检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

74 篇 期刊文献
48 篇 会议

馆藏范围

122 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

117 篇 工学
- 83 篇 计算机科学与技术...
- 51 篇 电气工程
- 14 篇 信息与通信工程
- 14 篇 测绘科学与技术
- 12 篇 控制科学与工程
- 12 篇 软件工程
- 11 篇 生物医学工程（可授...
- 6 篇 电子科学与技术（可...
- 6 篇 环境科学与工程（可...
- 5 篇 仪器科学与技术
- 4 篇 机械工程
- 2 篇 动力工程及工程热...
- 2 篇 交通运输工程
- 2 篇 生物工程
- 1 篇 材料科学与工程（可...
- 1 篇 土木工程
38 篇 医学
- 24 篇 临床医学
- 10 篇 特种医学
- 7 篇 基础医学(可授医学...
34 篇 理学
- 12 篇 地球物理学
- 11 篇 物理学
- 6 篇 生物学
- 5 篇 地理学
- 2 篇 数学
- 2 篇 化学
- 1 篇 大气科学
- 1 篇 地质学
7 篇 管理学
- 6 篇 管理科学与工程(可...
3 篇 农学
- 2 篇 作物学
1 篇 教育学
- 1 篇 体育学

主题

122 篇 masked autoencod...
34 篇 self-supervised ...
12 篇 transformer
10 篇 deep learning
10 篇 feature extracti...
9 篇 vision transform...
9 篇 task analysis
9 篇 training
7 篇 transformers
7 篇 contrastive lear...
6 篇 image reconstruc...
5 篇 anomaly detectio...
5 篇 decoding
5 篇 data models
4 篇 graph neural net...
4 篇 computational mo...
4 篇 multimodal
4 篇 point cloud comp...
4 篇 unsupervised lea...
3 篇 three-dimensiona...

机构

2 篇 univ sci & techn...
2 篇 chinese acad sci...
2 篇 univ sci & techn...
2 篇 xidian univ sch ...
2 篇 microsoft res as...
2 篇 south china univ...
2 篇 univ hong kong p...
2 篇 singapore inst t...
2 篇 xidian univ sch ...
2 篇 univ chinese aca...
2 篇 univ massachuset...
1 篇 southeast univ l...
1 篇 xiamen univ sch ...
1 篇 univ sci & techn...
1 篇 henan polytech u...
1 篇 university of sc...
1 篇 north china univ...
1 篇 bournemouth univ...
1 篇 univ hong kong d...
1 篇 univ chinese aca...

作者

3 篇 liu wei
2 篇 chen dongdong
2 篇 song yan
2 篇 zhang xixi
2 篇 huang chao
2 篇 chen dong
2 篇 sadok samir
2 篇 wang min
2 篇 fang wei
2 篇 ye yaowen
2 篇 tao jianhua
2 篇 xu yongshun
2 篇 xia lianghao
2 篇 mcloughlin ian
2 篇 han shuo
2 篇 xu ke
2 篇 sun licai
2 篇 li houqiang
2 篇 rudolph yannick
2 篇 leglaive simon

语言

119 篇 英文
1 篇 中文

检索条件"主题词=Masked AutoEncoder"

共 122 条记录，以下是101-110 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval

Contrastive masked auto-encoders based self-supervised hashi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wei, Rukai Cui, Heng Liu, Yu Xie, Yanzhao Hou, Yufeng Zhou, Ke HUST Wuhan Natl Lab Optoelect Wuhan Peoples R China HUST Sch Software Engn Wuhan Peoples R China HUST Sch Comp Sci & Technol Wuhan Hubei Peoples R China GZU Sch Comp Sci & Cyber Engn Guangzhou Peoples R China

ISBN: (纸本)9798350390155;9798350390162

Implementing cross-modal hashing between 2D images and 3D point-cloud data is a growing concern in real-world retrieval systems. Simply applying existing cross-modal approaches to this new task fails to adequately capture latent multi-modal semantics and effectively bridge the modality gap between 2D and 3D. To address these issues without relying on hand-crafted labels, we propose contrastive masked autoencoders based self-supervised hashing (CMAH) for retrieval between images and point-cloud data. We start by contrasting 2D-3D pairs and explicitly constraining them into a joint Hamming space. This contrastive learning process ensures robust discriminability for the generated hash codes and effectively reduces the modality gap. Moreover, we utilize multi-modal auto-encoders to enhance the model's understanding of multi-modal semantics. By completing the masked image/point-cloud data modeling task, the model is encouraged to capture more localized clues. In addition, the proposed multi-modal fusion block facilitates fine-grained interactions among different modalities. Extensive experiments on three public datasets demonstrate that the proposed CMAH significantly outperforms all baseline methods.

关键词： 3D point-cloud data cross-modal hashing contrastive learning masked autoencoder retrieval

来源：评论

学校读者我要写书评

暂无评论

PATCH INHERENT FEATURE GUIDED MASK SELECTION FOR IMAGE COMPRESSION 49

PATCH INHERENT FEATURE GUIDED MASK SELECTION FOR IMAGE COMPR...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Huang, Xianhan Zhu, Qingmeng Yu, Zhipeng Liu, Kun He, Hao Chinese Acad Sci Inst Software Beijing Peoples R China Beijing Univ Technol Beijing Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Recent advances in Learned Image Compression (LIC) utilize the powerful masked Image Modeling (MIM) framework (e.g., MAE). However, the random masking treats all patches equally, which could lead (i) missing critical information and (ii) poor robustness, since different patches may have different contributions to image reconstruction. The principle experiment shows that the patch-level inherent feature evaluation is highly correlated with the quality of the reconstructed image. Based on this key insight, we propose a simple mask selection approach based on the patch's inherent feature. Specifically, we design plug-and-play frequency and spatial inherent feature modules to select masks, enhancing various MIMs based on the MAE model and achieving high-quality image reconstruction and strong robustness at high mask rates for data-intensive compression tasks.

关键词： Image Compression masked Image Modeling masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

DUAL-BRANCH POLSAR IMAGE CLASSIFICATION BASED ON GRAPHMAE AND LOCAL FEATURE EXTRACTION

DUAL-BRANCH POLSAR IMAGE CLASSIFICATION BASED ON GRAPHMAE AN...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Wang, Yuchen Guo, Ziyi Bi, Haixia Hong, Danfeng Xu, Chen Xi An Jiao Tong Univ Sch Informat & Commun Engn Xian 710049 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Peng Cheng Lab Dept Math & Fundamental Res Shenzhen 518055 Peoples R China Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Peoples R China

ISBN: (纸本)9798350360332;9798350360325

The annotation of polarimetric synthetic aperture radar (PolSAR) images is a labor-intensive and time-consuming process. Therefore, classifying PolSAR images with limited labels is a challenging task in remote sensing domain. In recent years, self-supervised learning approaches have proven effective in PolSAR image classification with sparse labels. However, we observe a lack of research on generative selfsupervised learning in the studied task. Motivated by this, we propose a dual-branch classification model based on generative self-supervised learning in this paper. The first branch is a superpixel-branch, which learns superpixel-level polarimetric representations using a generative self-supervised graph masked autoencoder. To acquire finer classification results, a convolutional neural networks-based pixel-branch is further incorporated to learn pixel-level features. Classification with fused dual-branch features is finally performed to obtain the predictions. Experimental results on the benchmark Flevoland dataset demonstrate that our approach yields promising classification results.

关键词： PolSAR image classification graph neural networks masked autoencoder self-supervised learning convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TrustHeartbeat: A Trustworthy Multimodal Interactive System with Heartbeat Recognition and User Identification

TrustHeartbeat: A Trustworthy Multimodal Interactive System ...

引用

IEEE Conference on Communications and Network Security (CNS)

作者： Zhang, Yan Univ Akron Dept Elect & Comp Engn Akron OH 44325 USA

ISBN: (纸本)9798350375978;9798350375961

The growing popularity of cardiac sensors has led to an increasing demand for smarter interactive systems in disease diagnosis. Various cardiac sensors have emerged as alternatives for heartbeat monitoring and cardiac disease diagnosis, but existing single -modal systems often exhibit biases in real -world applications. In this paper, we propose TrustHeartbeat, a multi modal interactive system that fuses multiple cardiac signals to recognize and identify heartbeat patterns, offering more robust and convenient interaction. TrustHeartbeat is built on a Multi modal masked autoencoder (Mu1tiMAE), capable of reconstructing multi-modal heartbeat signals even when some modalities are unavailable. We further enhance the Mu1tiMAE model by replacing the decoder with a global classifier for classification tasks. TrustHeartbeat fuses embeddings from multiple modalities for downstream tasks, such as heartbeat classification and user identification. A prototype of TrustHeartbeat was implemented and evaluated, with extensive experiments demonstrating its effectiveness. The system achieved Fl -scores of 85% for user identification and 92% for heartbeat recognition, maintaining robustness across different experimental settings.

关键词： masked autoencoder Multimodal Trustworthy

来源：评论

学校读者我要写书评

暂无评论

Self Supervised Temporal Ultrasound Reconstruction for Muscle Atrophy Evaluation 6th

Self Supervised Temporal Ultrasound Reconstruction for Muscl...

引用

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Zhang, Yue Du, Getao Zhan, Yonghua Guo, Kaitai Zheng, Yang Guo, Jianzhong Chen, Xiaoping Liang, Jimin Xidian Univ Sch Elect Engn Xian 710071 Shaanxi Peoples R China Xidian Univ Sch Life Sci & Technol Xian 710071 Shaanxi Peoples R China Shanxi Normal Univ Sch Phys & Informat Technol Xian 710071 Shaanxi Peoples R China China Astronaut Res & Training Ctr Natl Key Lab Human Factors Engn Beijing Peoples R China

ISBN: (纸本)9789819985456;9789819985463

Muscle atrophy is a widespread disease that can reduce quality of life and increase morbidity and mortality. The development of noninvasive method to evaluate muscle atrophy is of great practical value. However, obtaining accurate criteria for the evaluation of muscle atrophy under non-invasive conditions is extremely difficult. This paper proposes a self-supervised temporal ultrasound reconstruction method based on masked autoencoder to explore the dynamic process of muscle atrophy. A score-position embedding is designed to realize the quantitative evaluation of muscle atrophy. Ultrasound images of the hind limb muscle of six macaque monkeys were acquired consecutively during 38 days of head-down bed rest experiments. Given an ultrasound image sequence, an asymmetric encoder-decoder structure is used to reconstruct the randomly masked images for the purpose of modelling the dynamic muscle atrophy process. We demonstrate the feasibility of using the position indicator as muscle atrophy score, which can be used to predict the degree of muscle atrophy. This study achieves the quantitative evaluation of muscle atrophy in the absence of accurate evaluation criteria for muscle atrophy.

关键词： masked autoencoder Muscle atrophy quantization Position embedding Ultrasound image

来源：评论

学校读者我要写书评

暂无评论

masked Scale-Recurrent Network for Incomplete Blurred Image Restoration 1

引用

32nd International Conference on Artificial Neural Networks (ICANN)

作者： Zhu, Jingzhou Chao, Wentao Yang, Dong Beijing Normal Univ Sch Artificial Intelligence Beijing Peoples R China

ISBN: (数字)9783031442230

ISBN: (纸本)9783031442223;9783031442230

Muilti-scale learning has been demonstrated to be an excellent deblurring approach in image restoration according to recent studies. It makes the optimization of the function easier to achieve the global optimum. In order to restore an image that is both incomplete and blurry, we propose a masked Scale-Recurrent Network (MSRN) in this paper, a restoration method based on multi-scale learning and an asymmetric autoencoder. It implements restoration in an end-to-end manner without any prior knowledge or other given conditions. Firstly, we process the GoPro dataset and obtain a dataset of incomplete images. And then, we perform a self-supervised reconstruction pre-training on the autoencoder, with a series of resblocks that increase the quality of the input image and improve the representation learning in the latent space. Finally, on the processed data, we train the model and finish the adjustment of the entire network. Compared with classical multi-scale learning, we introduce masks to help the model train more efficiently by focusing on essential regions of the image. It is also shown that MSRN has successful image restoration capability as well as robustness, as demonstrated in our experiments.

关键词： image restoration masked autoencoder residual network scale-recurrent network multi-scale learning

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning of 3D Point Clouds: A Survey 36

Self-Supervised Learning of 3D Point Clouds: A Survey

引用

36th Chinese Control and Decision Conference (CCDC)

作者： Guo, Qi Liu, Wei Zhao, Qixi Ning, Zuotao Cheng, Shuai Hu, Jun Northeastern Univ Coll Informat Sci & Engn Shenyang Peoples R China Neusoft Reach Automot Technol Ltd Shenyang Peoples R China

ISBN: (纸本)9798350387780;9798350387797

The use of 3D point cloud is widespread in robotics and autonomous driving systems. With the development of deep learning, an increasing number of models are being proposed to address tasks in 3D point cloud processing, including shape classification and 3D object detection. However, training these models requires large amounts of labeled data, which is expensive to obtain. Therefore, self-supervised learning methods for 3D point clouds have recently gained significant attention, which train the model with unlabeled data by designing pretext tasks. This paper aims to review these methods. Based on the pretext tasks designed, we divide those more than 30 existing methods into three categories: reconstruction-based, contrastive-based and MAE(masked autoencoder)-based methods. Then, we introduce the research motivations, implementations and characteristics of these methods one by one. Finally, two performance evaluation criteria are introduced and the performance of each selfsupervised learning method is assessed and analyzed based on these criteria.

关键词： Self-supervised learning Pre-train 3D Point clouds Contrastive learning masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Community-Guided Contrastive Learning with Anomaly-Aware Reconstruction for Anomaly Detection on Attributed Networks 29th

Community-Guided Contrastive Learning with Anomaly-Aware Rec...

引用

29th International Conference on Database Systems for Advanced Applications (DASFAA)

作者： Wang, Yang Wang, Xinye He, Chengxin Chen, Xiaocong Luo, Zhaohang Duan, Lei Zuo, Jie Sichuan Univ Sch Comp Sci Chengdu Peoples R China Nucl Power Inst China Chengdu Peoples R China

ISBN: (纸本)9789819755745;9789819755752

Anomaly detection on attributed networks is of wide practical application in many domains, such as business and cybersecurity. Typically, existing methods mainly focus on utilizing the graph neural networks (GNNs) that aggregate information from neighbors to learn node representations for detecting anomalies. However, it may ignore the information beyond the neighbors like community associations. Furthermore, roughly stacking multiple GNNs layers may lead to the over-smoothing problem, making nodes representations more similar and anomalies undistinguishable. In this paper, we propose a novel method, named CARD, to tackle these issues. Specifically, we propose different augmentation strategies to offer diverse scale information for CARD. Then, to better capture community associations, we establish a community-guided contrastive learning module that can capture different scale of structure information as well. To capture multiple attribute information and aid in anomaly detection, we design an anomaly-aware masked autoencoder, effectively making anomalies more distinguished. Extensive experiments on nine datasets show the superiority of CARD. Our code are available at https://***/scu-kdde/OAM-CARD-2024.

关键词： Anomaly detection Attributed networks Community structure masked autoencoder Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

MSTEM: masked Spatiotemporal Event Series Modeling for Urban Undisciplined Events Forecasting 24

MSTEM: Masked Spatiotemporal Event Series Modeling for Urban...

引用

33rd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Gu, Zehao Zhou, Shiyang Xiong, Yun Luo, Yang Ren, Hongrun Wang, Qiang Gao, Xiaofeng Yu, Philip Fudan Univ Sch Comp Sci Shanghai Key Lab Data Sci Shanghai Peoples R China Shanghai Jiao Tong Univ Dept Comp Sci & Engn MoE Key Lab Artificial Intelligence Shanghai Peoples R China Shanghai Ctr Meteorol Disaster Prevent Technol Shanghai Peoples R China Univ Illinois Chicago IL USA

ISBN: (纸本)9798400704369

Urban undisciplined events (UUE) are of increasing concern to urban officials because they reduce the quality of life and cause societal disorder. How to accurately predict future occurrences is a key point in preventing these events. However, existing supervised methods struggle to perform well on sparse UUEs while self-supervised MAE-based methods adopt a traditional random masking strategy which leads to limited performance on UUE forecasting. Fortunately, we have designed an innovative spatiotemporal masking strategy and its corresponding pre-training task called masked Spatio-Temporal Event Series Modeling (MSTEM). Through Cluster-assisted region masking, MSTEM efficiently distributes masked regions evenly among different clusters, enhancing the model's ability to capture spatial correlation and heterogeneity while addressing sparse region distribution of UUEs. Frequency-enhanced patch masking helps the model to sufficiently extract the temporal features of UUEs by reconstructing multiple views. Additionally, we propose future merge and cluster label modeling to enhance the extraction of spatiotemporal dependencies, thereby improving the performance of MSTEM on downstream prediction tasks. Experimental evaluations on four real-world datasets including crimes and disorderly conduct show that our masked autoencoder with MSTEM outperforms most of the state-of-the-art baselines.

关键词： Spatiotemporal Prediction masked autoencoder Self-supervised learning Smart City

来源：评论

学校读者我要写书评

暂无评论

DART: DEFORMABLE ANATOMY-AWARE REGISTRATION TOOLKIT FOR LUNG CT REGISTRATION WITH KEYPOINTS SUPERVISION 21

DART: DEFORMABLE ANATOMY-AWARE REGISTRATION TOOLKIT FOR LUNG...

引用

21st IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Zhu, Yunzheng Zhuang, Luoting Lin, Yannan Zhang, Tengyue Tabatabaei, Hossein Aberle, Denise R. Prosper, Ashley E. Chien, Aichi Hsu, William UCLA David Geffen Sch Med Dept Radiol Sci Med & Imaging Informat Los Angeles CA 90095 USA UCLA Dept Elect & Comp Engn Samueli Sch Engn Los Angeles CA 90095 USA UCLA Med Informat Home Area Grad Programs Biosci Los Angeles CA USA UCLA Dept Comp Sci Samueli Sch Engn Los Angeles CA USA UCLA David Geffen Sch Med Dept Radiol Sci Los Angeles CA USA UCLA Dept Bioengn Samueli Sch Engn Los Angeles CA USA

ISBN: (纸本)9798350313345;9798350313338

Spatially aligning two computed tomography (CT) scans of the lung using automated image registration techniques is a challenging task due to the deformable nature of the lung. However, existing deep-learning-based lung CT registration models are not trained with explicit anatomical knowledge. We propose the deformable anatomy-aware registration toolkit (DART), a masked autoencoder (MAE)-based approach, to improve the keypoint-supervised registration of lung CTs. Our method incorporates features from multiple decoders of networks trained to segment anatomical structures, including the lung, ribs, vertebrae, lobes, vessels, and airways, to ensure that the MAE learns relevant features corresponding to the anatomy of the lung. The pretrained weights of the transformer encoder and patch embeddings are then used as the initialization for the training of downstream registration. We compare DART to existing state-of-the-art registration models. Our experiments show that DART outperforms the baseline models (Voxelmorph, ViT-V-Net, and MAE-TransRNet) in terms of target registration error of both corrField-generated keypoints with 17%, 13%, and 9% relative improvement, respectively, and bounding box centers of nodules with 27%, 10%, and 4% relative improvement, respectively. Our implementation is available at https://***/yunzhengzhu/DART.

关键词： Lung image registration masked autoencoder Anatomy-Aware Pretraining

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共13页 << < 4 5 6 7 8 9 10 11 12 13 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：