检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Ozdemir, Firat Lafci, Berkan Deán-Ben, Xosé Luís Razansky, Daniel Perez-Cruz, Fernando Swiss Data Science Center ETH Zurich and EPFL Zurich Switzerland Institute of Pharmacology and Toxicology Institute for Biomedical Engineering Faculty of Medicine University of Zurich Switzerland Institute for Biomedical Engineering Department of Information Technology and Electrical Engineering ETH Zurich Switzerland Institute for Machine Learning Department of Computer Science ETH Zurich Switzerland

Optoacoustic (OA) imaging is based on excitation of biological tissues with nanosecond-duration laser pulses followed by subsequent detection of ultrasound waves generated via light-absorption-mediated thermoelastic expansion. OA imaging features a powerful combination between rich optical contrast and high resolution in deep tissues. This enabled the exploration of a number of attractive new applications both in clinical and laboratory settings. However, no standardized datasets generated with different types of experimental set-up and associated processing methods are available to facilitate advances in broader applications of OA in clinical settings. This complicates an objective comparison between new and established data processing methods, often leading to qualitative results and arbitrary interpretations of the data. In this paper, we provide both experimental and synthetic OA raw signals and reconstructed image domain datasets rendered with different experimental parameters and tomographic acquisition geometries. We further provide trained neural networks to tackle three important challenges related to OA image processing, namely accurate reconstruction under limited view tomographic conditions, removal of spatial undersampling artifacts and anatomical segmentation for improved image reconstruction. Specifically, we define 44 experiments corresponding to the aforementioned challenges as benchmarks to be used as a reference for the development of more advanced processing methods. © 2022, CC BY-NC-SA.

关键词： Photoacoustic effect

来源：评论

学校读者我要写书评

暂无评论

Overview of the Tenth Dialog System Technology Challenge: DSTC10

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

Cluster-Based Oversampling with Area Extraction from Representative Points for Class Imbalance Learning

SSRN

引用

SSRN 2023年

作者： Farou, Zakarya Wang, Yizhi Horváth, Tomáš ELTE – Eötvös Loránd University Faculty of Informatics Institute of Industry-Academia Innovation Department of Data Science and Engineering Pázmány Péter sétány 1/C BudapestH-1117 Hungary Pavol Jozef Šafárik University Faculty of Science Institute of Computer Science Jesenná 5 Košice040 01 Slovakia

Class imbalance learning is challenging in various domains where training datasets exhibit disproportionate samples in a specific class. Resampling methods have been used to adjust the class distribution, but they often have limitations for small disjunct minority subsets. This paper introduces AROSS, an adaptive cluster-based oversampling approach that addresses these limitations. AROSS utilizes an optimized agglomerative clustering algorithm with the Cophenetic Correlation Coefficient and the Bayesian Information Criterion to identify representative areas of the minority class. Safe and half-safe areas are obtained using an incremental k-Nearest Neighbor strategy, and oversampling is performed with a truncated hyperspherical Gaussian distribution. Experimental evaluations on 70 binary datasets demonstrate the effectiveness of AROSS in improving class imbalance learning performance, making it a promising solution for mitigating class imbalance challenges, especially for small disjunct minority subsets. © 2023, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Hidformer: A Frequency-Domain Transformer for High-Resolution Image Deblurring in IoT Devices

引用

IEEE Internet of Things Journal 2025年

作者： Zheng, Xianqiu Li, Yujian Chen, Ruoyu Zhang, Leqian Li, Gen Liu, Baolong Guilin University of Electronic Technology School of Computer Science and Information Security Jinji Road Guangxi Guilin541004 China Shanxi Institute of Technology Department of Big Data and Intelligent Engineering Xueyuan Road Shanxi Yangquan045000 China Guilin University of Electronic Technology School of Artificial Intelligence Jinji Road Guangxi Guilin541004 China

Image deblurring is a critical technology for enhancing the visual perception capabilities of Internet of Things (IoT) devices, but challenges such as motion blur and defocus blur continue to degrade image quality. Although Convolutional Neural Networks (CNNs) have achieved progress in image deblurring tasks, their limited receptive fields and static filters result in performance bottlenecks when processing high-resolution images and modeling long-range dependencies. Transformers, while demonstrating remarkable success in vision tasks, suffer from computational complexity that increases quadratically with spatial resolution, making them less suitable for resource-constrained IoT environments. To address these challenges, we propose Hidformer, a novel architecture that combines frequency-domain processing with Transformer structures to efficiently capture multi-scale representations and model long-range dependencies, particularly for high-resolution image deblurring. Inspired by the convolution theorem, we introduce the Frequency-Domain Self-Attention (FDSA) module, which leverages Fast Fourier Transform (FFT) to map images from the spatial-domain to the frequency-domain and computes attention maps efficiently through the Hadamard product, significantly reducing spatial and temporal complexity. To further optimize performance, we propose SIGA, a simplified variant of the Gated Linear Unit (GLU) that replaces the computationally expensive Gaussian Error Linear Unit (GELU) while retaining nonlinearity. Additionally, we design an Optimal Cutoff-Frequency Selection Algorithm (OCSA) to improve the performance of high-pass filters. Extensive experiments on GoPro dataset demonstrate that Hidformer outperforms state-of-the-art methods, especially in detail and texture recovery. With only 16.3M parameters and an inference time of 0.11 seconds, Hidformer achieves a balance between accuracy and efficiency, highlighting its potential for deployment in IoT devices, particularly i

关键词： Cutoff frequency

来源：评论

学校读者我要写书评

暂无评论

Defect Detection in Steel Castings Using Deep Learning with X-ray Images

Defect Detection in Steel Castings Using Deep Learning with ...

引用

IEEE International Conference on Signal Processing, Computing and Control (ISPCC)

作者： K. Kalaiarasi V. Ramachandran S. Karuppaiah M. Senthil Murugan M. Thirunavukkarasu M. Durairaj Department of ECE Saveetha School of Engineering Saveetha Institute of Technical and Medical Sciences Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Saveetha Engineering College Chennai Tamil Nadu India Department of ECE R.M.D Engineering College Chennai Tamil Nadu India Department of ECE St. Joseph’s Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Biomedical Engineering Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798331538934

ISBN: (纸本)9798331538941

For product reliability and workplace safety, flaw detection in steel castings is very important. The study presents a novel deep learning approach that can employ X-ray images to detect flaws in steel castings. With the help of a custom convolutional neural network called SteelNet, cracks, porosity, and inclusions can be accurately located and classified. In this approach, modern model characteristics such as attention processes and multi-scale detection are combined with domainspecific preprocessing methods, including noise reduction and contrast enhancement. Using transfer learning and data augmentation reduces the issue of data shortage and increases the generalizability of the model. The proposed method surpasses the state-of-the-art in defect localization using a varied dataset of X-ray images from steel castings, with a classification accuracy of 98.7 percent, a mean Average Precision (mAP) of 95.7 percent, and an Intersection over Union (IoU) of 92.0 percent. This technology enhances quality assurance in industrial operations by automating the process of defect identification and reduces the requirement for human inspection.

关键词： Location awareness Deep learning Casting Accuracy Quality assurance Transfer learning Inspection Safety Steel X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Context Modeling Network for Landmark Recognition

Hierarchical Context Modeling Network for Landmark Recogniti...

引用

IEEE International Conference on data Mining (ICDM)

作者： Xing Bao Huan Zheng Zhao Zhang Zhengjun Zha Meng Wang School of Information Science and Technology University of Science and Technology of China Hefei China Aerospace Information Research Institute Suzhou China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China

Landmark recognition stands as a prominent classification challenge within the domain of vision and perception, involving the identification and localization of landmarks in images. However, existing landmark recognition methods often fall short in delivering satisfactory performance. A critical issue lies in the lack of simultaneous exploration of local, regional, and global modeling. Intuitively, the local details, regional features, and global structure within an image, especially of a building, significantly contribute to landmark recognition. To address this issue, we propose a novel approach, termed Hierarchical Context Modeling Network (HCMNet), for landmark recognition. In our methodology, we introduce a Hierarchical Context Modeling Block (HCMB) designed with a triplet-branch structure to model image context in a hierarchical manner. These branches consist of the local branch, which leverages a convolutional layer to capture local details, the regional branch focused on extracting regional features through large-kernel asymmetrical convolutional layers, and the global branch aims at encompassing the broader context by incorporating channel attention. To enhance the modeling capacity, we assemble multiple HCMBs into the HCMNet, creating a hierarchical structure. Comprehensive experiments validate the efficacy of the proposed HCMNet for landmark recognition, showcasing its superior performance compared to current methods. The proposed hierarchical context modeling approach proves instrumental in capturing the intricate features essential for accurate landmark recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrated Gradients Demystified: An MRI Case Study on Aβ-T Protein Localization

Integrated Gradients Demystified: An MRI Case Study on Aβ-T...

引用

Metrology for Extended Reality, Artificial Intelligence and Neural engineering (MetroXRAINE), IEEE International Conference on

作者： Giorgio Dolci Cristian Morasso Federica Cruciani Lorenza Brusini Lorenzo Pini Vince D. Calhoun Ilaria Boscolo Galazzo Gloria Menegaz Dept. of Engineering for Innovation Medicine University of Verona Verona Italy Dept. of Computer Science University of Verona Verona Italy Padua Neuroscience Center University of Padua Padua Italy Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University Georgia Institute of Technology Emory University Atlanta GA USA

ISBN: (数字)9798350378009

ISBN: (纸本)9798350378016

Explainability in Artificial Intelligence is gaining increasing importance, especially in critical fields. In biomedical applications, attribution maps are particularly relevant for their inherent spatial localization property. Features that are relevant for a given task (e.g., classification of cases versus controls) can then be associated to specific regions, revealing disease-specific modulations and enabling ad-hoc post-hoc validation. Among these, baseline-dependent methods require a neutral image (called baseline) for computing the feature importance. The choice of the baseline is critical in that it determines the relevance map. In this work, we focused on a classification task, that is, subject stratification based on the amyloid-β and τ status in controls and patients in the Alzheimer's disease continuum, and employed Integrated Gradients to extract the attribution maps. This allowed identifying relevant brain regions driving the classification. Aware of the dependence of the outcomes from the chosen baseline, post-hoc statistical analysis was performed for validating the results confirming their plausibility. This puts forth the need to systematically assess the impact of the baseline for the correct interpretation of the corresponding outcomes.

关键词： Proteins Location awareness Protein engineering Statistical analysis Magnetic resonance imaging Neural engineering Modulation Metrology Feature extraction Reliability

来源：评论

学校读者我要写书评

暂无评论

TLDR: Traffic Light Detection using Fourier Domain Adaptation in Hostile WeatheR

arXiv

引用

arXiv 2024年

作者： Gakhar, Ishaan Guha, Aryesh Gupta, Aryaman Agarwal, Amit Toshniwal, Durga Verma, Ujjwal Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education India Department of Electrical and Electronics Engineering Manipal Institute of Technology Manipal Academy of Higher Education India Department of Computer Science Engineering Manipal Institute of Technology Manipal Academy of Higher Education India Enterprise Analytics & Data Science Artificial Intelligence Center of Excellence Wells Fargo International Solutions Private Limited Center For Transportation Systems Indian Institute of Technology Roorkee India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education India

The scarcity of comprehensive datasets in the traffic light detection and recognition domain and the poor performance of state-of-the-art models under hostile weather conditions present significant challenges. To address these issues, this paper proposes a novel approach by merging two widely used datasets, LISA and S2TLD. The merged dataset is further processed to tackle class imbalance, a common problem in this domain. This merged dataset becomes our source domain. Synthetic rain and fog are added to the dataset to create our target domain. We employ Fourier Domain Adaptation (FDA) to create a final dataset with a minimized domain gap between the two datasets, helping the model trained on this final dataset adapt to rainy and foggy weather conditions. Additionally, we explore Semi-Supervised Learning (SSL) techniques to leverage the available data more effectively. Experimental results demonstrate that models trained on FDA-augmented images outperform those trained without FDA across confidence-dependent and independent metrics, like mAP50, mAP50-95, Precision, and Recall. The best-performing model, YOLOv8, achieved a Precision increase of 5.1860%, Recall increase of 14.8009%, mAP50 increase of 9.5074%, and mAP50- 95 increase of 19.5035%. On average, percentage increases of 7.6892% in Precision, 19.9069% in Recall, 15.8506% in mAP50, and 23.8099% in mAP50-95 were observed across all models, highlighting the effectiveness of FDA in mitigating the impact of adverse weather conditions on model performance. These improvements pave the way for real-world applications where reliable performance in challenging environmental conditions is critical. Impact Statement-This research addresses a critical challenge in autonomous driving systems-poor performance in adverse weather conditions-by introducing a novel method using Fourier Domain Adaptation (FDA). The FDA-enhanced models significantly improve the detection of traffic lights in rain and fog, which has broad implicatio

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

What kind of person wins the turing award?

arXiv

引用

arXiv 2021年

作者： Shangguan, Zhongkai Zheng, Zihe Luo, Jiebo Department of Electrical and Computer Engineering Goergen Institute for Data Science Department of Computer Science University of Rochester RochesterNY14627 United States

computer science has grown rapidly since its inception in the 1950s and the pioneers in the field are celebrated annually by the A.M. Turing Award. In this paper, we attempt to shed light on the path to influential computer scientists by examining the characteristics of the 72 Turing Award laureates. To achieve this goal, we build a comprehensive dataset of the Turing Award laureates and analyze their characteristics, including their personal information, family background, academic background, and industry experience. The FP-Growth algorithm is used for frequent feature mining. Logistic regression plot, pie chart, word cloud and map are generated accordingly for each of the interesting features to uncover insights regarding personal factors that drive influential work in the field of computer science. In particular, we show that the Turing Award laureates are most commonly white, male, married, United States citizen, and received a PhD degree. Our results also show that the age at which the laureate won the award increases over the years;most of the Turing Award laureates did not major in computer science;birth order is strongly related to the winners' success;and the number of citations is not as important as one would expect. © 2021, CC0.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Product states optimize quantum p-spin models for large p

arXiv

引用

arXiv 2023年

作者： Anschuetz, Eric R. Gamarnik, David Kiani, Bobak T. Institute for Quantum Information and Matter Caltech Walter Burke Institute for Theoretical Physics Caltech MIT Center for Theoretical Physics MIT United States Operations Research Center Statistics and Data Science Center Sloan School of Management MIT United States John A. Paulson School of Engineering and Applied Sciences Harvard Department of Electrical Engineering and Computer Science MIT United States

We consider the problem of estimating the maximal energy of quantum p-local spin glass random Hamiltonians, the quantum analogues of widely studied classical spin glass models. Denoting by E∗(p) the (appropriately normalized) maximal energy in the limit of a large number of qubits n, we show that E∗(p) approaches √2 log 6 as p increases. This value is interpreted as the maximal energy of a much simpler so-called Random Energy Model, widely studied in the setting of classical spin glasses. Our most notable and (arguably) surprising result proves the existence of near-maximal energy states which are product states, and thus not entangled. Specifically, we prove that with high probability as n → ∞, for any E ∗(p) there exists a product state with energy ≥ E at sufficiently large constant p. Even more surprisingly, this remains true even when restricting to tensor products of Pauli eigenstates. Our approximations go beyond what is known from monogamy-of-entanglement style arguments—the best of which, in this normalization, achieve approximation error growing with n. Our results not only challenge prevailing beliefs in physics that extremely low-temperature states of random local Hamiltonians should exhibit non-negligible entanglement, but they also imply that classical algorithms can be just as effective as quantum algorithms in optimizing Hamiltonians with large locality—though performing such optimization is still likely a hard problem. Our results are robust with respect to the choice of the randomness (disorder) and apply to the case of sparse random Hamiltonian using Lindeberg’s interpolation method. The proof of the main result is obtained by estimating the expected trace of the associated partition function, and then matching its asymptotics with the extremal energy of product states using the second moment method. Copyright © 2023, The Authors. All rights reserved.

关键词： Hamiltonians

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：