检索结果-内蒙古大学图书馆

3rd international Conference on Machine Vision and Augmented Intelligence, MAI 2023

ISBN: (纸本)9789819743582

The proceedings contain 76 papers. The special focus in this conference is on Machine Vision and Augmented Intelligence. The topics include: Survey on Robustness of Deep Learning Techniques on Adversarial Attacks in WBAN;synergizing Collaborative and Content-Based Filtering for Enhanced Movie Recommendations;exploring Transformer-Based Approaches for Hyperspectral image Classification: A Comparative analysis;deep Learning for Cognitive Task and Seizure Classification with Hilbert–Huang Transform and Variational Mode Decomposition;tracking of Ship and Plane in Satellite Videos Using a Convolutional Regression Network with Deep Features;Tumor Detection and analysis from Brain MRI images Using Deep Learning;software Maintenance Prediction Using Stack Ensemble Deep Learning Algorithms;resource Allocation in 6G Network for High-Speed Train Using D2D Outband Communication;controlling the Band-to-Band Tunneling Effect in Charge Plasma Based Dopingless Transistor;Comparison of Different CIC Filter Architectures on the Basis of a Novel Parameter Called Noise Factor for Sigma-Delta Based ADCs;the Scientific analysis on Effective Yoga Posture Recognition Techniques;impact of Gamma Rays on Emerging Devices for Photonic Applications;shaft Rotation Monitoring Using Radar signal processing and Wavelet Transform;gysel Power Divider Miniaturization Using an Inter-Digital Capacitor-Based Slow-Wave Structure;noise Estimation and Removal in Fundus images Using Pyramid Real image Denoising Network;evaluation of Hybrid Encryption Method to Secure Healthcare Data;multimodal Face Recognition System Using Hybrid Deep Learning Feature;Classification of Copy and Move image by Using HELM-FSK Method: An Efficient Approach;analysis of Energy Efficient Smart Home Based on IoT System;role of Explainable Artificial Intelligence Approaches in Cybersecurity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A deep neural network approach to compact source removal

引用

ASTRONOMY & ASTROPHYSICS 2025年 696卷

作者： Madarasz, M. Marton, G. Gezer, I. Lehner, S. Roquette, J. Audard, M. Hernandez, D. Dionatos, O. HUN REN Hungarian Res Network Res Ctr Astron & Earth Sci Konkoly Observ Konkoly Thege Mikl Ut 15-17 H-1121 Budapest Hungary MTA Ctr Excellence CSFK Konkoly Thege Mikl ut 15-17 H-1121 Budapest Hungary Univ Linz Altenberger Str 69 A-4040 Linz Austria Johannes Kepler Univ Linz Inst Machine Learning Altenberger Str 69 A-4040 Linz Austria Univ Geneva Dept Astron Chemin Pegasi 51 CH-1290 Versoix Switzerland Univ Vienna Dept Astrophys Turkenschanzstr 17 A-1180 Vienna Austria Nat Hist Museum Vienna Burgring 7 A-1010 Vienna Austria

Context. Analyzing extended emission in photometric observations of star-forming regions requires maps free from compact foreground, embedded, and background sources, which can interfere with various techniques used to characterize the interstellar medium. Within the framework of the NEMESIS project, we applied machine-learning techniques to improve our understanding of the star formation timescales, which involves the unbiased analysis of the extended emission in these regions. Aims. We present a deep learning-based method for separating the signals of compact sources and extended emission in photometric observations made by the Herschel Space Observatory, facilitating the analysis of extended emission and improving the photometry of compact sources. Methods. Central to our approach is a modified U-Net architecture with partial convolutional layers. This method enables effective source removal and background estimation across various flux densities, using a series of partial convolutional layers, batch normalization, and ReLU activation layers within blocks. Our training process utilized simulated sources injected into Herschel images, with controlled flux densities against known backgrounds. A dynamic, signal-to-noise ratio (S/N)-based adaptive masking system was implemented to assess how prominently a compact source stands out from the surrounding background. Results. The results demonstrate that our method can significantly improve the photometric accuracy in the presence of highly fluctuating backgrounds. Moreover, the approach can preserve all characteristics of the images, including the noise properties. Conclusions. The presented approach allows users to analyze extended emission without the interference of disturbing point sources or perform more precise photometry of sources located in complex environments. We also provide a Python tool with tutorials and examples to help the community effectively utilize this method.

关键词： methods: data analysis techniques: image processing techniques: photometric ISM: structure

来源：评论

学校读者我要写书评

暂无评论

SAM-OCTA2: Layer Sequence OCTA Segmentation with Fine-tuned Segment Anything Model 2

SAM-OCTA2: Layer Sequence OCTA Segmentation with Fine-tuned ...

引用

2025 IEEE international Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Chen, Xinrun Wang, Chengliang Ning, Haojian Zhang, Mengzhan Shen, Mei Li, Shiying College of Computer Science Chongqing University Chongqing China Department of Ophthalmology Xiang'an Hospital of Xiamen University Xiamen China

ISBN: (纸本)9798350368741

Segmentation of indicated targets aids in the precise analysis of optical coherence tomography angiography (OCTA) samples. Existing segmentation methods typically perform on 2D projection targets, making it challenging to capture the variance of segmented objects through the 3D volume. To address this limitation, the low-rank adaptation technique is adopted to fine-tune the Segment Anything Model (SAM) version 2, enabling the tracking and segmentation of specified objects across the OCTA scanning layer sequence. To further this work, a prompt point generation strategy in frame sequence and a sparse annotation method to acquire retinal vessel (RV) layer masks are proposed. This method is named SAM-OCTA2 and has been experimented on the OCTA-500 dataset. It achieves state-of-the-art performance in segmenting the foveal avascular zone (FAZ) on regular 2D en-face and effectively tracks local vessels across scanning layer sequences. The code is available at: https://***/ShellRedia/SAM-OCTA2. © 2025 IEEE.

关键词： fine-tuning image segmentation OCTA segment anything model sparse annotation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Breast Cancer Molecular Biomarker Classification: A Novel Two-Stage Machine Learning Pipeline for Accurate Histological analysis of Whole Slide images

Enhanced Breast Cancer Molecular Biomarker Classification: A...

引用

2025 IEEE international Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Aboudessouki, A. Ali, Kh.M. Alksas, A. Elsharkawy, M. Rahma, M. Abo Ghazal, M. Mekky, N. El-Daydamony, E. Gondim, D. El-Baz, A. BioImaging Laboratory Bioengineering Department University of Louisville United States Pathology Department Faculty of Medicine Mansoura University Egypt Mansoura University Hospital Mansoura University Egypt Electrical Computer and Biomedical Engineering Department Abu Dhabi University United Arab Emirates Department of Information Technology Faculty of Computers and Information Mansoura University Egypt Department of Pathology and Laboratory Medicine University of Louisville LouisvilleKY United States

ISBN: (纸本)9798350368741

Breast cancer, a prevalent and diverse form of cancer, is characterized by unique clinicopathologic features. Accurate classification of its molecular subtype, essential for targeted treatment and improved survival rates, relies on testing molecular biomarkers such as estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and Ki67 antigen. This study introduces an innovative two-stage machine learning pipeline for breast cancer PR molecular biomarker classification using whole slide immunohistochemistry images. Our approach consists of two specialized stages. In the first stage, a watershed algorithm segments the Cells from the input image. Morphological and statistical features extracted from these segments are then used by machine learning classifiers to distinguish between tumor and nontumor tissues [1]-[3]. The second stage focuses on the tumor tissues that were identified in the first stage, extracting texture and appearance features to classify them into positive or negative biomarker responses, again using machine learning classifiers [4], [5]. This method not only automates the classification of PR biomarkers in tumor regions but also generates a detailed image map for each cell in the Whole Slide image (WSI). By doing so, it can determine whether the tissue represents tumor cells and whether the tumor tissue exhibits positive or negative PR status. The results show the ability of our machine learning-based approach to augment pathologists' diagnostic capabilities, offering significant advancements in the automated classification of histopathological images. © 2025 IEEE.

关键词： Breast cancer Histopathology Immunohistochemistry Machine Learning Marker-based Watershed Segmentation Molecular biomarker Status Molecular biomarkers Tissue classification Tumor Detection Watershed Segmentation

来源：评论

学校读者我要写书评

暂无评论

KLFormer: Karhunen-Loève Transform for Robust 3D Human Pose Estimation

KLFormer: Karhunen-Loève Transform for Robust 3D Human Pose...

引用

2025 IEEE international Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Zeng, Xin Luo, Haonan Wang, Zihang Li, Sijia Zhang, Leyu Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798350368741

In the scope of 3D human pose estimation, the task encompasses estimating the 3D positions of key skeletal points (i.e., wrists, elbows, and knees) from a 2D image or video sequence. This technology demonstrates widespread applicability across diverse domains, encompassing domains such as kinematic analysis, virtual reality, augmented reality, and medical imaging analysis. The common approach is divided into two stages: i) 2D Keypoint Detection: Detecting 2D keypoints from images. ii) 2D-to-3D Lifting: Converting 2D keypoints into 3D coordinates. Present research predominantly concentrates on Stage 2 and leverages sophisticated deep learning architectures, notably Transformers, yet two key challenges exist: i) suboptimal performance in predicting local details;ii) susceptibility to noise interference. In this work, we propose a time-principal component fusion model with limb segment property tracking is proposed to address the challenges above. By integrating time-domain features with principal components extracted through the Karhunen-Loève Transform (KLT), the model aims to address challenges related to feature extraction and noise reduction. Furthermore, to address the issue of suboptimal performance in predicting local details, we devise a property transformer to track the lengths of limb segments and predict the fixed property. Extensive experiments demonstrate that KLFormer showcases state-of-the-art performance on the standard benchmark dataset, Human3.6M. © 2025 IEEE.

关键词： 3D Human Pose Estimation Karhunen-Loève Transform Principal Component analysis Transformer

来源：评论

学校读者我要写书评

暂无评论

TROI: Cross-Subject Pretraining with Sparse Voxel Selection for Enhanced fMRI Visual Decoding

TROI: Cross-Subject Pretraining with Sparse Voxel Selection ...

引用

2025 IEEE international Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Wang, Ziyu Pan, Tengyu Li, Zhenyu Wu, Ji Li, Xiuxing Wang, Jianyong Department of Computer Science and Technology Tsinghua University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9798350368741

fMRI (functional Magnetic Resonance Imaging) visual decoding involves decoding the original image from brain signals elicited by visual stimuli. This often relies on manually labeled ROIs (Regions of Interest) to select brain voxels. However, these ROIs can contain redundant information and noise, reducing decoding performance. Additionally, the lack of automated ROI labeling methods hinders the practical application of fMRI visual decoding technology, especially for new subjects. This work presents TROI (Trainable Region of Interest), a novel two-stage, data-driven ROI labeling method for cross-subject fMRI decoding tasks, particularly when subject samples are limited. TROI leverages labeled ROIs in the dataset to pretrain an image decoding backbone on a cross-subject dataset, enabling efficient optimization of the input layer for new subjects without retraining the entire model from scratch. In the first stage, we introduce a voxel selection method that combines sparse mask training and low-pass filtering to quickly generate the voxel mask and determine input layer dimensions. In the second stage, we apply a learning rate rewinding strategy to fine-tune the input layer for downstream tasks. Experimental results on the same small sample dataset as the baseline method for brain visual retrieval and reconstruction tasks show that our voxel selection method surpasses the state-of-the-art method MindEye2 with an annotated ROI mask. © 2025 IEEE.

关键词： Computational neuroscience multi-modal learning region of interest analysis small sample learning

来源：评论

学校读者我要写书评

暂无评论

Effects of visual rotation axis and clockwise/counterclockwise directions on circular vection in virtual reality 24

Effects of visual rotation axis and clockwise/counterclockwi...

引用

2024 international Conference on Virtual Reality, image and signal processing, ICVISP 2024

作者： Xu, Xiaotian Song, Zhe Zhang, Kexin Xu, Yan Zhang, Yuankun Fan, Xiaoya Pu, Fang Key Laboratory of Human Motion Analysis and Rehabilitation Technology of the Ministry of Civil Affairs Beihang University Beijing China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian University of Technology Liaoning Dalian China State Key Laboratory of Virtual Reality Technology and System Beihang University Beijing China

ISBN: (纸本)9798400710926

Vection, an illusion of self-motion induced by visual stimulus frequently experienced in virtual reality, significantly impacts user experiences in gaming, driving simulation, and rehabilitation training. User often experience circular vection, an illusion of self-rotation. However, the effects of visual rotation axes and rotation directions on circular vection remain elusive. We employ a 3 (rotation axis: sagittal, coronal, vertical) × 2 (rotation direction: clockwise, counterclockwise) repeated-measures design. Twenty participants were recruited. They were exposed to a virtual visual rotating drum at 60 °/s to induce circular vection. The real-time estimation of perceived self-motion rotation velocity (PSRV) was obtained. Results indicated that during the 30-second constant rotation, the group-level PSRV showed an initial rapid increase followed by a slower rise. A significant interaction effect between rotation axis and direction was revealed. The rotation direction showed no significant effect on PSRV under sagittal and vertical conditions. However, under coronal condition, the PSRV was significantly higher when rotating counterclockwise, compared to rotation clockwise. In addition, when rotating counterclockwise, the highest PSRV appeared under sagittal condition, with the lowest under the coronal condition and the middle under the vertical condition. These findings provide valuable insights for designing VR scenarios with better user experience by vection manipulation. © 2024 Copyright held by the owner/author(s).

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Anima2: Cross-Species Animal Animation through image-to-Video Synthesis with Subject Alignment

Anima2: Cross-Species Animal Animation through Image-to-Vide...

引用

2025 IEEE international Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Xu, Yuanfeng Chen, Yuhao Huang, Zhongzhan He, Zijian Wang, Guangrun Lin, Liang Sun Yat-sen University China Peng Cheng Laboratory China Guangdong Key Laboratory of Big Data Analysis and Processing China

ISBN: (纸本)9798350368741

Recent video editing advancements rely on accurate pose sequences to animate human actors. However, these efforts are not suitable for cross-species animation due to pose misalignment between species (for example, the poses of a cat differ greatly from that of a pig due to their distinct body structures). In this paper, we present Anima2, a zero-shot diffusion-based video generator to address this issue, aiming to accurately ANIMAte ANIMAls while preserving the background. The key technique involves two-fold subject alignment. First, we improve appearance feature extraction by integrating a Laplacian detail booster and a prompt-tuning identity extractor. They capture essential appearance information, including identity and fine details. Second, we align shape features and address conflicts from differing animals by introducing a scale-information remover and an adaptive rescaling module. They both enhance subject alignment for accurate cross-species animation. Additionally, we introduce two high-quality animal video datasets with diverse species to benchmark cross-species animation. Trained on these extensive datasets, our model directly generates videos with accurate movements, consistent appearances, and high-fidelity frames, eliminating the need for test-time training. Extensive experiments demonstrate our method's superiority in cross-species animation, showcasing robust adaptability and generality. © 2025 IEEE.

关键词： cross-species subject alignment video editing

来源：评论

学校读者我要写书评

暂无评论

Multi-class Histology image analysis Using Handcrafted Texture and Colour Features for Breast Abnormality Classification 11th

Multi-class Histology Image Analysis Using Handcrafted Textu...

引用

11th international symposium on Applied Computing for Software and Smart Systems, ACSS 2024

作者： Mohanta, Anindita Roy, Sourav Dey Nath, Niharika Bhowmik, Mrinal Kanti Suryamaninagar Tripura Agartala799022 India Biological and Chemical Sciences Department New York Institute of Technology New YorkNY10023 United States

ISBN: (纸本)9789819797615

Breast cancer is one of the most common cancers among women worldwide, affecting around 10% of all women. Its fatality rate is extraordinarily high when compared to other cancer types. Histopathological analysis is one of the reliable methods for identifying breast cancer with confidence. But it's a highly specialized, time-consuming procedure that depends on the pathologist's experience. An automatic computerized histopathological image classification model can assist doctors and pathologists for early diagnosis. But most of the work is based on the non-interpretable black box model for feature selection tasks which is not very encouraging in the medical field. To introduce features interpretability in histopathological imaging, handcrafted features analysis is important first. In this paper, a novel hybrid computer-aided multi-class classification framework is proposed for predicting breast abnormality using histopathological images and handcrafted features. The proposed framework uses traditional handcrafted features (i.e. texture features, colour features, and fusion of texture and colour features) and a deep neural network (DNN) for breast cancer abnormality classification in order to facilitate the screening process for early diagnosis. The DNN classifier is trained using the features that were extracted using the handcrafted methods for two-class and multi-class classifications. The experimental results show that the use of handcrafted texture features had a better prediction performance in histopathological image classification as compared to the other handcrafted features for breast abnormality prediction. Using texture features with a DNN classifier, we achieved average values for accuracy, recall, precision and F1-score of 73%, 79%, 81% and 82% respectively for multi-class classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Comparative analysis of Denoising Techniques in image processing 3rd

A Comparative Analysis of Denoising Techniques in Image Proc...

引用

3rd international Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Jaiswal, Nitesh Kumar Srivastava, Subodh Mahto, Manipuran Department of Electronics and Communication Engineering NIT Patna Bihar Patna India

ISBN: (纸本)9789819743582

This paper presents the results obtained from an experimental study on the effectiveness of a noise reduction technique applied to medical images. This study compares the effectiveness of various noise-removal filters in order to determine which is the most efficient. Mode, median, Gaussian, adaptive median, non-local mean, wavelet, and deep learning-based denoising convolutional neural network (CNN) filters were used. This paper seeks to demonstrate experimental results on two types of noisy input images used: impulse noise and Gaussian noise, and compare them to the denoising effect of various methods. Among all the methods evaluated, the deep learning-based Convolutional Neural Network (CNN) approach demonstrates superior performance compared to the other techniques. While maintaining the edges and fine structures in the images, this method was able to eliminate both additive and multiplicative noise. The evaluation of these methods performance primarily relied on several metrics, including visual assessment, Mean Square Error (MSE), Peak signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Normalized Absolute Mean (NAM), and Cross-Correlation (CC). These metrics provided a comprehensive analysis of the effectiveness and quality of the methods in reducing noise and preserving image details. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

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：