检索结果-内蒙古大学图书馆

Four-dimensional direct detection receiver enabling Jones-space field recovery with phase and polarization diversity

引用

Photonics Research 2024年第3期12卷 399-410页

作者： QI WU YIXIAO ZHU XUEYANG LI HEXUN JIANG CHEN CHENG MENGFAN FU YIKUN ZHANG QUNBI ZHUGE ZHAOHUI LI WEISHENG HU Peng Cheng Laboratory Shenzhen 518055China State Key Laboratory of Advanced Communication Systems and Networks Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghai 200240China School of Electronics and Information Technology and Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Sun Yat-sen UniversityGuangzhou 510006China

Data centers,the engines of the global Internet,rely on powerful high-speed optical *** optical fiber communication,classic direct detection captures only the intensity of the optical field,while the coherent detection counterpart utilizes both phase and polarization diversities at the expense of requiring a narrow-linewidth and high-stability local oscillator(LO).Herein,we propose and demonstrate a four-dimensional Jones-space optical field recovery(4-D JSFR)scheme without an *** polarization-diverse full-field receiver structure captures information encoded in the intensity and phase of both polarizations,which can be subsequently extracted *** our knowledge,our proposed receiver achieves the highest electrical spectral efficiency among existing direct detection systems and potentially provides similar electrical spectral efficiency as standard intradyne coherent detection *** fully recovered optical field extends the transmission distance beyond the limitations imposed by fiber chromatic ***,the LO-free advantage makes 4-D JSFR suitable for photonic integration,offering a spectrally efficient and cost-effective solution for massively parallel data center *** results may contribute to the ongoing developments in the theory of optical field recovery and the potential design considerations for future high-speed optical transceivers.

关键词： polarization receiver phase

来源：评论

学校读者我要写书评

暂无评论

HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval

arXiv

引用

arXiv 2024年

作者： He, Chao Wei, Hongxi School of Computer Science Inner Mongolia University Provincial Key Laboratory of Mongolian Information Processing Technology National and Local Joint Engineering Research Center of Mongolian Information Processing Hohhot China

Deep image hashing aims to map input images into simple binary hash codes via deep neural networks and thus enable effective large-scale image retrieval. Recently, hybrid networks that combine convolution and Transformer have achieved superior performance on various computer tasks and have attracted extensive attention from researchers. Nevertheless, the potential benefits of such hybrid networks in image retrieval still need to be verified. To this end, we propose a hybrid convolutional and self-attention deep hashing method known as HybridHash. Specifically, we propose a backbone network with stage-wise architecture in which the block aggregation function is introduced to achieve the effect of local self-attention and reduce the computational complexity. The interaction module has been elaborately designed to promote the communication of information between image blocks and to enhance the visual representations. We have conducted comprehensive experiments on three widely used datasets: CIFAR-10, NUS-WIDE and IMAGENET. The experimental results demonstrate that the method proposed in this paper has superior performance with respect to state-of-the-art deep hashing methods. Source code is available https://***/shuaichaochao/HybridHash. Copyright © 2024, The Authors. All rights reserved.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Semantic Feature Interaction Network for Semantic Change Detection in Remote Sensing Images

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12090-12102页

作者： Zhang, Yuhang Zhang, Wuxia Ding, Songtao Wu, Siyuan Lu, Xiaoqiang Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing School of Computer Science and Technology Xi'an710121 China Xi'an University of Technology College of Computer Science and Engineering Shaanxi Xi'an710048 China Fuzhou University College of Physics and Information Engineering Fuzhou350002 China

Semantic Change Detection (SCD) in Remote Sensing Images (RSI) aims to identify changes in the type of Land Cover/Land Use (LCLU) corresponding to changed areas in RSI. The "from-to" information of the acquired image has more profound practical significance than Binary Change Detection (BCD). However, most deep learning-based SCD algorithms do not fully exploit the spatial-temporal information of multi-level features, leading to challenges in extracting LCLU features in complex changing scenes. To address these issues, we propose a Spatial-Temporal Semantic Feature Interaction Network (STS-FINet) to improve the performance of SCD in RSI. The proposed STS-FINet comprises a Multi-Scale Feature Extraction Encoder (MS-FEE), a Transformer-based Multi-Level Feature Interaction module (TML-FI), and a Multi-Level Feature Fusion Decoder (ML-FFD). The MS-FEE extracts deep semantic and differential information from the RSI. The TML-FI is designed to mine the spatial-temporal information by extracting long-range dependencies and spatial information from multi-level features to improve spatial perception. Moreover, Mixed Spatial Reasoning Convolution block (MixSrc) is presented to enrich the spatial information by extracting the multi-scale features, thus improving the model's capability to interpret complex changing scenes. Finally, ML-FFD integrates the multi-level features, resulting in the generation of the semantic change map. The effectiveness of the proposed STS-FINet is verified on two high-resolution RSI datasets. Experimental results show that the proposed STS-FINet achieves better change detection performance than SOTA methods. © 2008-2012 IEEE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Building Edge Detection technology from Remote Sensing Image Based on NSCT and Tensor Voting 8

Building Edge Detection Technology from Remote Sensing Image...

引用

2024 8th International Conference on Machine Vision and information technology, CMVIT 2024

作者： Wu, Yingbin Zhao, Peng Zhou, Mingquan Geng, Shengling Zhang, Dan School of Computer Science Qinghai Normal University Qinghai Xining China School of Mathematics and Information Technology Yuncheng University Shanxi Yuncheng China State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining China

An edge detection technology based on the combination of non-downsampling contour wave transform (NSCT) and tensor voting is proposed, which aims to obtain more accurate and detailed edge information of buildings in remote sensing images. Firstly, NSCT is used for image decomposition to obtain the subband frequency information of different scales and angles. Then, position encoding is performed on these subband coefficients to obtain second-order symmetric tensors at the corresponding positions. Tensors of different scales and angles at the same position are weighted and summed to complete feature fusion. Finally, the edge features of the image are obtained based on tensor voting theory. The experimental results show that compared to common edge detection technologies, such as Canny, Fast Edge (Fast edge detection using structured forests) and HED (Holistically-Nested Edge Detection), our method can more accurately and intensively reflect the boundaries of buildings and the edge information of roofs, providing better support for the analysis of building types and architectural styles. Compared to the HED method, which is based on deep learning, our method improves PSNR and SSIM metrics by 0.98 and 0.03, respectively. © Published under licence by IOP Publishing Ltd.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

An Assisting Education System of Electronic Building Blocks Based on Deep Learning 24

An Assisting Education System of Electronic Building Blocks ...

引用

2024 7th International Conference on computer information Science and Artificial Intelligence, CISAI 2024

作者： Shi, Zhuo Xu, Ziquan Qiu, Xia He, Haoen Luo, Xiaonan School of Art and Design Guilin University of Electronic Technology Guangxi Guilin China Guangxi Key Laboratory of lmage and Graphic Intelligent Processing Guangxi Guilin China Department of Computer and Information Security University of Guilin Electronic Technology Guangxi Guilin China Department of Guangxi Key Laboratory of Image and Graphic Intelligent Processing University of Guilin Electronic Technology Guangxi Guilin China

ISBN: (纸本)9798400707254

It is difficult for children to build electronic building blocks. In order to facilitate users to build building blocks, this paper designs and implements an electronic building block auxiliary system based on machine vision. The system uses the deep learning object detection model PP-YOLOv2 to detect the building block pictures taken by the user, obtain the location information of all the two-dimensional code in the pictures, and then decode the two-dimensional code, perform perspective transformation on the pictures, and obtain the final two-dimensional code decoding information and location information. Finally, the position of the QR code identified by the building blocks on the user’s picture is crossed and compared with the position of the standard building blocks, so as to determine whether the building blocks placed by the user are correct and give the user a prompt. The system test shows that the system is not only easy to use, but also easy to maintain, and can correctly handle most of the small and medium difficulty examples in the electronic building blocks course. © 2024 Copyright held by the owner/author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Joint Extraction of Interaction Features and Attention Mechanism Fused with Entity-Relations 36

Joint Extraction of Interaction Features and Attention Mecha...

引用

36th International Conference on Software Engineering and Knowledge Engineering, SEKE 2024

作者： Su, Lisha Yan, Rong College of Computer Science Inner Mongolia University Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot010021 China

ISBN: (纸本)1891706594

Joint extraction of entities and relations is an essential task in information extraction. Recently, tagging-based models have gained attention but with poor performance on overlapping triplets, which confronted the issues like cascading errors, information redundancy, and sensitivity to subject extraction. To solve the issue of overlapping triplets, we propose a model combined Gated Attention Unit (GAU) and Multi-head Attention Mechanism (MHA) in this paper. This model distinguishes features for entities and relations, and performs entity recognition for each head entity, different head entities are matched to the same or different tail entities. Then specific tail entity tagging is applied to determine all possible relations and corresponding tails. At the same time, in order to better solve the long-distance dependence and complex multiple relations between entities, GAU and MHA are used to enhance the semantic representation, effectively identify entities and relations, and enhance the learning ability and generalization ability of the model. Experiment results on the public datasets DuIE2.0 and CMeIE show that our model performs better than baselines. © 2024 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Large Model-Based Data Augmentation for Imbalanced Text Classification 5

Large Model-Based Data Augmentation for Imbalanced Text Clas...

引用

5th International Seminar on Artificial Intelligence, Networking and information technology, AINIT 2024

作者： Zhang, Dawei Mi, Rongxin Zhou, Peiyao Jin, Dawei Zhang, Manman Song, Tianhang School of Computer Science Jiangsu University of Science and Technology Jiangsu Zhenjiang China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China Key Laboratory of Intelligent Information Processing Beijing China

ISBN: (纸本)9798350385557

This study focuses on the application of large models to deal with imbalanced data problems in text classification. In view of the central position of text in web data and the negative impact of class imbalance on classifier performance, researchers have explored the method of using large models to generate high-quality minority class samples to enhance model performance. This paper reviews the technical progress of machine learning, deep learning, and large language models and their applications in text classification tasks. Although large models perform well in complex tasks due to their excellent language understanding ability, traditional machine learning and deep learning methods are popular in text classification scenarios that require fast response due to their simple structure and higher computational efficiency. This study proposes a data augmentation technique inspired by SMOTE, which uses a large language model combined with a simple prompt engineering strategy to generate high-quality minority samples. The experimental results show that the proposed method significantly improves the macro average precision, recall and F1 score on multiple text classification models, and effectively alleviates the challenge of class imbalance. © 2024 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Sub-50-pm displacement sensing via phase-matched metasurface-prism configuration

引用

Optics Letters 2025年第12期50卷 3919-3922页

作者： Zhouxin LiangXin GuJiaqi LiLixun WuZhaoxiang ZhuShuqing LinYuhang LinYujie Chen Siyuan Yu State Key Laboratory of Optoelectronic Materials and Technologies Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems School of Electronics and Information Technology Sun Yat-sen University Guangzhou 510275 China

Accurate transverse displacement measurement at the picometer scale is essential for advancing ultraprecision metrology and probing microscopic physical interactions. Here, we demonstrate a high-precision transverse displacement sensor leveraging a phase-matched Pancharatnam–Berry (PB) metasurface and trapezoidal prism configuration, which simplifies optical alignment by eliminating stringent Talbot self-imaging requirements. By synergistically matching the phase gradient of the PB metasurface with the prism geometry, we enable robust signal extraction through the photonic spin Hall effect, while a near-infrared source ( λ = 1550 nm) suppresses environmental interference. Differential amplification further rejects common-mode noise from laser fluctuations and electronic drift. The system achieves a displacement resolution of 46.18 pm under quasi-static conditions (0.2–100 Hz) and 124.86 pm across the full operational bandwidth (0.2–1.25 MHz), surpassing conventional polarization-encoded schemes in both sensitivity and practicality. This work thus presents a strategy for metasurface-enhanced metrology via geometric-phase-engineered photonic architectures, with transformative potential across applications from semiconductor lithography to quantum optomechanics.

关键词： Chemical vapor deposition Finite-difference time-domain method Lithography Near infrared Optical testing Phase matching

来源：评论

学校读者我要写书评

暂无评论

PLIP: Language-Image Pre-training for Person Representation Learning 38

PLIP: Language-Image Pre-training for Person Representation ...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Zuo, Jialong Hong, Jiahao Zhang, Feng Yu, Changqian Zhou, Hanyu Gao, Changxin Sang, Nong Wang, Jingdong National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Skywork AI United States Department of Computer Vision Baidu Inc. China

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory performance. The reason is that they neglect critical person-related characteristics, i.e., fine-grained attributes and identities. To address this issue, we propose a novel language-image pre-training framework for person representation learning, termed PLIP. Specifically, we elaborately design three pretext tasks: 1) Text-guided Image Colorization, aims to establish the correspondence between the person-related image regions and the fine-grained color-part textual phrases. 2) Image-guided Attributes Prediction, aims to mine fine-grained attribute information of the person body in the image;and 3) Identity-based Vision-Language Contrast, aims to correlate the cross-modal representations at the identity level rather than the instance level. Moreover, to implement our pre-train framework, we construct a large-scale person dataset with image-text pairs named SYNTH-PEDES by automatically generating textual annotations. We pre-train PLIP on SYNTH-PEDES and evaluate our models by spanning downstream person-centric tasks. PLIP not only significantly improves existing methods on all these tasks, but also shows great ability in the zero-shot and domain generalization settings. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Graph Convolutional Neural Network based on Adaptive Sampling and Aggregation Strategy 2

Deep Graph Convolutional Neural Network based on Adaptive Sa...

引用

2nd International Conference on Machine Vision, Image processing and Imaging technology, MVIPIT 2024

作者： Wang, Xueli Zhang, Wei Li, Gege Zhou, Lin Liu, Hongkai Ye, Zhonglin School of Computer Qinghai Normal University Xining810008 China Qinghai Provincial Key Laboratory of Tibetan Information Processing and Machine Translation Xining810008 China Graduate School of Engineering Nagasaki Institute of Applied Science Nagasaki851-0193 Japan

ISBN: (纸本)9798331543037

Graph neural networks learn node embeddings by recursively sampling and aggregating nodes in a graph, while existing methods have a fixed pattern of node sampling and aggregation, and usually only consider direct neighborhood. When sampling high-order neighborhood, it is easy to produce over-smoothing, which affects the model performance and accuracy. Therefore, this paper proposes an adaptive sampling and aggregation deep graph convolutional network (Adaptive Sampling and Aggregation Depth Graph Convolutional Network, ASA-GCN). A sampling strategy based on node importance is designed to adaptively sample high-order neighbors of nodes. Meanwhile, an aggregation strategy based on self-attention mechanism is proposed to adaptively aggregate node information within a given neighborhood. Finally, experimental results on multiple benchmark graph datasets show that the model has superior performance on the node classification task. ©2024 IEEE.

关键词： Convolutional neural networks

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：