检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Zhixuan Li Weining Ye Juan Terven Zachary Bennett Ying Zheng Tingting Jiang Tiejun Huang National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China AiFi Inc. California United States Beijing Academy of Artificial Intelligence Beijing China

Amodal Instance Segmentation (AIS) endeavors to accurately deduce complete object shapes that are partially or fully occluded. However, the inherent ill-posed nature of single-view datasets poses challenges in determining occluded shapes. A multi-view framework may help alleviate this problem, as humans often adjust their perspective when encountering occluded objects. At present, this approach has not yet been explored by existing methods and datasets. To bridge this gap, we propose a new task called Multi-view Amodal Instance Segmentation (MAIS) and introduce the MUVA dataset, the first MUlti-View AIS dataset that takes the shopping scenario as instantiation. MUVA provides comprehensive annotations, including multi-view amodal/visible segmentation masks, 3D models, and depth maps, making it the largest image-level AIS dataset in terms of both the number of images and instances. Additionally, we propose a new method for aggregating representative features across different instances and views, which demonstrates promising results in accurately predicting occluded objects from one viewpoint by leveraging information from other viewpoints. Besides, we also demonstrate that MUVA can benefit the AIS task in real-world scenarios. 1

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Irregular Convolution U-Net for Reconstructing Ancient Channel of the Yellow River

An Adaptive Irregular Convolution U-Net for Reconstructing A...

引用

IEEE SENSORS

作者： Zhishun Guo Jianhui Zhao Ning Li Lin Wu College of Computer and Information Engineering Henan University Kaifeng China Henan. Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China

The lower reaches of the ancient Yellow River (AYR) migrated very frequently, like a loong swinging its tail on the land of China. This paper, based on Gaofen-3 full-polarization synthetic aperture radar (SAR) data, analyzed scattering characteristics of archaeolandscapes, which provided reliable evidences for the existence of AYR between Lankao and Sui County. Then, an adaptive irregular convolution kernel U-Net (AICK-U-Net) was proposed to reconstruct the part of channel of AYR, based on the image obtained by polarization decomposition, and the precision reached 96.21%. In summary, polarization decomposition and neural network in spaceborne SAR field, provided new insights for detecting and reconstructing archaeolandscapes.

关键词： Convolution Spaceborne radar Neural networks Scattering Sensors Rivers Reliability

来源：评论

学校读者我要写书评

暂无评论

BIRA-NET: BILINEAR ATTENTION NET FOR DIABETIC RETINOPATHY GRADING

arXiv

引用

arXiv 2019年

作者： Zhao, Ziyuan Zhang, Kerui Hao, Xuejie Tian, Jing Chua, Matthew Chin Heng Chen, Li Xu, Xin Institute of Systems Science National University of Singapore Singapore University of Electronic Science and Technology of China China School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China

Diabetic retinopathy (DR) is a common retinal disease that leads to blindness. For diagnosis purposes, DR image grading aims to provide automatic DR grade classification, which is not addressed in conventional research methods of binary DR image classification. Small objects in the eye images, like lesions and microaneurysms, are essential to DR grading in medical imaging, but they could easily be influenced by other objects. To address these challenges, we propose a new deep learning architecture, called BiRA-Net, which combines the attention model for feature extraction and bilinear model for fine-grained classification. Furthermore, in considering the distance between different grades of different DR categories, we propose a new loss function, called grading loss, which leads to improved training convergence of the proposed approach. Experimental results are provided to demonstrate the superior performance of the proposed approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Eye protection

来源：评论

学校读者我要写书评

暂无评论

PPBFL: A Privacy Protected Blockchain-based Federated Learning Model

arXiv

引用

arXiv 2024年

作者： Li, Yang Xia, Chunhe Lin, Wanshuang Wang, Tianbo The Key Laboratory of Beijing Network Technology Beihang University Beijing100191 China The Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing Guangxi Normal University Guilin541004 China The School of Cyber Science and Technology Beihang University Beijing100191 China The Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai201112 China

With the rapid development of machine learning and a growing concern for data privacy, federated learning has become a focal point of attention. However, attacks on model parameters and a lack of incentive mechanisms hinder the effectiveness of federated learning. Therefore, we propose A Privacy Protected Blockchain-based Federated Learning Model (PPBFL) to enhance the security of federated learning and encourage active participation of nodes in model training. Blockchain technology ensures the integrity of model parameters stored in the InterPlanetary File System (IPFS), providing protection against tampering. Within the blockchain, we introduce a Proof of Training Work (PoTW) consensus algorithm tailored for federated learning, aiming to incentive training nodes. This algorithm rewards nodes with greater computational power, promoting increased participation and effort in the federated learning process. A novel adaptive differential privacy algorithm is simultaneously applied to local and global models. This safeguards the privacy of local data at training clients, preventing malicious nodes from launching inference attacks. Additionally, it enhances the security of the global model, preventing potential security degradation resulting from the combination of numerous local models. The possibility of security degradation is derived from the composition theorem. By introducing reverse noise in the global model, a zero-bias estimate of differential privacy noise between local and global models is achieved. Furthermore, we propose a new mix transactions mechanism utilizing ring signature technology to better protect the identity privacy of local training clients. Security analysis and experimental results demonstrate that PPBFL, compared to baseline methods, not only exhibits superior model performance but also achieves higher security. Copyright © 2024, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Multiple Spatial information Weighted Fuzzy Clustering for Image Segmentation

Multiple Spatial Information Weighted Fuzzy Clustering for I...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xiangdao Liu Jin Zhou Hui Jiang C. L. Philip Chen Tong Zhang Lin Wang Shiyuan Han Yuehui Chen Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan China Development and Test Center Chinabond Fintech Information Technology Co. Ltd. Beijing China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (数字)9781728185262

ISBN: (纸本)9781728185279

For image segmentation, fuzzy clustering methods with single spatial information cannot ensure robustness to the image corrupted by different noises. In this paper, to figure out this problem, we propose a multiple spatial information weighted fuzzy clustering method, in which the original pixel intensity and its two spatial information, the mean and median of neighbors within a local window, are combined with different weights to obtain precise segmentation results of noise images. And the entropy-regularized method is employed to optimize the weight of each term to handle the images with different noise. What's more, the kernelization of the proposed method is presented to relief the impact of outliers. It is worth noting that our methods can be further extended by combining with other spatial information. Experiments on synthetic images and natural images show the superiority and efficiency of the proposed methods.

关键词： Image segmentation Clustering methods Scalability Conferences Robustness Entropy Cybernetics

来源：评论

学校读者我要写书评

暂无评论

A Conflict Degree-Guided Quantum Group Consensus Method Based on Graph Convolutional Networks with Enhanced Sentiment Analysis for Consumer Electronics Products

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Zhang, Chao Liang, Xinyu Sangaiah, Arun Kumar Li, Deyu Shanxi University School of Computer and Information Technology Key Laboratory of Computational Intelligence Chinese Information Processing Ministry of Education Taiyuan030006 China National Yunlin University of Science and Technology International Graduate Institute of Artificial Intelligence Douliou64002 Taiwan Sunway University School of Engineering and Technology Petaling Jaya Selangor 47500 Malaysia Chandigarh University University Centre for Research and Development Punjab Mohali140413 India

Artificial intelligence-based human-computer interaction (AI-HCI) and consumer electronics (CE) are closely linked, making AI-HCI crucial in e-commerce by providing intelligent and personalized product recommendations. In this context, consumers often select from multiple websites and products when purchasing CE products. This makes CE product selections conflicting and random to reach a consensus, often modeled as a quantum group consensus problem. Therefore, this paper aims to enhance consumer selections via intelligent decision support using online reviews. First, an ensemble technique, multi-objective salp swarm optimization bi-directional long short-term memory (MOSSO-BiLSTM) with gate recurrent unit (GRU), is employed for sentiment analysis (SA). Second, graph convolutional networks (GCN) is used to calculate weights for key indicators. Meanwhile, according to hybrid distances, an improved fuzzy C-means three-way (FCMTW) clustering analysis is explored. Third, a conflict degree-guided quantum two-stage consensus reaching process (CRP) is designed. It includes identification rules determined by quantum frameworks and modification rules determined by regret theory (RT). Fourth, multi-objective optimization by ratio analysis plus the full MULTIplicative form (MULTIMOORA) and RT are combined for stable optimal product selections. Finally, a case study of selecting solar emergency lights verifies the viability of the proposed methodology. © 1975-2011 IEEE.

关键词： Quantum electronics

来源：评论

学校读者我要写书评

暂无评论

Intelligent Speech Enhancement Algorithm Model Based on Recorded Classroom Audio

Intelligent Speech Enhancement Algorithm Model Based on Reco...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Xinyun Zhang Li Shen Li Zhou Dawei Luo Dejiangmo Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China School of Physics and Electronic Information Gannan Normal University Ganzhou China School of Mathematics and Computer Science Northwest Minzu University Lanzhou China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

With advancements in communication technology, there is increasing demand for high-quality voice communication and accurate speech recognition. In the complex acoustic environment of a recording classroom, noise, reverberation and other interferences can seriously affect the quality and intelligibility of the picked-up target speech signal, which in turn affects the effectiveness of the subsequent speech communication and recognition, so it is crucial to enhance the target speech signal in order to satisfy people's demand for clear and recognizable speech information. In this paper, based on the network model of Deep Complex Convolutional Recurrent Network (DCCRN), we introduce the F-T-LSTM structure to more accurately describe the correlation between the time and frequency domains of speech, and at the same time, we integrate the channel attention mechanism and the spatial attention mechanism to carry out a more comprehensive feature extraction of the speech features in the complex domain, and we skillfully concentrate the computational power in the area with the most feature-rich information, so that the quality and intelligibility of speech signals under the complex domain are significantly improved. significantly improve the overall performance of speech enhancement networks in the complex domain.

关键词： Time-frequency analysis Attention mechanisms Correlation Target recognition Computational modeling Speech recognition Speech enhancement Feature extraction Complexity theory Reverberation

来源：评论

学校读者我要写书评

暂无评论

Bi-Objective Search Method for Bayesian Network Structure Learning

Bi-Objective Search Method for Bayesian Network Structure Le...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Ting Wu Hong Qian Aimin Zhou Zhenzi Li Shanghai Institute of AI for Education School of Computer Science and Technology East China Normal University Shanghai China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China 2012 Labs Huawei Technologies CO. LTD Shenzhen China

ISBN: (纸本)9781665441506

Bayesian network (BN) is a probability graph model, which makes uncertain reasoning logically clearer and more understandable. Structure learning is the first step to learn a BN model. And the score + search methods are a kind of the effective methods to learn the structure. This paper proposes a Bi-Objective Search (BOS) method for Bayesian network structure learning, which considers two objectives, i.e., the log-likelihood score and network complexity. To avoid the illegal structures, BOS samples edges and generates permutations to add directions to the edges for the initial population. To improve the diversity, BOS designs the genetic operators to generate new solutions. The new approach is applied to a set of discrete Bayesian networks, and the experimental results show that the algorithm is superior to the existing algorithms in BN structure learning.

关键词： Conferences Sociology Search problems Genetics Inference algorithms Bayes methods Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Programmable Graphene Metasurface for Terahertz Propagation Control Based on Electromagnetically Induced Transparency

SSRN

引用

SSRN 2023年

作者： Guo, Guanxuan Zhang, Xueqian Niu, Li Wu, Tong Chen, Xieyu Xu, Quan Han, Jiaguang Zhang, Weili Tianjin300072 China Guangxi Key Laboratory of Optoelectronic Information Processing School of Optoelectronic Engineering Guilin University of Electronic Technology Guilin541004 China School of Electrical and Computer Engineering Oklahoma State University StillwaterOK74078 United States

Metasurfaces with programmable functions possess great potential in developing propagation control devices for electromagnetic waves. However, in the terahertz (THz) regime, related metasurfaces are mainly focused on strength tuning and dual-function switching. Here, we propose a programmable graphene metasurface based on the quantum effect analogue, electromagnetically induced transparency. By varying the bias voltages applied to the graphene patterns connected to the dark resonators, the amplitude and phase of the unit cell’s cross-polarized transmission can be continuously tuned and robustly switched between 0 and π, respectively. Based on this, flexible manipulations over the diffraction angles and focal lengths of the transmitted THz beams are achieved in either an amplitude or phase control manner. The proposed programmable scheme may provide new inspirations for designing THz programmable metasurface devices. © 2023, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

MDCN: Multi-scale Dense Cross Network for image super-resolution

arXiv

引用

arXiv 2020年

作者： Li, Juncheng Fang, Faming Li, Jiaqian Mei, Kangfu Zhang, Guixu Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200062 China School of Computer Science and Technology East China Normal University Shanghai200062 China Chinese University of Hong Kong ShenZhen Hong Kong

Convolutional neural networks have been proven to be of great benefit for single-image super-resolution (SISR). However, previous works do not make full use of multi-scale features and ignore the inter-scale correlation between different upsampling factors, resulting in sub-optimal performance. Instead of blindly increasing the depth of the network, we are committed to mining image features and learning the inter-scale correlation between different upsampling factors. To achieve this, we propose a Multi-scale Dense Cross Network (MDCN), which achieves great performance with fewer parameters and less execution time. MDCN consists of multi-scale dense cross blocks (MDCBs), hierarchical feature distillation block (HFDB), and dynamic reconstruction block (DRB). Among them, MDCB aims to detect multi-scale features and maximize the use of image features flow at different scales, HFDB focuses on adaptively recalibrate channel-wise feature responses to achieve feature distillation, and DRB attempts to reconstruct SR images with different upsampling factors in a single model. It is worth noting that all these modules can run independently. It means that these modules can be selectively plugged into any CNN model to improve model performance. Extensive experiments show that MDCN achieves competitive results in SISR, especially in the reconstruction task with multiple upsampling factors. The code will be provided at https://***/MIVRC/MDCN-PyTorch. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal sampling

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：