character image is challenging, because there is no explicit representation for image to sequence learning. This paper investigates the approach in Chinese character generation given just a few image samples of a specific font. Then, keypoint extraction for stroke decomposition and learning to rank method are proposed for obtaining stroke order. Since the same character can appear in multiple fonts, different font of Chinese character has distinct keypoints. Thus, it brings difficulties in acquiring stroke order. Generative Adversarial networks (GANs) is introduced to generate lots of Chinese character images with different fonts for training and testing the proposed method. The keypoint ranking model based on stroke extraction combining font transfer based on GANs is proposed to complete this task. Compared to other methods, our method can be accomplished without human annotation as initial hints in prediction stage. The experimental results demonstrate the effectiveness of our method that achieved 0.9667 NDCG in average and up to 29.53% samples are higher than 0.98 NDCG.

关键词：

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：