检索结果-内蒙古大学图书馆

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chengji Shen Zhenjiang Liu Kaixuan Chen Jie Lei Mingli Song Zunlei Feng State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Idlefish Network Technology Alibaba Group College of Computer Science and Technology Zhejiang University of Technology

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The remarkable success of AI-Generated Content (AIGC), especially diffusion image generation models, brings about unprecedented creative applications, but also creates fertile ground for malicious counterfeiting and crime. A highly effective family of forgery image detection methods based on diffusion reconstruction error has emerged, as images generated by diffusion are more easily reconstructed by any diffusion model. However, we find that existing methods only use reconstruction error from a single time step, failing to fully leverage the entire reconstruction process. To this end, we propose to comprehensively consider every single time step to form the Temporal reconstruction Error (TRE) that offers a richer feature representation. Furthermore, we design temporal aggregation and spatial focusing modules from two dimensions respectively to more effectively extract discriminative information from the TRE feature. Finally, we validate the proposed method on two popular datasets, and experimental results demonstrate that the proposed approach achieves state-of-the-art performance.

关键词： Deepfakes image synthesis Focusing Signal processing Feature extraction Diffusion models Forgery data mining Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

BioNet and NeFF: Crop Biomass Prediction from Point Clouds to Drone imagery

BioNet and NeFF: Crop Biomass Prediction from Point Clouds t...

引用

2025 IEEE/CVF Winter conference on Applications of Computer Vision, WACV 2025

作者： Li, Xuesong Hayder, Zeeshan Zia, Ali Cassidy, Connor Liu, Shiming Stiller, Warwick Stone, Eric Conaty, Warren Petersson, Lars Rolland, Vivien Csiro Agriculture and Food Australia Australian National University Australia Csiro Data61 Australia

ISBN: (纸本)9798331510831

Crop biomass offers crucial insights into plant health and yield, making it essential for crop science, farming systems, and agricultural research. However, current measurement methods, which are labor-intensive, destructive, and imprecise, hinder large-scale quantification of this trait. To address this limitation, we present a biomass prediction network (BioNet), designed for adaptation across different data modalities, including point clouds and drone imagery. Our BioNet, utilizing a sparse 3D convolutional neural network (CNN) and a transformer-based prediction module, processes point clouds and other 3D data representations to predict biomass. To further extend BioNet for drone imagery, we integrate a neural feature field (NeFF) module, enabling 3D structure reconstruction and the transformation of 2D semantic features from vision foundation models into the corresponding 3D surfaces. For the point cloud modality, BioNet demonstrates superior performance on two public datasets, with an approximate 6.1% relative improvement (RI) over the state-of-the-art. In the RGB image modality, the combination of BioNet and NeFF achieves a 7.9% RI. Additionally, the NeFF-based approach utilizes inexpensive, portable drone-mounted cameras, providing a scalable solution for large field applications. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving the Identification of Layers in 3D images of Ancient Papyrus Using Artificial Neural Networks

Improving the Identification of Layers in 3D Images of Ancie...

引用

2025 IEEE/CVF Winter conference on Applications of Computer Vision Workshops, WACVW 2025

作者： Klenert, Nicolas Schwoerer, Finn Hajarolasvadi, Noushin Bournez, Siloé Arlt, Tobias Mahnke, Heinz-Eberhard Lepper, Verena Baum, Daniel Zuse Institute Berlin Department of Visual and Data-Centric Computing Berlin Germany Helmholtz-Zentrum Berlin für Materialien und Energie Berlin Germany Ägyptisches Museum und Papyrussammlung Staatliche Museen zu Berlin Berlin Germany

ISBN: (纸本)9798331536626

The non-invasive digital unfolding of ancient documents, such as folded papyrus packages, from 3D image data aims to reveal previously hidden writing without risking to damage the precious documents. One of the main tasks in this process is the geometric reconstruction of the writing sub-strate, which is a prerequisite for its subsequent unfolding. All current reconstruction methods require the existence of an interspace between different layers of the document to ensure a correct topology. Layers that appear merged to-gether in the 3D image often result in wrong connections between layers and thus also in a wrong topology of the reconstructed geometry, which hinders the successful unfolding. Here, we propose to use a neural network to facilitate the discrimination of the layers. Using papyrus documents as an example of a particularly difficult writing material, we show that our approach significantly reduces the number of wrong connections and improves the overall identification of the layers. This in turn enables fully automatic digital unfolding of large areas of highly complex papyrus packages. Utilizing explainable AI (XAI) further allows us to explore the results of the applied neural network. © 2025 IEEE.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Personalized image Generation with Large Multimodal Models 34

Personalized Image Generation with Large Multimodal Models

引用

34th ACM Web conference, WWW 2025

作者： Xu, Yiyan Wang, Wenjie Zhang, Yang Tang, Biao Yan, Peng Feng, Fuli He, Xiangnan University of Science and Technology of China Hefei China National University of Singapore Singapore Singapore Meituan China Shanghai China Meituan China Beijing China MoE Key Lab of BIPC University of Science and Technology of China Hefei China

ISBN: (纸本)9798400712746

Personalized content filtering, such as recommender systems, has become a critical infrastructure to alleviate information overload. However, these systems merely filter existing content and are constrained by its limited diversity, making it difficult to meet users’ varied content needs. To address this limitation, personalized content generation has emerged as a promising direction with broad applications. Nevertheless, most existing research focuses on personalized text generation, with relatively little attention given to personalized image generation. The limited work in personalized image generation faces challenges in accurately capturing users’ visual preferences and needs from noisy user-interacted images and complex multimodal instructions. Worse still, there is a lack of supervised data for training personalized image generation models. To overcome the challenges, we propose a Personalized image Generation Framework named Pigeon, which adopts exceptional large multimodal models with three dedicated modules to capture users’ visual preferences and needs from noisy user history and multimodal instructions. To alleviate the data scarcity, we introduce a two-stage preference alignment scheme, comprising masked preference reconstruction and pairwise preference alignment, to align Pigeon with the personalized image generation task. We apply Pigeon to personalized sticker and movie poster generation, where extensive quantitative results and human evaluation highlight its superiority over various generative baselines. © 2025 Copyright held by the owner/author(s).

关键词： Large Multimodal Models Personalized image Generation Preference Alignment

来源：评论

学校读者我要写书评

暂无评论

Analysis for Predicting English Premier League Matches Using Clifford-Steerable Convolutional Networks 5

Analysis for Predicting English Premier League Matches Using...

引用

5th IEEE International conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Mohideen AbdulKader, M. Vaithieswaran, S. Advay Rao, Tanuj School of Computing Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Tamilnadu Chengalpattu India

ISBN: (纸本)9798350356236

The most widely watched football league globally is the Barclays English Premier League (EPL), the future performance of which attracts attention from both scholars and practitioners in terms of outcome prediction. It is still challenging to provide accurate predictions per match result because of the many attempts tried in the past due to complicated interference of many factors that entice game dynamics. In order to predict the EPL matches, this paper proposed a Cubature Kalman Filter Haar Wavelet Transform Clifford-Steerable Convolutional Neural Network with Mud Ring Algorithm (CKFHWTCSCNNet-MRA). The data was downloaded from Kaggle and the OCRCKF was used for data pre-processing. For feature selection the Q-DHWT was used, which stands for Quantized Discrete Haar Wavelet Transform. CS-CNNs were then applied to predict match results while The Mud Ring Algorithm (MRA) was applied to the analysis of hyperparameters. The rationale and validation of the proposed model is established based on the performance measures employed in predicting wins/loses of the match which yielded an outstanding accuracy, specificity, sensitivity and recall of 99%, F1-Score of 99% and error of 0.25%. © 2025 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Appearance-adapter: A Self-supervised Pose-guided Human image Synthesis Approach

Appearance-adapter: A Self-supervised Pose-guided Human Imag...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sameer Malik Moyuru Yamada Fujitsu Research India Private Limited Bengaluru India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Human image synthesis with pose guidance generates images of a specified human in a given pose, a task complicated by dis-occlusions and varying body articulations. While generative model-based approaches are effective, they often require paired training data, limiting generalizability. Recent selfsupervised methods, such as reconstruction from body parts and jigsaw puzzle-solving, face issues like pose leaking and inadequate appearance encoding. We propose a novel approach that learns to reconstruct images from body parts using a body symmetricity loss, leveraging human body symmetries. Our method preserves appearance information and mitigates pose leaking by aligning appearance features of corresponding body parts from symmetric left-right halves. Additionally, we leverage pretrained models, specifically stable-diffusion, to enhance performance and training efficiency. Extensive experiments and ablation studies on the deepfashion dataset demonstrate our method’s effectiveness.

关键词： Training Limiting image coding Training data Encoding data models Human image synthesis Speech processing image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

image reconstruction from radially incomplete spherical Radon data

引用

EUROPEAN JOURNAL OF APPLIED MATHEMATICS 2018年第3期29卷 470-493页

作者： Ambartsoumian, Gaik Gouia-Zarrad, Rim Krishnan, Venkateswaran P. Roy, Souvik Univ Texas Arlington Dept Math Arlington TX 76019 USA Amer Univ Sharjah Dept Math & Stat Sharjah U Arab Emirates Tata Inst Fundamental Res Ctr Applicable Math Bangalore Karnataka India Univ Wurzburg Dept Math Wurzburg Germany

We study inversion of the spherical Radon transform with centres on a sphere (the data acquisition set). Such inversions are essential in various image reconstruction problems arising in medical, radar and sonar imaging. In the case of radially incomplete data, we show that the spherical Radon transform can be uniquely inverted recovering the image function in spherical shells. Our result is valid when the support of the image function is inside the data acquisition sphere, outside that sphere, as well as on both sides of the sphere. Furthermore, in addition to the uniqueness result, our method of proof provides reconstruction formulas for all those cases. We present a robust computational algorithm and demonstrate its accuracy and efficiency on several numerical examples.

关键词： spherical Radon transform medical imaging spherical harmonics Volterra integral equations truncated singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Hybrid EEG Signal Processing Framework for Driver Drowsiness Detection Using QWT, EMD, and Bayesian Optimized SVM 3

Hybrid EEG Signal Processing Framework for Driver Drowsiness...

引用

3rd International conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Sardesai, Shilpa Gedam, Rahul Pune India Lcit Department of Electronics and Telecommunication Bilaspur India

ISBN: (纸本)9798331508456

Drowsiness among drivers poses an urgent safety problem in road transportation because it creates serious risks to both drivers and their passengers. Carrying out prolonged driving operations creates a mind state between full wakefulness and sleep. The research presents a new supervised learning approach to evaluate sleep stages which helps detect driver sleepiness and trigger prompt alerts. A deep feature extraction system based on QWT with time-frequency scalogram and EMD artifact removal generates features from EEG signals. The system uses evaluation of decomposition levels' energy measurements to build Energy Vectors which lead to the processing of each EEG signal into feature vectors. data classification in this research occurs through implementation of the BO-SVM classifier which features Bayesian optimization. The BO-SVM classifier delivers exceptional accuracy results because it reaches 99.17% maximum accuracy beyond typical SVM classifier performance levels. This paper combines signal processing methods with machine learning techniques which result in advanced EEG data-based sleep stage diagnosis to enhance driver safety. © 2025 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Robust Convolutional Neural Network for Electrical Impedance Tomography image reconstruction

A Robust Convolutional Neural Network for Electrical Impedan...

引用

IEEE SSD International Multi-conference on Systems, Signals and Devices

作者： Mariem Hafsa Kailun Lin Najoua Essoukri Ben Amara Olfa Kanoun Ecole Nationale d'Ingénieurs de Sousse LATIS-Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Sousse Tunisie Professorship of Measurement and Sensor Technology Technische Universität Chemnitz Chemnitz Germany Department of Mechanical Engineering Technische Universität Chemnitz Chemnitz Germany

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

Electrical Impedance Tomography (EIT) is a widely used non-invasive imaging method in a variety of application fields. Most EIT applications require an accurate and high-quality reconstructed inner conductivity distribution image. Several solutions have been developed for reliable EIT image reconstruction, but they still suffer from limitations such as low spatial resolution and inconsistency in real measurement scenarios. In this paper, we propose using physically based, extensive simulation data to train a Convolutional Neural Network (CNN) model with 5-fold cross-validation. We generate a set of 10.000 data samples, which builds a comprehensive basis for its training and ensures reliability and generalization capability. The quantitative evaluation demonstrates good reconstruction performance, achieving a Mean Squared Error (MSE) of 0.0151 and an image Correlation Coefficient (ICC) of 0.97 in the best-performing fold for the simulated data. The method's effectiveness is particularly validated through experimental measurements, where it significantly outperforms traditional Gauss-Newton reconstruction in terms of image sharpness and boundary definition. The algorithm is robust and easily applicable for EIT imaging.

关键词： Training image quality Electrical impedance tomography Voltage measurement Impedance measurement Imaging Robustness Convolutional neural networks Spatial resolution image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Bayesian image and pattern reconstruction from incomplete and noisy data

引用

Pattern Recognition and image Analysis 2012年第1期22卷 99-107页

作者： Vengrinovich, V.L. Institute of Applied Physics National Academy of Sciences Minsk Belarus

A Bayesian iterative method can be the basis for a wide range of technologies in the field of pattern recognition and image reconstruction. It involves finding the most probable solutions for images or patterns, if functionals describing the likelihood function and a priori information, respectively, are already known. The article describes the basic principles and recent advances in the development of BIM and its applications in various fields, mainly in tomography and restoration of functions from incomplete and noisy data. © 2012 Pleiades Publishing, Ltd.

关键词： Restoration

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：