检索结果-内蒙古大学图书馆

31st ACM International Conference on Multimedia (MM)

作者： Xu, Dongsheng Zhao, Wenye Cai, Yi Huang, Qingbao Guangxi Univ Sch Elect Engn Nanning Guangxi Peoples R China South China Univ Technol Sch Software Engn Guangzhou Guangdong Peoples R China MOE China Key Lab Big Data & Intelligent Robot SCUT Guangzhou Guangdong Peoples R China Guangxi Key Lab Multimedia Commun & Network Techn Nanning Guangxi Peoples R China

ISBN: (纸本)9798400701085

Text-based image captioning is a vital but under-explored task, which aims to describe images by captions containing scene text automatically. Recent studies have made encouraging progress, but they are still suffering from two issues. Firstly, current models cannot capture and generate scene text in non-Latin script languages, which severely limits the objectivity and the information completeness of generated captions. Secondly, current models tend to describe images with monotonous and templated style, which greatly limits the diversity of the generated captions. Although the above-mentioned issues can be alleviated through carefully designed annotations, this process is undoubtedly laborious and time-consuming. To address the above issues, we propose a Zero-shot Framework for Text-based Image Captioning (Zero-TextCap). Concretely, to generate candidate sentences starting from the prompt 'Image of' and iteratively refine them to improve the quality and diversity of captions, we introduce a Hybrid-sampling masked language model (H-MLM). To read multi-lingual scene text and model the relationships between them, we introduce a robust OCR system. To ensure that the captions generated by H-MLM contain scene text and are highly relevant to the image, we propose a CLIP-based generation guidance module to insert OCR tokens and filter candidate sentences. Our Zero-TextCap is capable of generalizing captions containing multi-lingual scene text and boosting the diversity of captions. Sufficient experiments demonstrate the effectiveness of our proposed Zero-TextCap. Our codes are available at https://***/VILAN-Lab/Zero_TextCap.

关键词： Text-based image captioning Zero-shot Language bias Diversity

来源：评论

学校读者我要写书评

暂无评论

Computer aided diagnosis of diabetic retinopathy based on multi-view joint learning

引用

Computers in Biology and Medicine 2024年 174卷 108428-108428页

作者： Xu, Xuebin Liu, Dehua Huang, Guohua Wang, Muyu Lei, Meng Jia, Yang School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China Weinan Central Hospital Shaanxi Xi'an714099 China

Diabetic retinopathy (DR) is a kind of ocular complication of diabetes, and its degree grade is an essential basis for early diagnosis of patients. Manual diagnosis is a long and expensive process with a specific risk of misdiagnosis. Computer-aided diagnosis can provide more accurate and practical treatment recommendations. In this paper, we propose a multi-view joint learning DR diagnostic model called RT2Net, which integrates the global features of fundus images and the local detailed features of vascular images to reduce the limitations of single fundus image learning. Firstly, the original image is preprocessed using operations such as contrast-limited adaptive histogram equalization, and the vascular structure of the extracted DR image is segmented. Then, the vascular image and fundus image are input into two branch networks of RT2Net for feature extraction, respectively, and the feature fusion module adaptively fuses the feature vectors’ output from the branch networks. Finally, the optimized classification model is used to identify the five categories of DR. This paper conducts extensive experiments on the public datasets EyePACS and APTOS 2019 to demonstrate the method's effectiveness. The accuracy of RT2Net on the two datasets reaches 88.2% and 85.4%, and the area under the receiver operating characteristic curve (AUC) is 0.98 and 0.96, respectively. The excellent classification ability of RT2Net for DR can significantly help patients detect and treat lesions early and provide doctors with a more reliable diagnosis basis, which has significant clinical value for diagnosing DR. © 2024 The Authors

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

RoboNet: A Neural Network Based Kinematic Parameter Identification Model 18

RoboNet: A Neural Network Based Kinematic Parameter Identifi...

引用

18th IEEE International Conference on Networking, Sensing and Control, ICNSC 2021

作者： Xiong, Diwen Shang, Mingsheng Chinese Academy of Sciences Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chongqing China

ISBN: (纸本)9781665440486

The positioning accuracy of a robot is crucial for its industrial applications. A common way to improve such accuracy is through robot calibration, which mostly aims to identify the errors of a robot's kinematic parameters. However, while a robot kinematic model being a highly nonlinear system with non-Gaussian noises, approaches could cause truncation error when approximating such nonlinearity, resulting in a less sufficient calibration result. To address this issue, this paper innovatively proposes a neural network-based approach: the RoboNet, which identifies the kinematic parameters by nonlinearly approximating the error function of each parameter with neurons and nonlinear activation functions. It also provides a unified architecture for kinematic parameters identification of the robot calibration process, so that with simple modifications, RoboNet could be applied to the various robot calibration processes. And supported by the simulation results, RoboNet can accurately identify the errors in kinematic parameters and is robust against flawed data. © 2021 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Target Speaker Extraction With Attention-Based Fusion

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2024年 32卷 178-188页

作者： Li, Xiao Liu, Ruirui Huang, Huichou Wu, Qingyao South China Univ Technol Sch Elect & Informat Engn Guangzhou 510006 Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot Beijing 100081 Peoples R China Brunel Univ London Dept Econ & Finance London UB8 3PH England Kings Coll London Data Analyt Finance & Macro Ctr London England City Univ Hong Kong Global Res Unit Hong Kong Peoples R China South China Univ Technol Sch Software Engn Guangzhou 510006 Peoples R China Pazhou Lab Guangzhou 510335 Peoples R China

Given a reference speech clip from the target speaker, Target Speaker Extraction (TSE) is a challenging task that involves extracting the signal of the target speaker from a multi-speaker environment. TSE networks typically comprise a main network and an auxiliary network. The former utilizes the obtained target speaker embedding to generate an appropriate mask for isolating the signal of the target speaker from those of other speakers, while the latter aims to learn deep discriminative embeddings from the signal of the target speaker. However, the TSE networks often face performance degradation when dealing with unseen speakers or speeches with short references. In this article, we propose a novel approach that leverages contrastive learning in the auxiliary network to obtain better representations of unseen speakers or speeches with short references. Specifically, we employ contrastive learning to bridge the gap between short and long speech features. In this case, the auxiliary network with the input of a short speech generates feature embeddings that are as rich as those obtained from a long speech. Therefore, improving the recognition of unseen speakers or short speeches. Moreover, we introduce an attention-based fusion method that integrates the speaker embedding into the main network in an adaptive manner for enhancing mask generation. Experimental results demonstrate the effectiveness of our proposed method in improving the performance of TSE tasks in realistic open scenarios.

关键词： Feature extraction Task analysis Visualization Speech enhancement Decoding Degradation Transformers Speaker extraction self-supervised learning contrastive learning attention

来源：评论

学校读者我要写书评

暂无评论

Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval

Towards a Smaller Student: Capacity Dynamic Distillation for...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yi Xie Huaidong Zhang Xuemiao Xu Jianqing Zhu Shengfeng He South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Huaqiao University Singapore Management University

Previous Knowledge Distillation based efficient image retrieval methods employ a lightweight network as the stu-dent model for fast inference. However, the lightweight stu-dent model lacks adequate representation capacity for effective knowledge imitation during the most critical early training period, causing final performance degeneration. To tackle this issue, we propose a Capacity Dynamic Distillation framework, which constructs a student model with editable representation capacity. Specifically, the employed student model is initially a heavy model to fruitfully learn distilled knowledge in the early training epochs, and the stu-dent model is gradually compressed during the training. To dynamically adjust the model capacity, our dynamic frame-work inserts a learnable convolutional layer within each residual block in the student model as the channel importance indicator. The indicator is optimized simultaneously by the image retrieval loss and the compression loss, and a retrieval- guided gradient resetting mechanism is proposed to release the gradient conflict. Extensive experiments show that our method has superior inference speed and accu-racy, e.g., on the VeRi-776 dataset, given the ResNet101 as a teacher, our method saves 67.13% model parameters and 65.67% FLOPs without sacrificing accuracy. Code is avail-able at https://***/SCY-X/Capacity_Dynamic_Distillation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Based Framework for Privacy-Preserving Machine Learning 24th

An Encoder-Based Framework for Privacy-Preserving Machine L...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wu, Jiayun Ren, Wei Zhang, Xianchao Zheng, Xianghan School of Computer Science China University of Geosciences Wuhan430074 China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR CASM Beijing China Ministry of Education Chengdu China Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province Jiaxing University Jiaxing China Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing University Jiaxing China College of Computer and Big Data Fuzhou University Fujian Fuzhou China School of Information and Intelligent Engineering Sanya College Hainan China

ISBN: (纸本)9789819615506

As a data-driven science, machine learning requires vast amounts of training data and computational resources. However, for highly privacy-sensitive data, it is crucial to protect the privacy of the data during both the training and utilization of machine learning models. In this paper, we propose a privacy-preserving machine learning approach using autoencoders and differential privacy mechanisms to safeguard data privacy while minimizing the impact on data availability. Specifically, we augment logistic regression and ResNet18 models with different architectures of autoencoders to perform data encryption? without compromising the machine learning tasks. Additionally, we employ differential privacy mechanisms to introduce gradient perturbations in the encoding part of the autoencoder, enhancing the algorithm’s security and further protecting data privacy. We also design the cosine similarity between the encoded and original data as a metric for evaluating data privacy, considering model performance, privacy budget, and data privacy collectively to balance data availability and privacy. Extensive experiments conducted on MNIST, CIFAR-10, PathMNIST, and BloodMNIST datasets demonstrate that for simple logistic regression models handling easily classifiable datasets, employing simple autoencoder structures can enhance classification accuracy, with significant performance impact after adding differential privacy. For ResNet18, utilizing convolutional autoencoders for data encryption generally has minimal impact on model classification performance and can even improve accuracy in most cases. Adding differential privacy has minor effects on model classification performance. Selecting appropriate model structures and privacy budgets for different usage scenarios can ensure both data availability and privacy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Mathematical model for predicting fungal growth and decomposition rates based on improved Logistic equations

引用

International Journal of Agricultural and Biological Engineering 2023年第1期16卷 60-65页

作者： Jiayong Pan Wenxin Le Zi’ao Wang Jian Chen College of Engineering China Agricultural UniversityBeijing 100083China Shenzhen Key Laboratory of Intelligent Microsatellite Constellation Shenzhen 518107GuangdongChina Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities MNRShanghai 200063China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhen 518000GuangdongChina Jiangsu Province and Education Ministry Co-sponsored Synergistic Innovation Center of Modern Agricultural Equipment Jiangsu UniversityZhenjiang 212013China Key Laboratory of Smart Agricultural Technology in Tropical South China Ministry of Agriculture and Rural AffairsGuangzhou 510642China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China State Key Laboratory of Clean Energy Utilization Zhejiang UniversityHangzhou 310013China

As the function of the decomposition of fungi has been clearly researched in the global carbon cycle,it is obviously of value to explore the decomposition rate of fungal *** study analyzed the relationship between environmental factors and biodiversity step by *** order to explore the interaction between the fungi and the relationship between the decomposition rate of fungi with time,the model based on the Logistic model was built and the Lotka-Volterra model was employed in the condition of two kinds of fungi existing in an environment with limited *** changing trend of population number and decomposition rate of several fungi under different environmental conditions can be predicted through the *** illustrate the applicability of the model,Laetiporus conifericola and Hyphoderma setigerum were applied as *** results showed that the higher the degree of population diversity,the greater the decomposition rate,and the higher the decomposition efficiency of the *** rich species diversity is conducive to accelerating the decomposition of litter,lignocellulose,and the circulation of the entire *** on the above model and using the data from measuring the mycelial elongation rate of each isolate at 10℃,16℃,and 22℃ under standardized laboratory conditions,the growth patterns of the five fungi combinations were *** results revealed a general increase in growth rate with increasing temperature,which verifies the accuracy of the ***,it also revealed that the total decomposition rate after fungal incorporation was negatively correlated with the decomposition rate of a fungal single *** on the above model,predictions can be made for fungal growth in different environments,and suitable environments for fungal growth can be *** the future,the model can be further optimized,and lignin and cellulose decomposition factors can be added to fit the decomposition of *** application

关键词： Logistic equations fungal decomposition mathematical model

来源：评论

学校读者我要写书评

暂无评论

CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting

CIRI: Curricular Inactivation for Residue-aware One-shot Vid...

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Zheng, Weiying Xu, Cheng Xu, Xuemiao Liu, Wenxi He, Shengfeng South China Univ Technol Guangzhou Peoples R China State Key Lab Subtrop Bldg Sci Guangzhou Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou Peoples R China Guangdong Prov Key Lab Computat Intelligence & Cy Guangzhou Peoples R China Fuzhou Univ Fuzhou Peoples R China Singapore Management Univ Singapore Singapore

ISBN: (纸本)9798350307184

Video inpainting aims at filling in missing regions of a video. However, when dealing with dynamic scenes with camera or object movements, annotating the inpainting target becomes laborious and impractical. In this paper, we resolve the one-shot video inpainting problem in which only one annotated first frame is provided. A naive solution is to propagate the initial target to the other frames with techniques like object tracking. In this context, the main obstacles are the unreliable propagation and the partially inpainted artifacts due to the inaccurate mask. For the former problem, we propose curricular inactivation to replace the hard masking mechanism for indicating the inpainting target, which is robust to erroneous predictions in long-term video inpainting. For the latter, we explore the properties of inpainting residue and present an on- line residue removal method in an iterative detect-andrefine manner. Extensive experiments on several real-world datasets demonstrate the quantitative and qualitative superiorities of our proposed method in one-shot video inpainting. More importantly, our method is extremely flexible that can be integrated with arbitrary traditional inpainting models, activating them to perform the reliable oneshot video inpainting task. Video demonstrations can be found in our supplement, and our code can be found at https://***/Arise-zwy/CIRI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Left Invariant Harmonic Vector Fields on Solvable Lie Groups

引用

南开大学学报（自然科学版） 2024年第5期57卷 115-120页

作者： Zhang Mengxue Tan Ju Sun Bichao School of Microelectronics and Data Science Anhui University of TechnologyMaanshan 243032China Anhui Provincial Joint Key Laboratory of Disciplines for Industrial Big Data Analysis and Intelligent Decision Maanshan 243032China

It's shown that on an n-dimensional LCS Lie group,there exist harmonic sections and left invariant vector fields defining harmonic maps only when it is endowed with a flat left invariant pseudo-Riemannian ***,we determine all the vector fields which are critical points of the energy functional restricted to vector fields of the same length on the n-dimensional pseudo-Riemannian LCS Lie group.

关键词： harmonic vector fields harmonic maps Lie group

来源：评论

学校读者我要写书评

暂无评论

Accumulative Time Based Ranking Method to Reputation Evaluation in Information Networks

引用

Journal of Computer Science & Technology 2022年第4期37卷 960-974页

作者： Hao Liao Qi-Xin Liu Ze-Cheng Huang Ke-Zhong Lu Chi Ho Yeung Yi-Cheng Zhang National Engineering Laboratory on Big Data System Computing Technology College of Computer Science and SoftwareEngineeringShenzhen UniversityShenzhen 518060China Guangdong Province Key Laboratory of Popular High Performance Computers Shenzhen UniversityShenzhen 518060China Guangdong Province Engineering Center of China-Made High Performance Data Computing System College of ComputerScience and Software EngineeringShenzhen UniversityShenzhen 518060China Institute of Big Data Intelligent Management and Decision Shenzhen UniversityShenzhen 518060China Department of Science and Environmental Studies The Education University of Hong KongHong Kong 999077China Department of Physics University of FribourgFribourg 1700Switzerland

Due to over-abundant information on the Web, information filtering becomes a key task for online users to obtain relevant suggestions and how to extract the most related item is always a key topic for researchers in various fields. In this paper, we adopt tools used to analyze complex networks to evaluate user reputation and item quality. In our proposed Accumulative Time Based Ranking (ATR) algorithm, we take into account the growth record of the network to identify the evolution of the reputation of users and the quality of items, by incorporating two behavior weighting factors which can capture the hidden facts on reputation and quality dynamics for each user and item respectively. Our proposed ATR algorithm mainly combines the iterative approach to rank user reputation and item quality with temporal dependence compared with other reputation evaluation methods. We show that our algorithm outperforms other benchmark ranking algorithms in terms of precision and robustness on empirical datasets from various online retailers and the citation datasets among research publications. Therefore, our proposed method has the capability to effectively evaluate user reputation and item quality.

关键词： temporal network behavior dynamics reputation evaluation ranking algorithm

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：