检索结果-内蒙古大学图书馆

Several progress of semi-supervised learning

Journal of information and Computational Science 2009年第1期6卷 211-217页

作者： Ding, Shifei Su, Chunyang Jia, Weikuan Jin, Fengxiang Shi, Zhongzhi School of Computer Science and Technology China University of Mining and Technology Xuzhou 221008 China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences Beijing 100080 China College of Plant Protection Shandong Agricultural University Taian 271018 China College of Geoinformation Science and Engineering Shandong University of Science and Technology Qingdao 266510 China

In this paper we discuss several progress of semi-supervised learning, making emphasis on semi-supervised classification. First, we introduce the history and basic concept and methods of semi-supervised learning, then explain the algorithms of semi-supervised learning in details, and discuss the current situation of semi-supervised learning, at last we look forward to the development trend of semi-supervised learning. © 2009 Binary information Press.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition for In-the-wild Videos

Facial Expression Recognition for In-the-wild Videos

引用

International Conference on Automatic Face and Gesture Recognition

作者： Hanyu Liu Jiabei Zeng Shiguang Shan Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728130798

ISBN: (纸本)9781728130804

In this paper, we propose a method for facial expression recognition for in-the-wild videos. Our method combines Deep Residual Network (ResNet) and Bidirectional Recurrent Neutral Network with Long-Short-Term Memory Unit (BLSTM). This method won the 2 nd place in the seven basic expression classification track of Affective Behavior Analysis in-the-wild Competition held in conjunction with the IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2020, achieving 66.9% accuracy and 40.8% final metric on the test set. We also visualize the learned attention maps and analyze the importance of different regions in facial expression recognition.

关键词： Face recognition Videos Feature extraction Training Conferences computer vision Mouth

来源：评论

学校读者我要写书评

暂无评论

Edge-Preserving Multi-Exposure Fusion with Guided Filtering for Structural Patch Decomposition

Edge-Preserving Multi-Exposure Fusion with Guided Filtering ...

引用

IEEE International Conference on Electronic information and Communication technology (ICEICT)

作者： Yang Zhen Junwei Qi Yingsong Li College of Information and Communication Engineering Harbin Engineering University Harbin China College of Computer Science and Technology Harbin Engineering University Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

Multi-exposure image fusion (MEF) is one of the effective ways to obtain high dynamic range (HDR) images. Multi-scale structural patch decomposition based MEF(MSPD) and edge-preserving structural patch decomposition (MESPD) have achieved state-of-the-art fusion quality. MESPD incorporates edge-preserving factors into MSPD to preserve details in a single-scale setting. However, we find that the edge-preserving factors put too much emphasis on the edge, resulting in artifacts on some edges and loss of details. To tackle this issue, guided filter is introduced into MSPD, which is directly used as an edge-preserving filter instead of mean filter to implicitly decompose images. In addition, we have designed a flexible adaptive weight, which can further maintain details of the light and dark areas. Likewise, we inherit MESPD and MSPD to extend our method to multi-scale framework. Extensive experimental results demonstrate our method can produce satisfactory results in both static and dynamic scenes with fewer artifacts and low computational cost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolution and Attention Mixer for Synthetic Aperture Radar Image Change Detection

arXiv

引用

arXiv 2023年

作者： Zhang, Haopeng Lin, Zijing Gao, Feng Dong, Junyu Du, Qian Li, Heng-Chao The School of Computer Science and Technology Ocean University of China Qingdao266100 China The Department of Electrical and Computer Engineering Mississippi State University StarkvilleMS39762 United States The Sichuan Provincial Key Laboratory of Information Coding and Transmission Southwest Jiaotong University Chengdu610031 China

Synthetic aperture radar (SAR) image change detection is a critical task and has received increasing attentions in the remote sensing community. However, existing SAR change detection methods are mainly based on convolutional neural networks (CNNs), with limited consideration of global attention mechanism. In this letter, we explore Transformer-like architecture for SAR change detection to incorporate global attention. To this end, we propose a convolution and attention mixer (CAMixer). First, to compensate the inductive bias for Transformer, we combine self-attention with shift convolution in a parallel way. The parallel design effectively captures the global semantic information via the self-attention and performs local feature extraction through shift convolution simultaneously. Second, we adopt a gating mechanism in the feed-forward network to enhance the non-linear feature transformation. The gating mechanism is formulated as the element-wise multiplication of two parallel linear layers. Important features can be highlighted, leading to high-quality representations against speckle noise. Extensive experiments conducted on three SAR datasets verify the superior performance of the proposed CAMixer. The source codes will be publicly available at https://***/summitgao/CAMixer. © 2023, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

On Secrecy Performance of MISO SWIPT Systems with TAS and Imperfect CSI

On Secrecy Performance of MISO SWIPT Systems with TAS and Im...

引用

作者： Pan, Gaofeng Lei, Hongjiang Deng, Yansha Fan, Lisheng Yang, Jing Chen, Yunfei Ding, Zhiguo Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing School of Electronic and Information Engineering Southwest University Chongqing400715 China School of Computing and Communications Lancaster University LancasterLA14YW United Kingdom Chongqing Key Laboratory of Mobile Communications Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Centre for Telecommunications King's College London LondonWC2R2LS United Kingdom School of Computer Science and Educational Software Guangzhou University Guangzhou510000 China Department of Electronic Engineering Shantou University Guangdong515063 China School of Information Engineering Yangzhou University Yangzhou225009 China School of Engineering University of Warwick CoventryCV47AL United Kingdom

In this paper, a multiple-input single-output (MISO) simultaneous wireless information and power transfer (SWIPT) system, including one base station (BS) equipped with multiple antennas, one desired single-antenna information receiver (IR), and N (N > 1) single-antenna energy-harvesting receivers (ERs) is considered. Assuming that the information signal to the desired IR may be eavesdropped by ERs if ERs are malicious, we investigate the secrecy performance of the target MISO SWIPT system when imperfect channel state information (CSI) is available and adopted for transmit antenna selection at the BS. Considering that each eavesdropping link experiences independent but not necessarily identically distributed Rayleigh fading, the closed-form expressions for the exact and the asymptotic secrecy outage probability, and the average secrecy capacity are derived and verified by simulations. Furthermore, the optimal power splitting factor is derived for each ER to realize the tradeoff between the energy harvesting and the information eavesdropping. Our results reveal the impact of the imperfect CSI on the secrecy performance of MISO SWIPT systems in the presence of multiple wiretap channels. © 2016 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Provable Data Possession Supporting Secure Data Transfer for Cloud Storage

Provable Data Possession Supporting Secure Data Transfer for...

引用

International Conference on Broadband, Wireless Computing, Communication and Applications (BWCCA)

作者： Yong Yu Jianbing Ni Wei Wu Yilei Wang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Fujian Provincial Key Laboratory of Network Security and Cryptology Fujian Normal University Fuzhou China

ISBN: (纸本)9781467383165

Due to the appealing advantages of cloud storage, such as on-demand self-service and ubiquitous network access, an increasing number of users prefer to store their data on remote remote servers. However, outsourced data transfer becomes a critical requirement for users to shift their cloud storage providers because of the emergence of various cloud storage services with different qualities of services. Therefore, the users may not only be anxious about the state of their data on the cloud server, but also concern on whether the data are transferred entirely to the new cloud without corruption and whether the data on original cloud are discarded. To address these problems, we propose a provable data possession scheme for cloud storage services characterized by secure data transfer, provable data erasure, high error detection probability, confidential data storage. Our scheme can guarantee the remote data integrity when the data are maintaining on the cloud servers and are transferring between two clouds, and secure deletion of transferred data on the original cloud.

关键词： Cloud computing Data transfer Servers Cryptography Reliability Distributed databases

来源：评论

学校读者我要写书评

暂无评论

A novel dataset and a two-stage mitosis nuclei detection method based on hybrid anchor branch

arXiv

引用

arXiv 2023年

作者： Wang, Huadeng Xu, Hao Li, Bingbing Pan, Xipeng Zeng, Lingqi Lan, Rushi Luo, Xiaonan School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China Department of Pathology Ganzhou Municipal Hospital Ganzhou341000 China

Mitosis detection is one of the challenging problems in computational pathology, and mitotic count is an important index of cancer grading for pathologists. However, current counts of mitotic nuclei rely on pathologists looking microscopically at the number of mitotic nuclei in hot spots, which is subjective and time-consuming. In this paper, we propose a two-stage cascaded network, named FoCasNet, for mitosis detection. In the first stage, a detection network named Mdet is proposed to detect as many mitoses as possible. In the second stage, a classification network Mclass is proposed to refine the results of the first stage. In addition, the attention mechanism, normalization method, and hybrid anchor branch classification subnet are introduced to improve the overall detection performance. Our method achieves the current highest F1-score of 0.888 on the public dataset ICPR 2012. We also evaluated our method on the GZMH dataset released by our research team for the first time and reached the highest F1-score of 0.563, which is also better than multiple classic detection networks widely used at present. It confirmed the effectiveness and generalization of our method. The code will be available at: https://***/antifen/mitosis-nuclei-detection. Copyright © 2023, The Authors. All rights reserved.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

ShapeMamba-EM: Fine-Tuning Foundation Model with Local Shape Descriptors and Mamba Blocks for 3D EM Image Segmentation

arXiv

引用

arXiv 2024年

作者： Shi, Ruohua Pang, Qiufan Ma, Lei Duan, Lingyu Huang, Tiejun Jiang, Tingting National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China State Key Laboratory of Multimedia Information Processing School of Computer Science Peking University Beijing China National Biomedical Imaging Center Peking University Beijing China Peng Cheng Laboratory Shenzhen China

Electron microscopy (EM) imaging offers unparalleled resolution for analyzing neural tissues, crucial for uncovering the intricacies of synaptic connections and neural processes fundamental to understanding behavioral mechanisms. Recently, the foundation models have demonstrated impressive performance across numerous natural and medical image segmentation tasks. However, applying these foundation models to EM segmentation faces significant challenges due to domain disparities. This paper presents ShapeMamba-EM, a specialized fine-tuning method for 3D EM segmentation, which employs adapters for long-range dependency modeling and an encoder for local shape description within the original foundation model. This approach effectively addresses the unique volumetric and morphological complexities of EM data. Tested over a wide range of EM images, covering five segmentation tasks and 10 datasets, ShapeMamba-EM outperforms existing methods, establishing a new standard in EM image segmentation and enhancing the understanding of neural tissue architecture. © 2024, CC BY-NC-SA.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

LC-Beating: An Online System for Beat and Downbeat Tracking using Latency-Controlled Mechanism

LC-Beating: An Online System for Beat and Downbeat Tracking ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xinlu Liu Jiale Qian Qiqi He Yi Yu Wei Li School of Computer Science and Technology Fudan University Shanghai China Digital Content and Media Sciences Research Division National Institute of Informatics (NII) Tokyo Japan Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

Beat and downbeat tracking is to predict beat and downbeat time steps from a given music piece. Some deep learning models with a dilated structure such as Temporal Convolutional Network (TCN) and Dilated Self-Attention Network (DSAN) have achieved promising performance for this task. However, most of them have to see the whole music context during inference, which limits their deployment to online systems. In this paper, we propose LC-Beating, a novel latency-controlled (LC) mechanism for online beat and downbeat tracking, in which the model only looks ahead a few frames. By appending limited future information, the model can better capture the activity of relevant musical beats, which significantly boosts the performance of online algorithms with limited latency. Moreover, LC-Beating applies a novel real-time implementation of the LC mechanism to TCN and DSAN. The experimental results show that our proposed method outperforms the previous online models by a large margin and is close to the results of the offline models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CSCL-DTI: predicting drug-target interaction through cross-view and self-supervised contrastive learning

CSCL-DTI: predicting drug-target interaction through cross-v...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xuan Lin Xi Zhang Zu-Guo Yu Yahui Long Xiangxiang Zeng Philip S. Yu College of Computer Science Xiangtan University China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University China Singapore Immunology Network (SIgN) Agency for Science Technology and Research (A*STAR) Singapore College of Information Science and Engineering Hunan University China Department of Computer Science University of Illinois Chicago USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Accurately predicting drug-target interactions (DTI) is a critical step in drug discovery. Existing methods of DTI prediction primarily employ Simplified Molecular-Input Line-Entry System (SMILES) sequences or molecular graphs to learn drug representations. However, the features learned by such single-view approach is prone to incomplete. While some multiview methods that consider the views of both SMILES sequences and molecular graphs have been developed, these methods often fall in short in capturing potential interactions between views. In this work, we propose a novel dual contrastive learning framework CSCL-DTI for DTI prediction. First, we design a contrastive-enhanced cross-view representation learning (CVRL) to learn representations for drugs. In this module, Transformer-based and graph convolutional network (GCN)-based encoders are separately adopted to learn view-specific representations, followed by contrastive learning to enrich the representations by accounting for the potential interplay between local chemical context and topological structure. Second, we combine Transformer with self-supervised contrastive learning (SSCL) to learn representations for targets by modelling protein amino acids sequences. The scheme allows to effectively preserve the intrinsic characteristics of the sequences. Finally, we introduce a bilinear attention network to obtain an integrated representation by adaptively incorporating drug and target representations. Benchmarking experiments on two datasets demonstrated that CSCL-DTI 1 outperforms six state-of-the-art methods.

关键词： Drugs Proteins Representation learning Protein engineering Adaptation models Contrastive learning Predictive models Transformers Amino acids Diffusion tensor imaging

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：