检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Ziwei Li, Siyang Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Epilepsy significantly impacts global health, affecting about 65 million people worldwide, along with various animal species. The diagnostic processes of epilepsy are often hindered by the transient and unpredictable nature of seizures. Here we propose a multi-space alignment approach based on cross-species and cross-modality electroencephalogram (EEG) data to enhance the detection capabilities and understanding of epileptic seizures. By employing deep learning techniques, including domain adaptation and knowledge distillation, our framework aligns cross-species and cross-modality EEG signals to enhance the detection capability beyond traditional within-species and within-modality models. Experiments on multiple surfaces and intracranial EEG datasets of humans and canines demonstrated substantial improvements in detection accuracy, achieving over 90% AUC scores for cross-species and cross-modality seizure detection with extremely limited labeled data from the target species/modality. To our knowledge, this is the first study that demonstrates the effectiveness of integrating heterogeneous data from different species and modalities to improve EEG-based seizure detection performance. This is a pilot study that provides insights into the challenges and potential of multi-species and multi-modality data integration, offering an effective solution for future work to collect huge EEG data to train large brain models. © 2024, CC BY.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation

KERM: Knowledge Enhanced Reasoning for Vision-and-Language N...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiangyang Li Zihan Wang Jiahao Yang Yaowei Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing China University of Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Vision-and-language navigation (VLN) is the task to enable an embodied agent to navigate to a remote location following the natural language instruction in real scenes. Most of the previous approaches utilize the entire features or object-centric features to represent navigable candidates. However, these representations are not efficient enough for an agent to perform actions to arrive the target location. As knowledge provides crucial information which is complementary to visible content, in this paper, we propose a Knowledge Enhanced Reasoning Model (KERM) to leverage knowledge to improve agent navigation ability. Specifically, we first retrieve facts (i.e., knowledge described by language descriptions) for the navigation views based on local regions from the constructed knowledge base. The re-trieved facts range from properties of a single object (e.g., color, shape) to relationships between objects (e.g., action, spatial position), providing crucial information for VLN. We further present the KERM which contains the purification, fact-aware interaction, and instruction-guided aggregation modules to integrate visual, history, instruction, and fact features. The proposed KERM can automatically select and gather crucial and relevant cues, obtaining more accurate action prediction. Experimental results on the REVERIE, R2R, and SOON datasets demonstrate the effectiveness of the proposed method. The source code is available at https://***/XiangyangLi20/KERM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perception-Oriented Stereo Image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Ma, Chenxi Tan, Weimin Yan, Bo Jiang, Xuhao Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China

Recent studies of deep learning based stereo image super-resolution (StereoSR) have promoted the development of StereoSR. However, existing StereoSR models mainly concentrate on improving quantitative evaluation metrics and neglect the visual quality of super-resolved stereo images. To improve the perceptual performance, this paper proposes the first perception-oriented stereo image super-resolution approach by exploiting the feedback, provided by the evaluation on the perceptual quality of StereoSR results. To provide accurate guidance for the StereoSR model, we develop the first special stereo image super-resolution quality assessment (StereoSRQA) model, and further construct a StereoSRQA database. Extensive experiments demonstrate that our StereoSR approach significantly improves the perceptual quality and enhances the reliability of stereo images for disparity estimation. © 2022, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Hundredfold increase of stimulated Brillouin-scattering bandwidth in whispering-gallery mode resonators

引用

Photonics Research 2023年第6期11卷 917-924页

作者： GUOPING LIN JINGYI TIAN TANG SUN QINGHAI SONG YANNE K.CHEMBO Ministry of Industry and Information Technology Key Laboratory of Micro-Nano Optoelectronic Information System School of ScienceHarbin Institute of TechnologyShenzhen 518055China Guangdong Provincial Key Laboratory of Semiconductor Optoelectronic Materials and Intelligent Photonic Systems Shenzhen 518055China Department of Electrical and Computer Engineering&Institute for Research in Electronics and Applied Physics(IREAP) University of MarylandCollege ParkMaryland 20742USA

Backward stimulated Brillouin scattering(SBS)is widely exploited for various applications in optics and *** typically features a narrow gain bandwidth of a few tens of megahertz in fluoride *** we report a hundredfold increase of SBS bandwidth in whispering-gallery mode *** crystalline orientation results in a large variation of the acoustic phase velocity upon propagation along the periphery,from which a broad Brillouin gain is *** 2.5 GHz wide Brillouin gain profile is theoretically found and experimentally *** phenomena with Brillouin shift frequencies ranging from 11.73 to 14.47 GHz in ultrahigh Q Z-cut magnesium fluoride cavities pumped at the telecommunication wavelength are ***,the Brillouin-Kerr comb in this device is *** 400 comb lines spanning across a spectral window of 120 nm are *** finding paves a new way for tailoring and harnessing the Brillouin gain in crystals.

关键词： scattering pumped Brillouin

来源：评论

学校读者我要写书评

暂无评论

Real-time quantification of nuclear RNA export using an intracellular relocation probe

引用

Chinese Chemical Letters 2022年第8期33卷 3865-3868页

作者： Jie Shen Juan Chen Dong Wang Zhengjie Liu Guangmei Han Bianhua Liu Mingyong Han Ruilong Zhang Guodong Liu Zhongping Zhang School of Chemistry and Chemical Engineering Information Materials and Intelligent Sensing Laboratory of Anhui Provinceand Institute of Physical Science and Information TechnologyAnhui UniversityHefei 230601China Key Laboratory of Structure and Functional Regulation of Hybrid Materials(Anhui University) Ministry of EducationHefei 230601China Key Lab of Photovoltaic and Energy Conservation Materials Institute of Solid State PhysicsHFIPSChinese Academy of SciencesHefei 230031China School of Life and Health Sciences Anhui Science and Technology UniversityChuzhou 233100China

Nuclear RNA export into the cytoplasm is one of the key steps in protein expression to realize biological *** the broad availability of nucleic acid dyes,tracking and quantifying the highly dynamic process of RNA export in live cells is *** dye-labeled RNA enters the cytoplasm,the dye molecules are released upon degradation of the RNA,allowing them to re-enter the cell *** a result,the ratio between the dye exported with RNA into the cytoplasm and the portion staying inside the nucleus cannot be *** address this common limitation,we report the design of a smart probe that can only check into the nucleus *** adding to cells,this probe rapidly binds with nuclear RNAs in live cells and reacts with intrinsic H_(2)*** reaction not only activates the fluorescence for RNA tracking but also changes the structure of probe and consequently its intracellular *** disassociating from exported RNAs in cytoplasm,the probe preferentially enters lysosomes rather than cell nucleus,enabling real-time quantitative measurement of nuclear RNA *** this probe,we successfully evaluated the effects of hormones and cancer drugs on nuclear RNA export in live ***,we found that hormones inhibiting RNA exports can partially offset the effect of chemotherapy.

关键词： RNA export Quantification Relocation probe Fluorescence imaging Hormone

来源：评论

学校读者我要写书评

暂无评论

Hybrid Pruning Method Based on Convolutional Neural Network Sensitivity and Statistical Threshold 2

Hybrid Pruning Method Based on Convolutional Neural Network ...

引用

2nd International Conference on Computer, Big Data and Artificial Intelligence, ICCBDAI 2021

作者： Guo, Changyi Li, Ping School of Computer and Communication Engineering Changsha University of Science and Technology Hunan Changsha410114 China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Hunan Changsha410114 China

The hybrid pruning algorithm can not only ensure the precision of the network, but also achieve a good balance between pruning ratio and computation. However, traditional pruning algorithms use coarse-grained or fine-grained pruning networks, which have the tradeoff problem between pruning rate and computation amount. To this end, this paper presents. A hybrid pruning method of sensitivity and statistical threshold. Firstly, coarse-grained pruning is carried out on the network, and a fast sensitivity test is conducted on the convolutional layer of the network to determine the channels that need pruning within the tolerance range of network precision decline. Then, fine-grained pruning is performed on the network. Count the weights of the pruned network, calculate the thresholds of the weights of each layer, and delete the weights less than the thresholds so as to further reduce the size of the network and the amount of calculation. Hybrid pruning performs very well in AlexNet and Resnet networks. In particular, the method proposed in this paper is used in CIFAR-10 dataset, and the compression of FLOPs is 60%, while the compression of parameter number is nearly 80%. Compared with single pruning method, Hybrid pruning is better. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

WDNet: A Water Depth Perception Network with Global information

WDNet: A Water Depth Perception Network with Global Informat...

引用

Chinese Control Conference (CCC)

作者： Zhihui Huang Yifeng Tang Chuancong Tang Yifan Xu ChuanShang Luo Bin Liu Hai-Tao Zhang the Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation the Engineering Research Center of Autonomous Intelligent Unmanned Systems Huazhong University of Science and Technology Wuhan China

Deep perception of the unmanned surface vehicle's surroundings is an inaccessible part of its fully autonomous navigation mission. The existing methods, whether based on traditional stereo matching or deep learning, do not fully consider the characteristics of water environment, resulting in severe error depths in weak textures (sky, calm lake) and water reflections regions, that increases the risk of running aground or collision. What is worse that there is not a public dataset for depth estimation in the water environment. Therefore, this work proposes a self-supervised model for depth estimation named Water Depth Perception Network (WDNet) to address these problems. The decoder of this network has a wider receptive field and can effectively handle the depth error in the weak texture region. Besides, the WDNet is trained with a novel and effective loss function which assist the network to reduce errors in sky and water region, and some indexes are proposed to evaluate the model's performances in sky and water region. Finally, our proposed WDNet achieves a 0.1056 absolute relative error in ranging, the average number of error pixels in the sky area drops from 15803.87 to 580.91, which only accounted for 0.29% of the image, and the error in water region drops from 51.04 to 6.75, all of them are superior to the performance of baseline model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Koopman Operator Learning Control of the Piezoelectric Actuator

Koopman Operator Learning Control of the Piezoelectric Actua...

引用

Chinese Control Conference (CCC)

作者： Xiang Huang Hai-Tao Zhang Engineering Research Center of Autonomous Intelligent Unmanned Systems the Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

The piezoelectric actuator is one kind of device that can drive nanoscale motion. However, the nonlinear hysteresis effect induced by its natural material greatly degrades its positioning accuracy. To handle this challenging issue, this work develops a Koopman model predict control (Koopman- MPC) framework for the piezoelectric actuator. Specifically, the Koopman operator theory is adapted for modeling the piezoelectric actuator dynamics. A simple yet powerful linear model spanned in a high-dimensional space is thus constructed to characterize the hysteresis dynamics. Subsequently, upon the established Koopman model, an MPC scheme is put forward for tracking control of piezoelectric actuators. Therein, by sustained optimizing a cost function containing future outputs and control increments, the control input is obtained. Moreover, extensive tracking simulations are carried out on a simulated piezoelectric actuator for verifying the feasibility and effectiveness of the Koopman- Mpc scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP

arXiv

引用

arXiv 2025年

作者： Ma, Wenxin Zhang, Xu Yao, Qingsong Tang, Fenghe Wu, Chenxu Li, Yingtai Yan, Rui Jiang, Zihang Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine USTC China MIRACLE Center Suzhou Institute for Advance Research USTC China Key Laboratory of Intelligent Information Processing of CAS ICT CAS China State Key Laboratory of Precision and Intelligent Chemistry USTC China Stanford University United States

Anomaly detection (AD) identifies outliers for applications like defect and lesion detection. While CLIP shows promise for zero-shot AD tasks due to its strong generalization capabilities, its inherent Anomaly-Unawareness leads to limited discrimination between normal and abnormal features. To address this problem, we propose Anomaly-Aware CLIP (AA-CLIP), which enhances CLIP’s anomaly discrimination ability in both text and visual spaces while preserving its generalization capability. AA-CLIP is achieved through a straightforward yet effective two-stage approach: it first creates anomaly-aware text anchors to differentiate normal and abnormal semantics clearly, then aligns patch-level visual features with these anchors for precise anomaly localization. This two-stage strategy, with the help of residual adapters, gradually adapts CLIP in a controlled manner, achieving effective AD while maintaining CLIP’s class knowledge. Extensive experiments validate AA-CLIP as a resource-efficient solution for zero-shot AD tasks, achieving state-of-the-art results in industrial and medical applications. The code is available at https://github. com/Mwxinnn/AA-CLIP. © 2025, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

ViT-MGI: Context-aware Lightweight Malicious Gradient Identification for Federated Vision Transformer Systems against Poisoning Attacks 10

ViT-MGI: Context-aware Lightweight Malicious Gradient Identi...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Yang, Shujie Li, Tengfei Zhou, Zan Hao, Hao Xu, Tianyu Wang, Bo Guan, Jianfeng Zhou, Tianhang Yao, Su Beijing University of Posts and Telecommunications School of Computer Science Beijing China Shandong Academy of Sciences & National Supercomputing Center Jinan China College of Carbon Neutrality Future Technology State Key Laboratory of Heavy Oil Processing Beijing102249 China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing China

ISBN: (纸本)9798331520861

With the continuous development of large vision models, training requires increasingly large datasets. Federated Learning for Vision Transformer models (Federated ViT) is needed to train models without data leaving multiple clients while capturing complex global features. However, various attacks, such as tampering with gradient data, label-flipping, and backdoor attacks, pose significant challenges to federated learning. Existing defense mechanisms like the Krum algorithm, PCA, and Sniper scheme exhibit low efficiency and poor robustness in Federated ViT scenarios due to the vast number of parameters and inactive neurons. This paper proposes a two-stage, context-aware lightweight malicious gradient identification method for ViT to improve the efficiency and robustness of malicious user detection. By using feature layer extraction and Principal Component Analysis (PCA), we eliminate invalid gradient information, enhancing both detection efficiency and robustness. We reduced data dimensions to 0. 4 % of the original without compromising detection accuracy. The Isolation Forest algorithm distinguishes between malicious and benign users based on extracted gradient features, and a Subjective Logic Model performs temporal accumulation of user scores to improve accuracy and reduce erroneous identifications. Experiments on CIFAR-10, MNIST, and OrganAMNIST datasets show that our model reduces processing time by approximately 70% compared to advanced PCA methods, while significantly improving accuracy and F1 scores. Additionally, our method offers substantial advantages in both efficiency and robustness compared to pooling techniques aimed at reducing computational load. We have named our model ViT-MGI and released its source code to facilitate future research in this field: https://***/LetMeFly666/ViT-MGI. © 2024 IEEE.

关键词： Federated learning

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：