检索结果-内蒙古大学图书馆

CLIP-Flow:Decoding images encoded in CLIP space

Computational Visual Media 2024年第6期10卷 1157-1168页

作者： Hao Ma Ming Li Jingyuan Yang Or Patashnik Dani Lischinski Daniel Cohen-Or Hui Huang Visual Computing Research Center College of Computer Science and Software EngineeringShenzhen UniversityShenzhen 518060China Department of Computer Science Tel Aviv UniversityTel Aviv 6997801Israel School of Computer Science and Engineering the Hebrew University of JerusalemJerusalem 91904Israel

This study introduces CLIP-Flow,a novel network for generating images from a given image or *** effectively utilize the rich semantics contained in both modalities,we designed a semantics-guided methodology for image-and text-to-image *** particular,we adopted Contrastive Language-Image Pretraining(CLIP)as an encoder to extract semantics and StyleGAN as a decoder to generate images from such ***,to bridge the embedding space of CLIP and latent space of StyleGAN,real NVP is employed and modified with activation normalization and invertible *** the images and text in CLIP share the same representation space,text prompts can be fed directly into CLIP-Flow to achieve text-to-image *** conducted extensive experiments on several datasets to validate the effectiveness of the proposed image-to-image synthesis *** addition,we tested on the public dataset Multi-Modal CelebA-HQ,for text-to-image *** validated that our approach can generate high-quality text-matching images,and is comparable with state-of-the-art methods,both qualitatively and quantitatively.

关键词： image-to-image text-to-image contrastive language-image pretraining(CLIP) flow StyleGAN

来源：评论

学校读者我要写书评

暂无评论

A Novel CAPTCHA Recognition System Based on Refined Visual Attention

引用

computers, Materials & Continua 2025年第4期83卷 115-136页

作者： Zaid Derea Beiji Zou Xiaoyan Kui Monir Abdullah Alaa Thobhani Amr Abdussalam School of Computer Science and Engineering Central South UniversityChangsha410083China College of Computer Science and Information Technology Wasit UniversityWasit52001Iraq Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha67714Saudi Arabia Electronic Engineering and Information Science Department University of Science and Technology of ChinaHefei230026China

Improving website security to prevent malicious online activities is crucial,and CAPTCHA(Completely Automated Public Turing test to tell computers and Humans Apart)has emerged as a key strategy for distinguishing human users from automated ***-based CAPTCHAs,designed to be easily decipherable by humans yet challenging for machines,are a common form of this ***,advancements in deep learning have facilitated the creation of models adept at recognizing these text-based CAPTCHAs with surprising *** our comprehensive investigation into CAPTCHA recognition,we have tailored the renowned UpDown image captioning model specifically for this *** approach innovatively combines an encoder to extract both global and local features,significantly boosting the model’s capability to identify complex details within CAPTCHA *** the decoding phase,we have adopted a refined attention mechanism,integrating enhanced visual attention with dual layers of Long Short-Term Memory(LSTM)networks to elevate CAPTCHA recognition *** rigorous testing across four varied datasets,including those from Weibo,BoC,Gregwar,and Captcha 0.3,demonstrates the versatility and effectiveness of our *** results not only highlight the efficiency of our approach but also offer profound insights into its applicability across different CAPTCHA types,contributing to a deeper understanding of CAPTCHA recognition technology.

关键词： Text-based CAPTCHA recognition refined visual attention web security computer vision

来源：评论

学校读者我要写书评

暂无评论

Distribution,enrichment mechanism and risk assessment for fluoride in groundwater:a case study of Mihe-Weihe River Basin,China

引用

Frontiers of Environmental science & engineering 2023年第6期17卷 63-83页

作者： Xingyue Qu Peihe Zhai Longqing Shi Xingwei Qu Ahmer Bilal Jin Han Xiaoge Yu College of Earth Science and Engineering Shandong University of Science and TechnologyQingdao 266590China College of Safety and Environmental Engineering Shandong University of Science and TechnologyQingdao 266590China College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590China Department of Resource and Civil Engineering Shandong University of Science and TechnologyTai'an 271019China

Due to the unclear distribution characteristics and causes of fluoride in groundwater of Mihe-Weihe River Basin(China),there is a higher risk for the future development and utilization of ***,based on the systematic sampling and analysis,the distribution features and enrichment mechanism for fluoride in groundwater were studied by the graphic method,hydrogeochemical modeling,the proportionality factor between conventional ions and factor *** results show that the fluorine content in groundwater is generally on the high side,with a large area of medium-fluorine water(0.5–1.0 mg/L),and high-fluorine water is chiefly in the interfluvial lowlands and alluvial-marine plain,which mainly contains HCO_(3)·Cl-Na-and HCO_(3)^(-)Na-type *** vertical zonation characteristics of the fluorine content decrease with increasing depth to the water *** high flouride groundwater during the wet season is chiefly controlled by the weathering and dissolution of fluorine-containing minerals,as well as the influence of rock weathering,evaporation and *** weak alkaline environment that is rich in sodium and poor in calcium during the dry season is the main reason for the enrichment of ***,an integrated assessment model is established using rough set theory and an improved matter element extension model,and the level of groundwater pollution caused by fluoride in the Mihe-Weihe River Basin during the wet and dry seasons in the Shandong Peninsula is defined to show the necessity for local management measures to reduce the potential risks caused by groundwater quality.

关键词： Groundwater in the Mihe-Weihe River Basin Distribution characteristics of fluorine Factors influencing fluoride Enrichment mechanism of fluorine Hydrogeochemical modeling Pollution and risk assessment

来源：评论

学校读者我要写书评

暂无评论

Multimodal emotion recognition model via hybrid model with improved feature level fusion on facial and EEG feature set

引用

Multimedia Tools and Applications 2025年第1期84卷 1-36页

作者： Singh, Pratima Tripathi, Mukesh Kumar Patil, Mithun B. Shivendra Neelakantappa, Madugundu Department of Computer Science and Engineering Galgotias University Gautam Buddh Nagar Uttar Pradesh India Department of Computer Science and Engineering Vardhaman College of Engineering Telangana Hyderabad India Department of Computer Science and Engineering N K Orchid College of Engineering & Technology Maharastra Solapur India Department of Computer Application D. K. College Dumraon Bihar Buxar India Department of Information Technology Vasavi College of Engineering Telangana Hyderabad India

In recent years, academics have placed a high value on multi-modal emotion identification, as well as extensive research has been conducted in the areas of video, text, voice, and physical signal emotion detection. This paper proposes a novel multimodal emotion recognition model that employs a hybrid model with AMIG-based feature fusion on facial and EEG feature sets. The EEG signal and facial image are subjected to preprocessing to remove unwanted background noises with the Butterworth filter and Viola Jones Algorithm, respectively. While considering the pre-processed EEG signal, features such as EWFS-transform, wavelet features, and CSP-based features are extracted. In the proposed EWFS-transform, the window function is modified by using the frequency function and updated STFT. Conversely, the features including SE-AMM-EST-based features;LGXP and GLCM are extracted while considering the preprocessed face image. In the proposed SE-AMM-EST-based features, the mean of shape is updated and covariance in PCA for extracting texture-based features. In order to extract redundant free essential features, AMIG-based feature fusion is proposed. Further, the fused features are fed into a proposed hybrid model that includes LSTM and AML-CNN models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

DeepGAN: Utilizing generative adversarial networks for improved deep learning

引用

International Journal of Knowledge-Based and Intelligent engineering Systems 2024年第4期28卷 732-748页

作者： V, Edward Naveen A, Jenefa T.M, Thiyagu A, Lincy Taurshia, Antony Department of Computer Science and Engineering Sri Shakthi Institute of Engineering and Technology India Department of Computer Science and Engineering Karunya Institute of Technology and Sciences India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences India Department of Computer Science and Engineering National Engineering College India

In the realm of deep learning, Generative Adversarial Networks (GANs) have emerged as a topic of significant interest for their potential to enhance model performance and enable effective data augmentation. This paper addresses the existing challenges in synthesizing high-quality data and harnessing the capabilities of GANs for improved deep learning outcomes. Unlike traditional approaches that heavily rely on manually engineered data augmentation techniques, our work introduces a novel framework that leverages DeepGANs to autonomously generate diverse and high-fidelity data. Our experiments encompass a diverse spectrum of datasets, including images, text, and time series data. In the context of image classification tasks, we conduct experiments on the widely recognized CIFAR-10 dataset, which consists of 50,000 image samples. Our results demonstrate the remarkable efficacy of DeepGANs in enhancing model performance across various data domains. Notably, in image classification using the CIFAR-10 dataset, our innovative approach achieves an impressive accuracy of 97.2%. This represents a substantial advancement beyond conventional CNN models, underscoring the profound impact of DeepGANs in the realm of deep learning. In summary, this research sheds light on DeepGANs as a fundamental component in the pursuit of enhanced deep learning performance. Our framework not only overcomes existing limitations but also heralds a new era of data augmentation, with generative adversarial networks leading the way. The attainment of an accuracy rate of 97.2% on CIFAR-10 serves as a compelling testament to the transformative potential of DeepGANs, solidifying their pivotal role in the future of deep learning. This promises the development of more robust, adaptive, and accurate models across a myriad of applications, marking a significant contribution to the field. © 2024 – IOS Press. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Detection method of students' online learning state based on posture recognition

引用

International Journal of Business Intelligence and Data Mining 2024年第3-4期24卷 278-292页

作者： He, Xiaowei Computer Engineering Technical College Guangdong Polytechnic of Science and Technology Zhuhai519090 China

Because of the problems of low detection accuracy and long detection time in traditional online learning state detection methods, a new method based on posture recognition is proposed. First of all, a pinhole camera perspective imaging model is constructed, students' online learning images are collected, and the images are processed with greyscale, smoothing, enhancement and light compensation. Secondly, according to the key points of bones, the online learning image features of students after preprocessing are extracted. Finally, identify students' online learning posture, and construct a state detection model combining eye movement behaviour to complete the detection of students' online learning state. The experimental results show that the proposed method has higher accuracy and shorter detection time for students' online learning state detection. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Energy Distribution Correlation Judgment Method for Interrupted Sampling Repeater Jamming Suppression

引用

Progress In Electromagnetics Research B 2024年 105卷 59-78页

作者： Li, Ji Su, Fan Wang, Wei Yan, Rui Li, Jialiang College of Computer and Communication Engineering Changsha University of Science & Technology Changsha410000 China

Interrupted Sampling Repeater Jamming (ISRJ) can produce several false targets through intermittent sampling and forwarding of the intercepted signals. The paper proposes an interference identification and suppression method based on Short-Time Fourier Transform-Energy Distribution Correlation Judgment (STFT-EDCJ) to lessen the impact of the false targets mixed in echo pulses. Firstly, the method obtains the energy distribution of echoes in the time-frequency domain employing the short-time Fourier transform, extracts the time slice of higher energy targets through energy peak detection, and then calculates the Pearson correlation coefficient (PCC) of the energy distribution in the frequency domain of each target time slice to construct the Target PCC Datasets (TPCCD). Secondly, it distinguishes between the real target and false targets after echo pulse pressure by the range and specificity of TPCCD. Finally, it uses mapping the time domain position of the false targets to suppress interference. The abundant simulation results verify the proposed method’s effectiveness, and the Monte Carlo simulation demonstrates the method’s effectiveness under ISRJ models. © (2023), (Electromagnetics Academy). All Rights Reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

science China(Information sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

来源：评论

学校读者我要写书评

暂无评论

Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows

引用

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1192-1208页

作者： Zheyun Qin Xiankai Lu Xiushan Nie Dongfang Liu Yilong Yin Wenguan Wang the School of Software Shandong UniversityJinan 250101China the School of Computer Science and Technology Shandong Jianzhu UniversityJinan 250101China the College of Computer and Information Science Southwest UniversityChongqing 400715China the College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

We introduce a novel method using a new generative model that automatically learns effective representations of the target and background appearance to detect,segment and track each instance in a video *** from current discriminative tracking-by-detection solutions,our proposed hierarchical structural embedding learning can predict more highquality masks with accurate boundary details over spatio-temporal space via the normalizing *** formulate the instance inference procedure as a hierarchical spatio-temporal embedded learning across time and *** the video clip,our method first coarsely locates pixels belonging to a particular instance with Gaussian distribution and then builds a novel mixing distribution to promote the instance boundary by fusing hierarchical appearance embedding information in a coarse-to-fine *** the mixing distribution,we utilize a factorization condition normalized flow fashion to estimate the distribution parameters to improve the segmentation *** qualitative,quantitative,and ablation experiments are performed on three representative video instance segmentation benchmarks(i.e.,YouTube-VIS19,YouTube-VIS21,and OVIS)and the effectiveness of the proposed method is *** impressively,the superior performance of our model on an unsupervised video object segmentation dataset(i.e.,DAVIS19)proves its *** algorithm implementations are publicly available at https://***/zyqin19/HEVis.

关键词： Embedding learning generative model normalizing flows video instance segmentation(VIS)

来源：评论

学校读者我要写书评

暂无评论

PIAFGNN:Property Inference Attacks against Federated Graph Neural Networks

引用

computers, Materials & Continua 2025年第2期82卷 1857-1877页

作者： Jiewen Liu Bing Chen Baolu Xue Mengya Guo Yuntao Xu College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing321002China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing210023China

Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving the data isolation problem faced by centralized GNNs in data-sensitive scenarios. Despite the plethora of prior work on inference attacks against centralized GNNs, the vulnerability of FedGNNs to inference attacks has not yet been widely explored. It is still unclear whether the privacy leakage risks of centralized GNNs will also be introduced in FedGNNs. To bridge this gap, we present PIAFGNN, the first property inference attack (PIA) against FedGNNs. Compared with prior works on centralized GNNs, in PIAFGNN, the attacker can only obtain the global embedding gradient distributed by the central server. The attacker converts the task of stealing the target user’s local embeddings into a regression problem, using a regression model to generate the target graph node embeddings. By training shadow models and property classifiers, the attacker can infer the basic property information within the target graph that is of interest. Experiments on three benchmark graph datasets demonstrate that PIAFGNN achieves attack accuracy of over 70% in most cases, even approaching the attack accuracy of inference attacks against centralized GNNs in some instances, which is much higher than the attack accuracy of the random guessing method. Furthermore, we observe that common defense mechanisms cannot mitigate our attack without affecting the model’s performance on mainly classification tasks.

关键词： Federated graph neural networks GNNs privacy leakage regression model property inference attacks embeddings

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：