检索结果-内蒙古大学图书馆

Vivim: a Video Vision Mamba for Ultrasound Video Segmentation

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Yang, Yijun Xing, Zhaohu Yu, Lequan Fu, Huazhu Huang, Chunwang Zhu, Lei Nansha Guangdong Guangzhou511400 China School of Computing and Data Science University of Hong Kong Hong Kong 138632 Singapore Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Southern Medical University Department of Ultrasound China Robotics and Autonomous Systems Thrust China Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong

Ultrasound video segmentation gains increasing attention in clinical practice due to the redundant dynamic references in video frames. However, traditional convolutional neural networks have a limited receptive field and transformer-based networks are unsatisfactory in constructing long-term dependency from the perspective of computational complexity. This bottleneck poses a significant challenge when processing longer sequences in medical video analysis tasks using available devices with limited memory. Recently, state space models (SSMs), famous by Mamba, have exhibited linear complexity and impressive achievements in efficient long sequence modeling, which have developed deep neural networks by expanding the receptive field on many vision tasks significantly. Unfortunately, vanilla SSMs failed to simultaneously capture causal temporal cues and preserve non-casual spatial information. To this end, this paper presents a Video Vision Mamba-based framework, dubbed as Vivim, for ultrasound video segmentation tasks. Our Vivim can effectively compress the long-term spatiotemporal representation into sequences at varying scales with our designed Temporal Mamba Block. We also introduce an improved boundary-aware affine constraint across frames to enhance the discriminative ability of Vivim on ambiguous lesions. Extensive experiments on thyroid segmentation in ultrasound videos, breast lesion segmentation in ultrasound videos, and polyp segmentation in colonoscopy videos demonstrate the effectiveness and efficiency of our Vivim, superior to existing methods. © 1991-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

ADAPT: Action-aware Driving Caption Transformer

ADAPT: Action-aware Driving Caption Transformer

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Bu Jin Xinyu Liu Yupeng Zheng Pengfei Li Hao Zhao Tong Zhang Yuhang Zheng Guyue Zhou Jingjing Liu Chinese Academy of Sciences Institute of Automation China Institute for AI Industry Research (AIR) Tsinghua University China Xidian University China Department of Computer Science and Technology Tsinghua University China Southern University of Science and Technology China School of Mechanical Engineering and Automation Beihang University China

End-to-end autonomous driving has great potential in the transportation industry. However, the lack of transparency and interpretability of the automatic decision-making process hinders its industrial adoption in practice. There have been some early attempts to use attention maps or cost volume for better model explainability which is difficult for ordinary passengers to understand. To bridge the gap, we propose an end-to-end transformer-based architecture, ADAPT (Action-aware Driving cAPtion Transformer), which provides user-friendly natural language narrations and reasoning for each decision making step of autonomous vehicular control and action. ADAPT jointly trains both the driving caption task and the vehicular control prediction task, through a shared video representation. Experiments on BDD-X (Berkeley DeepDrive eXplanation) dataset demonstrate state-of-the-art performance of the ADAPT framework on both automatic metrics and human evaluation. To illustrate the feasibility of the proposed framework in real-world applications, we build a novel deployable system that takes raw car videos as input and outputs the action narrations and reasoning in real time. The code, models and data are available at https://***/jxbbb/ADAPT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LSTM-Based Jamming Diagnosis and Prediction Model Utilizing Transport in Wi-Fi-Enabled IoT Systems

LSTM-Based Jamming Diagnosis and Prediction Model Utilizing ...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Wamika Goyal Vikrant Sharma K Karthika Raghu G Anand Y.V. Dongre K. Ranjith Singh Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Computer Science and Engineering Graphic Era Hill University Dehradun Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Civil Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai School of Management -UG Management JAIN Deemed to be University Bangalore Karnataka Comp Vishwakarma Institute of Technology Pune India Department of Computer Science Karpagam Academy of Higher Education Coimbatore

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

Every industry is seeing a rise in the use of the Internet of Things (IoT). Because of its widespread availability, high bandwidth, low cost, and adaptability, Wi-Fi-based communication is favored by wireless IoT devices. However, serious dangers exist due to security flaws in IoT devices, particularly in mission-critical and industrial settings. With an emphasis on industrial communication and environmental dynamics, this article introduces a new method for detecting jamming in the Internet of Things (IoT). Using production lines that include wireless IoT devices with a server-client architecture, it first focuses on collecting connection parameters and quality of service (QoS) during normal communication and jamming attacks so that it can more effectively investigate the communication conditions along with jamming in the industrial production environment. Results from experiments show that spot jamming has a devastating effect on higher-level protocol layers, showing that physical-layer jamming assaults may cause transport and application-layer failures to cascade. This research introduces a novel multi-layer jamming detection model based on stacked Long Short-Term Memory (LSTM). With its strong performance in real-time applications for IoT and impressive accuracy in anticipating jamming attempts, the suggested LSTM model is a clear winner. The model undergoes testing on a real-time experimental testbed that simulates different sorts of jamming assaults after being trained on a dataset that has been meticulously selected. A 99.5% accuracy rate for jamming detection and a 99.4% precision rate were produced by the findings. This study provides new insight into the effects of jamming assaults on Internet of Things (IoT) devices and introduces a sophisticated detection model that has the potential to reduce the severity of these attacks.

关键词： Wireless communication Accuracy Quality of service Production Real-time systems Data models Internet of Things Jamming Long short term memory Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

Improved Denoising for Multi-frame Image Restoration with Convolutional Neural Networks

Improved Denoising for Multi-frame Image Restoration with Co...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Hitesh Kalra Kiran Lokesh Maney Omkaresh S. Kulkarni K. Ranjith Singh Gunveen Ahluwalia T. Surulivel Rajan Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India School of Mangement - UG Mangement JAIN (Deemed to be University) Bangalore Karnataka India Department of Computer Science and Engineering (AI & ML) Vishwakarma Institute of Technology Pune India Department of Computer Science Karpagam Academy of Higher Education Coimbatore India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Multi-body photograph restoration is a key application of state-of-the-art image processing. With the improvement of cutting-edge convolutional neural networks (CNNs), it has come to be modern-day viable to repair photos with improved denoising performance. CNNs allow the present-day modern-day complicated non-linear features with high accuracy and fast inference. A CNN-based totally multi-body image healing (MFIR) technique is proposed that is able to seize the spatial correlations between noise and texture in multi-body snapshots. Experiments on benchmark datasets show that our technique achieves overall performance, demonstrating the effectiveness of modern-day CNNs in this challenge. Our approach is powerful to extraordinary multi-frame noise levels and works higher than CNNs with the best unmarried-body entry. Additionally, our proposed technique will be extended to different picture healing responsibilities with diverse today’s corpora.

关键词： Correlation Accuracy Noise reduction Noise Maintenance engineering Benchmark testing Image restoration Convolutional neural networks Noise measurement Noise level

来源：评论

学校读者我要写书评

暂无评论

Error Density-dependent Empirical Risk Minimization

引用

Expert Systems with Applications 2024年 254卷

作者： Chen, Hong Zhang, Xuelin Gong, Tieliang Gu, Bin Zheng, Feng College of Informatics Huazhong Agricultural University Wuhan430070 China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan430070 China Shenzhen Institute of Nutrition and Health Huazhong Agricultural University Shenzhen518000 China Shenzhen Branch Guangdong Laboratory for Lingnan Modern Agriculture Genome Analysis Laboratory of the Ministry of Agriculture Agricultural Genomics Institute at Shenzhen Chinese Academy of Agricultural Sciences Shenzhen518000 China School of Computer Science and Technology Xi'an Jiaotong University Xi'an710049 China School of Artificial Intelligence Jilin University Jilin130012 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Empirical Risk Minimization (ERM) with the squared loss has become one of the most popular principles for designing learning algorithms. However, the existing mean regression models under ERM usually suffer from poor generalization performance due to their sensitivity to atypical observations (e.g., outliers). For alleviating this sensitivity, some strategies have been proposed by utilizing the quantitative relationship of error values with different observations to form robust learning objectives. Instead of focusing on error values, this paper considers the error density to uncover the structure information of observations and proposes a new learning objective, called Error Density-dependent Empirical Risk Minimization (EDERM), for robust regression under complex data environments. Property characterizations and experimental analysis validate the robustness and competitiveness of the proposed EDERM-based learning models. The implemented codes can be found at https://***/zhangxuelincode/EDERM. © 2024 Elsevier Ltd

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

High Quality Factor AlScN Lamb Wave Resonators Using NbN/Al Top Electrodes at Cryogenic Temperature

High Quality Factor AlScN Lamb Wave Resonators Using NbN/Al ...

引用

International Conference on Solid State Sensors and Actuators (TRANSDUCERS)

作者： Zhifang Luo Shuai Shao Peng Dong Haowen Guo Xinbo Zou Jun Li Chengkuo Lee Tao Wu School of Information Science and Technology ShanghaiTech University China Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Department of Electrical & Computer Engineering National University of Singapore Singapore Center for Intelligent Sensors and MEMS National University of Singapore Singapore School of Physical Science and Technology ShanghaiTech University China Shanghai Engineering Research Center of Energy Efficient and Custom AI IC China

Coupling between phonons and qubits provides a solid quantum platform for information transmission and processing. We report the high quality factor (Q a ) aluminum scandium nitride (AlScN) Lamb wave resonators (LWRs) at cryogenic temperature for quantum applications. Superconducting 60 nm NbN/30nm Al serves as top electrodes for ultra-low energy dissipation at around 11 K. Al 0.84 Sc 0.16 N provides a high piezoelectric constant for high electro-mechanical coupling $\left( {{{\text{k}}_{\text{t}}}^{\text{2}}} \right)$ of resonators. Additionally, LWRs allow lithography-defined resonant frequency for flexible multi-frequency phonon sources. The fabricated LWR shows Q a over 6000, and resulting in a record figure-of-merit $\left( {{\text{FoM }} = {\text{ }}{{\text{k}}_{\text{t}}}^{\text{2}}{\text{*}}{{\text{Q}}_{\text{a}}}} \right)$ of 211 for AlScN resonators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

C2RG: Parameter-efficient Adaptation of 3D Vision and Language Foundation Model for Coronary CTA Report Generation

C2RG: Parameter-efficient Adaptation of 3D Vision and Langua...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ye, Zhiyu Sun, Yue Shi, Wei Yang, Bang Wu, Shibin Wang, Hancong Xu, Cheng Zheng, Hairong Wang, Yining Zhang, Tong Shenzhen Institute of Advanced Technology Pengcheng Laboratory Paul C.Lauterbur Research Center for Biomedical Imaging Department of Network Intelligence Shenzhen China University of Chinese Academy of Sciences Beijing China Chinese Academy of Medical Sciences Peking Union Medical College Peking Union Medical College Hospital Department of Radiology Beijing China Sun Yat-sen University School of Computer Science Guangzhou China Pengcheng Laboratory Department of Network Intelligence Shenzhen China Peking University Pengcheng Laboratory Adsplab School of Electronic and Computer Engineering Department of Network Intelligence Shenzhen China Tsinghua University Pengcheng Laboratory Shenzhen International Graduate School Department of Network Intelligence Shenzhen China Shenzhen Institute of Advanced Technology Paul C.Lauterbur Research Center for Biomedical Imaging Shenzhen China

ISBN: (纸本)9798350386226

Medical report generation (MRG) is a challenging yet highly demanding task in the application of multi-modal artificial intelligence in medicine. Typically, training an MRG model requires tens of thousands of labelled radiology images and reports datasets, which could be impractical for most clinical research groups. In this study, we present C2RG, a novel 3D vision and language foundation model tailored for Coronary Computed Tomography Angiography (CTA) Report Generation. Inspired by BLIP-2's architecture, our method integrates a self-supervised pre-trained 3D cardiac vision model (ViT-B) and a general-purpose bilingual foundation model (ChatGLM-6B), with a lightweight querying Transformer (Q-Former). We also introduce a parallel high-resolution feature extractor module and a coronary calcification evaluation loss to simultaneously encode fine-grained 3D features and constrain the accuracy of report generation. We compared our model with six state-of-the-art MRG methods on a clinical dataset with 118 subjects, comprising 453 paired 3D CTA images and radiology reports. Experimental results with extensive ablations show the efficacy of our C2RG. Codes will be open-sourced after the conference. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

A BI-LEVEL ASSESSMENT OF TWITTER IN PREDICTING THE RESULTS OF AN ELECTION: DELHI ASSEMBLY ELECTIONS 2020

arXiv

引用

arXiv 2022年

作者： Singh, Maneet Iyengar, S.R.S. Saxena, Akrati Kaur, Rishemjit Department of Computer Science and Engineering Indian Institute of Technology Ropar India Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands CSIR-Central Scientific Instruments Organisation Chandigarh India Academy of Scientific and Innovative Research Ghaziabad India

Elections are the backbone of any democratic country, where voters elect the candidates as their representatives. The emergence of social networking sites has provided a platform for political parties and their candidates to connect with voters in order to spread their political ideas. Our study aims to use Twitter in assessing the outcome of Delhi Assembly elections held in 2020, using a bi-level approach, i.e., concerning political parties and their candidates. We analyze the correlation of election results with the activities of different candidates and parties on Twitter, and the response of voters on them, especially the mentions and sentiment of voters towards a party. The Twitter profiles of the candidates are compared both at the party level as well as the candidate level to evaluate their association with the outcome of the election. We observe that the number of followers and the replies to the tweets of candidates are good indicators for predicting actual election outcome. However, we observe that the number of tweets mentioning a party and the sentiment of voters towards the party shown in tweets are not aligned with the election result. We also use machine learning models on various features such as linguistic, word embeddings and moral dimensions for predicting the election result (win or lose). The random forest model using tweet features provides promising results for predicting if the tweet belongs to a winning or losing candidate. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Certain Electroenchaphalography Signal Analysis for Artifact Removal Using Multiwavelet Transform

Certain Electroenchaphalography Signal Analysis for Artifact...

引用

Advanced Technologies in Intelligent Control, Environment, Computing & Communication engineering (ICATIECE), International Conference on

作者： Basavesha D Madhumala R B Prashanth Venkatareddy Sapna Kadakadiyavar Piyush Kumar Pareek Surabhi K R Department of Computer Science & Engineering Shridevi Institute of Engineering & Technology Bengaluru Department of ISE Dayananda Sagar Academy of Technology and Management Bangalore Department of Electrical & Electronics Engineering Nitte Meenakshi Institute of Technology Bengaluru Department of Electronics and communication Sambhram Institute of Technology Bangalore Department of Artificial Intelligence & Machine Learning Nitte Meenakshi Institute of Technology Bengaluru Department of Information Science and Engineering Dayananda Sagar Academy of Technology and Management Bangalore

ISBN: (纸本)9781665493970

This work presents an efficient strategy for eliminating mixed artifacts that are present in electroencephalogram recordings. All three categories of recordings are suitable candidates for use of the approach. The presence of the noise source makes it more challenging to do an analysis of the EEG and get clinical information. This is because the EEG is being measured in a noisy environment. EEG signals are biological signals that take place in the temporal domain and are multidimensional, non-stationary, and irreproducible. EEG signals are also known as electroencephalogram signals. Electroencephalogram signals are sometimes often referred to as EEG signals. This suggests that the statistical qualities of these people do not remain the same over time as shown by the fact that this is the case. It is anticipated that it will offer information on the activities that are taking place at the level of the ensemble of excitatory pyramidal neurons, with a temporal resolution scale of milliseconds. This prediction is based on the fact that the scale measures time in milliseconds. It is highly difficult to derive any useful information from scalp EEG since it includes a substantial amount of background noise and artifacts, and the particular area from which it originates cannot be determined. As a result of these factors, it is quite difficult to analyze scalp EEG. This is because the background noise and artifacts might make it difficult to determine the source of the signal. As a result of this, it is of the utmost importance to develop specific methods for reducing the occurrence of artifacts in EEG recordings, such as the one in question. These methodologies need to be created as quickly as time permits. In this piece of research, we suggest making use of the Multiwavelet transform to clean up the EEG data and get rid of any artifacts that could be present. Following the use of the GHM algorithm, which cleans up the noisy signal produced by the Multiwavelet transform, th

关键词： Time series analysis Scalp Transforms Electroencephalography Time measurement Recording Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Shallow Sea Bathymetry Mapping from Satellite SAR Observations Using Deep Learning

Shallow Sea Bathymetry Mapping from Satellite SAR Observatio...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Yide Cui Sheng Wang Yanlei Du Yang Yu Guihong Liu Wentao Ma Junjun Yin Xiaofeng Yang Key Laboratory of Remote Sensing and Digital Earth Aerospace Information Research Institute Chinese Academy of Sciences Beijing China National Key Laboratory of Microwave Imaging Aerospace Information Research Institute Chinese Academy of Sciences Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Institute of Space Earth Science Nanjing University Suzhou China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

This study proposes a deep-learning model to map underwater topography from spaceborne synthetic aperture radar (SAR) images. For the model development, 18 high-resolution Sentinel-1 dual-polarization SAR images covering the southern Cape Cod area from 2014 to 2022 are collected, among which twelve images were used for model training, while the rest were used for testing. In order to facilitate the model learning complex and nonlinear relations among various parameters, the model input is designed to consist of 8 variables, which involve radar backscatter coefficient, radar observation geometry, geography information and marine dynamic environmental parameters. The deep learning network consists of a convolutional layer, two residual blocks, and a fully connected layer, facilitating feature extraction and regression prediction. The final model performances in retrieving shallow water depth are shown as follows: For the training set, the model achieved a root mean square error (RMSE) of 1.02 m and a relative error of 4.32%, with the maximum detectable water depth reaching 48.17 m. For testing, the best performance of the model presented with an RMSE of 1.59 m and a relative error of 5.29%, while the worst performance corresponds to an RMSE of 4.53 m with a relative error of 15.61%. Thus, the proposed model has the capacity of detecting the shallow water depth up to 50 meters with high precision.

关键词： Deep learning Training Spaceborne radar Sentinel-1 Radar imaging Surfaces Radar polarimetry Water resources Synthetic aperture radar Testing

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：