检索结果-内蒙古大学图书馆

Fast-adaptive super-resolution lattice light-sheet microscopy for rapid, long-term, near-isotropic subcellular imaging

引用

Nature Methods 2025年第5期22卷 1059-1069页

作者： Qiao, Chang Li, Ziwei Wang, Zongfa Lin, Yuhuan Liu, Chong Zhang, Siwei Liu, Yong Feng, Yun Yang, Xiaoyu Fu, Wenfeng Dong, Xue Guo, Jiabao Xu, Wencong Wang, Xinyu Jiang, Tao Meng, Quan Wang, Qinghua Dai, Qionghai Li, Dong Department of Automation Tsinghua University Beijing China Institute for Brain and Cognitive Sciences Tsinghua University Beijing China Key Laboratory for Information Science of Electromagnetic Waves (MoE) Fudan University Shanghai China National Laboratory of Biomacromolecules CAS Center for Excellence in Biomacromolecules Institute of Biophysics Chinese Academy of Sciences Beijing China College of Life Sciences University of Chinese Academy of Sciences Beijing China Global Health Institute Swiss Federal Institute of Technology Lausanne (EPFL) Lausanne Switzerland Microelectronics Instruments and Equipment R & D Center Institute of Microelectronics Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Multi-dimension & Multi-scale Computational Photography Tsinghua University Beijing China Beijing Laboratory of Brain and Cognitive Intelligence Beijing Municipal Education Commission Beijing China IDG/McGovern Institute for Brain Research Tsinghua-Peking Center for Life Sciences Beijing Frontier Research Center for Biological Structure State Key Laboratory of Membrane Biology New Cornerstone Science Laboratory School of Life Sciences Tsinghua University Beijing China

Lattice light-sheet microscopy provides a crucial observation window into intra- and intercellular physiology of living specimens but at the diffraction-limited resolution or anisotropic super-resolution with structured illumination. Here we present meta-learning-empowered reflective lattice light-sheet virtual structured illumination microscopy (Meta-rLLS-VSIM), which upgrades lattice light-sheet microscopy to a near-isotropic super resolution of ~120 nm laterally and ~160 nm axially without modifications of the core optical system or loss of other live-cell imaging metrics. Moreover, we devised an adaptive online training approach by synergizing the front-end imaging system and back-end meta-learning framework, which alleviated the demand for training data by tenfold and reduced the total time for data acquisition and model training down to tens of seconds. We demonstrate the versatile functionalities of Meta-rLLS-VSIM by imaging a variety of bioprocesses with ultrahigh spatiotemporal resolution for hundreds of multicolor volumes, delineating the nanoscale distributions, dynamics and interaction patterns of multiple organelles in embryos and eukaryotic cells. © The Author(s), under exclusive licence to Springer Nature America, Inc. 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical focusing feature of single element in 128×128 elements electrically controllable cylindrical liquid crystal lens array

引用

Chinese Optics Letters 2010年第3期8卷 329-331页

作者：李晖刘侃张新宇张天序沈绪榜 Institute for Pattern Recognition and Artificial IntelligenceHuazhong University of Science and Technology National Laboratory for Multi-Spectral Information Processing Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics

A 128× 128 elements cylindrical liquid crystal （LC） lens array with electrically controllable focal length is proposed. The cylindrical LC lens array uses transparent indium tin oxide （ITO） films as electrode, avoiding to affect the optical path operating in the voltage-off status. As the top electrode of the cylindrical LC lens array contacts with LC, the operation voltage root-mean-square （RMS） amplitude can be as low as 1.4 V and the response time is about 20-30 ms. The special optical focusing feature of the cylindrical LC lens array is got. And the focal length of this array is about 60-450 μm.

关键词： Focusing ITO glass Liquid crystals Oxide films Tin Titanium compounds

来源：评论

学校读者我要写书评

暂无评论

Small moving target detection model based on improved mixed disturbance gauss model

引用

Telkomnika (Telecommunication Computing Electronics and Control) 2016年第3A期14卷 229-236页

作者： Bai, Ting Tian, Jinwen Sun, Xiao National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Automation Huazhong University of Science and Technology Wuhan430074 China

In order to obtain ideal moving target detection results, a kind of moving target detection algorithm of improved mixture Gaussian model is proposed in this paper on the basis of analyzing the deficiency of traditional Mixture Gaussian model. Firstly, in this algorithm, the update rate is increased to better adapt to the change of environment and the idea of pixel connected region is introduced to remove the noise, then the invariance property of chroma is adopted to avoid arising of "shadow" phenomenon;finally, simulation comparison experiment is used to test its performance. The experiment results show that this algorithm can generate reliable background image and accurately and completely detect the moving target to obtain more superior detection results of comparison algorithm, which can meet the practical application requirement of target tracking. © 2016 Universitas Ahmad Dahlan. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

multilingual Parameter-Sharing Adapters: A Method for Optimizing Low-Resource Neural Machine Translation

Multilingual Parameter-Sharing Adapters: A Method for Optimi...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yunlong Zhang Nan Chen Yonghe Wang Xiangdong Su Feilong Bao School of Computer Science Inner Mongolia University Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China National and Local Joint Engineering Research Center of Mongolian Information Processing Technology Hohhot China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Adapter-based multilingual Neural Machine Translation (MNMT) has become a significant approach in low-resource language translation by mitigating data imbalances between high-resource and low-resource language pairs and reducing training costs. However, existing adapter-based methods lack generalization in cross-lingual settings, particularly under low-resource conditions, where their scalability is limited. Additionally, current methods often introduce independent adapter modules for each language, leading to a linear increase in model parameters with the number of languages. To address these challenges, we propose a multilingual parameter-sharing adapter approach. Moreover, we introduce a neural architecture search (NAS)-based strategy to improve translation performance. Experimental results demonstrate that the multilingual parameter-sharing adapter exhibits competitive performance on both low-resource and high-resource datasets. The multilingual parameter-sharing adapter method has only 400K trainable parameters, which is 20× lower than the parameters of the traditional adapter method.

关键词： Training Degradation Adaptation models Translation Scalability Neural machine translation Signal processing multilingual Neural architecture search Speech processing

来源：评论

学校读者我要写书评

暂无评论

Structural-Aware Disentangled Learning with CLIP for Hyperbolic Zero-Shot Sketch-Based Image Retrieval*

Structural-Aware Disentangled Learning with CLIP for Hyperbo...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Qing Zhang Jing Zhang Feilong Bao Xiangdong Su Guanglai Gao School of Computer Science Inner Mongolia University Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China National and Local Joint Engineering Research Center of Mongolian Information Processing Technology Hohhot China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The zero-shot sketch-based image retrieval task faces two key challenges: domain gap and knowledge transfer. Our innovation is recognizing that directly aligning cross-domain features weakens the discriminative ability of the model, as it overlooks the asymmetry between sketches and images. Additionally, Euclidean space is inadequate for capturing the hierarchical structure, which limits the performance of the model on complex data. To address these issues, we propose a Structural-Aware Disentangled Learning network (termed SADLnet) that incorporates CLIP and hyperbolic geometry. Specifically, we use CLIP to extract visual features from each domain to enhance the domain generalization of the model. Furthermore, we design a structure-guided disentanglement strategy to decompose image representations into sketch-related and sketch-unrelated features, addressing the domain gap. Moreover, we project the retrieval features into hyperbolic space to capture hierarchical information, improving feature discrimination in retrieval tasks. Extensive experiments demonstrate that SADLnet establishes new state-of-the-art performance on three datasets.

关键词： Geometry Adaptation models Visualization Technological innovation Disentangled representation learning Image retrieval Signal processing Feature extraction Data models Speech processing

来源：评论

学校读者我要写书评

暂无评论

HNet: A Loss Rate Robust ISAR Imaging Framework Based on Hypernetwork

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Li, Xiaoyong Liu, Lei Huang, Jiale Li, Lei Bai, Xueru Zhou, Feng Xidian University Hangzhou Institute of Technology Hangzhou311231 China Xidian University Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education Xi'an710071 China Xidian University National Key Lab of Radar Signal Processing Xi'an710071 China Xidian University School of Aerospace Science and Technology Xi'an710071 China

Deep learning has significantly advanced the field of sparse inverse synthetic aperture radar (ISAR) imaging. Nonetheless, current methodologies often face constraints due to their reliance on fixed loss rates and types, which can limit practical applicability and result in elevated computational demands both spatially and temporally, as well as diminished generalizability. In tackle to these challenges, this paper introduces a resilient ISAR imaging architecture grounded in hypernetwork technology capable of accommodating diverse loss rates. Initially, we devise a sparse signal reconstruction technique that functions irrespective of the loss rate or matrix dimensions. Subsequently, a methodology for producing arbitrary loss rates is outlined. Building upon this foundation, we present a hypernetwork framework that harnesses hypernetworks to derive defocus characteristics from range-Doppler (RD) imagery across varying loss rates, subsequently transforming these insights into ideal parameters for the sparse signal reconstruction process. By executing the iterative algorithm with these optimized parameters, we achieve loss rate robust ISAR imaging. Comprehensive evaluations conducted on point simulated data, electromagnetic simulated data and measured data confirm the superiority of our proposed approach in terms of reconstruction accuracy and generalization capabilities. This advancement facilitates reliable ISAR imaging across a spectrum of loss rates. 1965-2011 IEEE.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

MN-Net: Speech Enhancement Network via Modeling the Noise

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 1208-1219页

作者： Ying Hu Qin Yang Wenbing Wei Li Lin Liang He Zhijian Ou Wenzhong Yang School of Computer Science and Technology Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China Xinjiang Institute of Electronics Research Shares Company Ltd. Urumqi China Department of Electrical Engineering Tsinghua University Beijing China Beijing National Research Center for information Science and Technology Department of Electronics Tsinghua University Beijing China

Currently, deep learning-based speech enhancement methods generally focus on target speech extraction while neglecting modeling the other sound sources in the mixture. These methods still can't distinguish the target speech from the interference well. In this paper, we present a monaural speech enhancement network via Modeling the Noise (MN-Net), which includes a shared Encoder and three separate Decoders for parallel modeling the magnitude and phase spectrogram of target speech, and the complex spectrogram of noise. Specifically, we propose a multi-Branch Feature Extractor (MBFE) module to capture the richer contextual information in mixture, and a Spatial Reconstruction Unit (SRU) to remove the redundancy from extracted features. We compared our proposed MN-Net with 18 classical speech enhancement methods on the VoiceBank+DEMAND dataset, and with 9 ones on DNS-Challenge dataset for denoising task, and with 7 ones on the WHAMR! dataset for simultaneous denoising & de-reverberation task. Our proposed MBFE module was applied to two classical speech enhancement methods, DB-AIAT and CMGAN, replacing their DenseBlocks module. The results demonstrate that applying the MBFE module can boost their performances while keeping smaller model size. A series of visualization analysis intuitively verify that modeling the noise can enable the network to distinguish the target speech from noise and other interference more accurately.

关键词： Noise Feature extraction Spectrogram Speech enhancement Decoding Kernel Transformers Noise reduction Data mining Training

来源：评论

学校读者我要写书评

暂无评论

Photonic axion insulator

引用

science (New York, N.Y.) 2025年第6730期387卷 162-166页

作者： Liu, Gui-Geng Mandal, Subhaskar Xi, Xiang Wang, Qiang Devescovi, Chiara Morales-Pérez, Antonio Wang, Ziyao Yang, Linyun Banerjee, Rimi Long, Yang Meng, Yan Zhou, Peiheng Gao, Zhen Chong, Yidong García-Etxarri, Aitzol Vergniory, Maia G. Zhang, Baile Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore Research Center for Industries of the Future Department of Electronic and Information Engineering School of Engineering Westlake University Hangzhou China School of Electrical Engineering and Intelligentization Dongguan University of Technology Dongguan China National Laboratory of Solid State Microstructures School of Physics Collaborative Innovation Center of Advanced Microstructures Nanjing University Nanjing China Donostia International Physics Center Donostia-San Sebastian Spain Institute for Theoretical Physics ETH Zurich Zurich Switzerland Material and Applied Physics Department University of the Basque Country (UPV/EHU) Donostia-San Sebastián Spain Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China National Engineering Research Center of Electromagnetic Radiation Control Materials Key Laboratory of Multi-spectral Absorbing Materials and Structures of Ministry of Education University of Electronic Science and Technology of China Chengdu China State Key Laboratory of Optical Fiber and Cable Manufacture Technology Department of Electronic and Electrical Engineering Guangdong Key Laboratory of Integrated Optoelectronics Intellisense Southern University of Science and Technology Shenzhen China Centre for Disruptive Photonic Technologies Photonics Institute Nanyang Technological University Singapore IKERBASQUE Basque Foundation for Science Bilbao Spain Max Planck Institute for Chemical Physics of Solids Dresden Germany Département de Physique et Institut Quantique Université de Sherbrooke Sherbrooke Canada

Axions, hypothetical elementary particles that remain undetectable in nature, can arise as quasiparticles in three-dimensional crystals known as axion insulators. Previous implementations of axion insulators have largely been limited to two-dimensional systems, leaving their topological properties in three dimensions unexplored in experiment. Here, we realize an axion insulator in a three-dimensional photonic crystal and probe its topological properties. Demonstrated features include half-quantized Chern numbers on each surface that resembles a fractional Chern insulator, unidirectional chiral hinge states forming topological transport in three dimensions, and arithmetic operations between fractional and integer Chern numbers. Our work experimentally establishes the axion insulator as a three-dimensional topological phase of matter and enables chiral states to form complex, unidirectional three-dimensional networks through braiding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Building localization from forward-looking infrared images for UAV guidance

引用

Gyroscopy and Navigation 2013年第4期4卷 188-197页

作者： Qin, Y. Cao, Zh. Li, H. Wang, X. Zhuo, W. National Key Laboratory of Science and Technology on Multi-Spectral Information Processing Wuhan China School of Automation Huazhong University of Science and Technology Wuhan China

This paper proposes a new approach to localizing a designated building from forward-looking infrared images under complex scenes, which can be used in UAV guidance. The approach makes full use of the scene information and is able to localize small or occluded buildings. The experiment results prove the algorithm efficiency. © 2013 Pleiades Publishing, Ltd.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Semantic Data Augmentation for Few-Shot Biomedical Named Entity Recognition

Semantic Data Augmentation for Few-Shot Biomedical Named Ent...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Ying Zhang Weihua Wang College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Biomedical Named Entity Recognition (BioNER) aims to identify and classify entities in biomedical text. This task struggles with data scarcity due to limited annotated data. Although data augmentation is effective, existing methods fail to handle the complex semantic mappings on biomedical terminology, which results in the generated samples lacking semantic diversity. In this paper, we propose a data augmentation method to create semantically diverse and coherent training samples for few-shot BioNER. The method utilizes the Unified Medical Language System (UMLS) for entity replacement and combines with a Masked Language Model (MLM) to generate contextually relevant words. Experimental results show that our method improves BioNER performance in few-shot scenarios. Compared to all baseline models, our method achieves an average F1 score improvement of 7.6% and 11.6% on the NCBI and JNLPBA datasets, respectively. Our source code and data are available at https://***/ABC8184/SDA

关键词： Training Terminology Biological system modeling Source coding Unified modeling language Semantics Named entity recognition Signal processing Data augmentation Speech processing

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：