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

70 篇 期刊文献
48 篇 会议

馆藏范围

118 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

110 篇 工学
- 78 篇 计算机科学与技术...
- 45 篇 电气工程
- 13 篇 测绘科学与技术
- 11 篇 信息与通信工程
- 10 篇 生物医学工程（可授...
- 9 篇 软件工程
- 8 篇 控制科学与工程
- 6 篇 环境科学与工程（可...
- 5 篇 仪器科学与技术
- 3 篇 机械工程
- 2 篇 电子科学与技术（可...
- 2 篇 交通运输工程
- 2 篇 生物工程
- 1 篇 动力工程及工程热...
- 1 篇 土木工程
- 1 篇 石油与天然气工程
- 1 篇 农业工程
- 1 篇 网络空间安全
37 篇 医学
- 24 篇 临床医学
- 9 篇 特种医学
- 7 篇 基础医学(可授医学...
32 篇 理学
- 11 篇 地球物理学
- 10 篇 物理学
- 6 篇 生物学
- 5 篇 地理学
- 2 篇 数学
- 2 篇 化学
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

118 篇 masked autoencod...
33 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
6 篇 contrastive lear...
5 篇 anomaly detectio...
5 篇 decoding
5 篇 image reconstruc...
5 篇 data models
4 篇 graph neural net...
4 篇 computational mo...
4 篇 multimodal
4 篇 unsupervised lea...
3 篇 eeg
3 篇 accuracy

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 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...
1 篇 univ malaya fac ...

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

116 篇 英文
1 篇 德文
1 篇 法文
1 篇 中文

检索条件"主题词=masked autoencoder"

共 118 条记录，以下是31-40 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：

AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual masked autoencoder 35

AV-MaskEnhancer: Enhancing Video Representations through Aud...

引用

35th IEEE International Conference on Tools with Artificial Intelligence (ICTAI)

作者： Diao, Xingjian Cheng, Ming Cheng, Shitong Dartmouth Coll Dept Comp Sci Hanover NH 03755 USA

ISBN: (纸本)9798350342734

Learning high-quality video representation has shown significant applications in computer vision and remains challenging. Previous work based on mask autoencoders such as ImageMAE [10] and VideoMAE [23] has proven the effectiveness of learning representations in images and videos through reconstruction strategy in the visual modality. However, these models exhibit inherent limitations, particularly in scenarios where extracting features solely from the visual modality proves challenging, such as when dealing with low-resolution and blurry original videos. Based on this, we propose AV-MaskEnhancer for learning high-quality video representation by combining visual and audio information. Our approach addresses the challenge by demonstrating the complementary nature of audio and video features in cross-modality content. Moreover, our result of the video classification task on the UCF101 [21] dataset outperforms the existing work and reaches the state-of-the-art, with a top-1 accuracy of 98.8% and a top-5 accuracy of 99.9%.

关键词： masked autoencoder audio-visual video representation cross-modality video reconstruction video classification

来源：评论

学校读者我要写书评

暂无评论

DP-MAE: A DUAL-PATH masked autoencoder BASED SELF-SUPERVISED LEARNING METHOD FOR ANOMALOUS SOUND DETECTION 49

DP-MAE: A DUAL-PATH MASKED AUTOENCODER BASED SELF-SUPERVISED...

引用

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

作者： Liu, Zhuo-Li Song, Yan Zeng, Xiao-Min Dai, Li-Rong McLoughlin, Ian Univ Sci & Technol China Natl Engn Res Ctr Speech & Language Informat Proc Hefei Peoples R China Singapore Inst Technol ICT Cluster Singapore Singapore

ISBN: (纸本)9798350344868;9798350344851

In this paper, we present a novel general-purpose audio representation learning method named Dual-Path masked autoencoder (DP-MAE) for anomalous sound detection (ASD) task. Existing methods mainly focus on frame-level generative methods or clip-level discriminative methods, which generally ignore the local information where anomalies are usually found more easily. Moreover, they apply multiple systems on one ASD task, which is lacking in generalizability. For tracking this, our method extracts patch-level features to learn unified audio representation that generalizes well and models local information that is beneficial to detecting anomalies under domain shifts by self-supervised representation learning and it further optimizes the informativeness of clip-level representations in fine-tuning. Concretely, the input spectrograms are randomly split into two patch-level subsets, and then they are fed into DP-MAE to predict each other. Meanwhile, the output of one path is also considered to be the predicted objective of the other path to perform regularization from the perspective of self-distillation. In fine-tuning stage, a linear classifier is applied on the features produced by the encoder to get a more compact representation of normal sound. Experiments on DCASE 2022 Challenge Task2 development dataset show the effectiveness of our method.

关键词： Self-supervised learning masked autoencoder Anomalous Sound Detection

来源：评论

学校读者我要写书评

暂无评论

Image Anomaly Detection and Localization Using masked autoencoder 29th

Image Anomaly Detection and Localization Using Masked Autoen...

引用

29th International Conference on Neural Information Processing

作者： Yu, Xiaohuo Guo, Jiahao Wang, Lu Shanghai Univ Sch Comp Engn & Sci Shanghai Peoples R China

ISBN: (纸本)9789819916443;9789819916450

Generally speaking, abnormal images are distinguished from normal images in terms of content or semantics. Image anomaly detection is the task of identifying anomalous images that deviate from normal images. Reconstruction based methods detect anomaly using the difference between the original image and the reconstructed image. These methods assume that the model will be unable to properly reconstruct anomalous images. But in practice, anomalous regions are often reconstructed well due to the network's generalization ability. Recent methods propose to decrease this effect by turning the generative task to an inpainting problem. By conditioning on the neighborhood of the masked part, small anomalies will not contribute to the reconstrued image. However, it is hard to reconstruct the masked regions when neighborhood exists much anomalous information. We suggest that it should include more useful information of the image when doing inpainting. Inspired by masked autoencoder (MAE), we propose a new anomaly detection method, which called MAE-AD. The architecture of the method can learn global information of the image, and it can avoid being affected by the large anomalous region. We evaluate our method on the MVTec AD dataset, and the results outperform the previous inpainting based approach. In comparison with the methods which use pre-trained models, MAE-AD also has a competitive performance.

关键词： Anomaly detection masked autoencoder Image inpainting

来源：评论

学校读者我要写书评

暂无评论

Flow-MAE: Leveraging masked autoencoder for Accurate, Efficient and Robust Malicious Traffic Classification 23

Flow-MAE: Leveraging Masked AutoEncoder for Accurate, Effici...

引用

26th International Symposium on Research in Attacks, Intrusions and Defenses (RAID)

作者： Hang, Zijun Lu, Yuliang Wang, Yongjie Xie, Yi Natl Univ Def Technol Hefei Peoples R China

ISBN: (纸本)9798400707650

Malicious traffic classification is crucial for Intrusion Detection Systems (IDS). However, traditional Machine Learning approaches necessitate expert knowledge and a significant amount of well-labeled data. Although recent studies have employed pre-training models from the Natural Language Processing domain, such as ET-BERT, for traffic classification, their effectiveness is impeded by limited input length and fixed Byte Pair Encoding. To address these challenges, this paper presents Flow-MAE, a pretraining model that employs masked autoencoders (MAE) from the Computer Vision domain to achieve accurate, efficient, and robust malicious network traffic classification. Flow-MAE overcomes these challenges by utilizing burst (a generic representation of network traffic) and patch embedding to accommodate extensive traffic length. Moreover, Flow-MAE introduces a self-supervised pre-training task, the masked Patch Model, which captures unbiased representations from bursts with varying lengths and patterns. Experimental results from six datasets reveal that Flow-MAE achieves new state-of-the-art accuracy (>0.99), efficiency (>900 samples/s), and robustness across diverse network traffic types. In comparison to the state-of-the-art ET-BERT, Flow-MAE exhibits improvements in accuracy and speed by 0.41%-1.93% and 7.8x-10.3x, respectively, while necessitating only 0.2% FLOPs and 44% memory overhead. The efficacy of the core designs is validated through few-shot learning and ablation experiments. The code is publicly available at https://***/NLear/Flow-MAE.

关键词： Malicious Traffic Classification masked autoencoder Pre-training Model masked Patch Model

来源：评论

学校读者我要写书评

暂无评论

DB-PMAE: Dual-Branch Prototypical masked autoencoder with locality for domain robust speaker verification 25

DB-PMAE: Dual-Branch Prototypical Masked AutoEncoder with lo...

引用

25th Interspeech Conference

作者： Xie, Wei-lin Xi, Yu-Xuan Song, Yan Zhang, Jian-tao Song, Hao-yu McLoughlin, Ian Univ Sci & Technol China Natl Engn Res Ctr Speech & Language Informat Proc Hefei Peoples R China Australian Natl Univ Canberra ACT Australia Singapore Inst Technol ICT Cluster Singapore Singapore

Existing speaker verification (SV) systems mainly consist of a frontend deep embedding network pretrained for speaker identification (SID) followed by a backend network finetuned to provide a similarity measure. Despite their success, the performance may degrade remarkably due to domain mismatch. In this paper, we present a novel dual-branch prototypical masked autoencoder (DB-PMAE) based SRE framework. Specifically, the teacher and student branches with siamese encoders are pre-trained to jointly learn patch-level features and prototypes. A multi-task learning framework is exploited for finetuning with SID and SV tasks, where the similarity is measured by finding local correspondence to improve domain robustness. Experiments on CNCeleb corpus demonstrate the superiority of DB-PMAE.

关键词： Speaker Verification Self-supervised learning masked autoencoder Domain Robustness

来源：评论

学校读者我要写书评

暂无评论

DHMAE: A Disentangled Hypergraph masked autoencoder for Group Recommendation 47

DHMAE: A Disentangled Hypergraph Masked Autoencoder for Grou...

引用

47th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Zhao, Yingqi Zhang, Haiwei Bai, Qijie Nie, Changli Yuan, Xiaojie Nankai Univ TJ Key Lab NDST Coll CS Tianjin Peoples R China

ISBN: (纸本)9798400704314

Group recommendation aims to suggest items to a group of users that are suitable for the group. Although some existing powerful deep learning models have achieved improved performance, various aspects remain unexplored: (1) Most existing models using contrastive learning tend to rely on high-quality data augmentation which requires precise contrastive view generation;(2) There is multifaceted natural noise in group recommendation, and additional noise is introduced during data augmentation;(3) Most existing hypergraph neural network-based models over-entangle the information of members and items, ignoring their unique characteristics. In light of this, we propose a highly effective Disentangled Hypergraph masked autoencoder-enhanced method for group recommendation (DHMAE), combining a disentangled hypergraph neural network with a graph masked autoencoder. This approach creates self-supervised signals without data augmentation by masking the features of some nodes and hyperedges and then reconstructing them. For the noise problem, we design a masking strategy that relies on pre-computed degree-sensitive probabilities for the process of masking features. Furthermore, we propose a disentangled hypergraph neural network for group recommendation scenarios to extract common messages of members and items and disentangle them during the convolution process. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art models and effectively addresses the noise issue.

关键词： Group Recommendation Graph Neural Networks masked autoencoder Self-Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

A VECTOR QUANTIZED masked autoencoder FOR SPEECH EMOTION RECOGNITION

A VECTOR QUANTIZED MASKED AUTOENCODER FOR SPEECH EMOTION REC...

引用

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

作者： Sadok, Samir Leglaive, Simon Seguier, Renaud CentraleSupelec IETR UMR CNRS 6164 Gif Sur Yvette France

ISBN: (纸本)9798350302615

Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data remains a significant challenge in the field. Self-supervised learning has recently emerged as a promising solution to address this challenge. In this paper, we propose the vector quantized masked autoencoder for speech (VQ-MAE-S), a self-supervised model that is fine-tuned to recognize emotions from speech signals. The VQ-MAE-S model is based on a masked autoencoder (MAE) that operates in the discrete latent space of a vector quantized variational autoencoder. Experimental results show that the proposed VQ-MAE-S model, pre-trained on the VoxCeleb2 dataset and fine-tuned on emotional speech data, outperforms an MAE working on the raw spectrogram representation and other state-of-the-art methods in SER.

关键词： Self-supervised learning masked autoencoder vector-quantized variational autoencoder speech emotion recognition

来源：评论

学校读者我要写书评

暂无评论

MAE-DFER: Efficient masked autoencoder for Self-supervised Dynamic Facial Expression Recognition 23

MAE-DFER: Efficient Masked Autoencoder for Self-supervised D...

引用

31st ACM International Conference on Multimedia (MM)

作者： Sun, Licai Lian, Zheng Liu, Bin Tao, Jianhua Univ Chinese Acad Sci Chinese Acad Sci Inst Automat Sch Artificial Intelligence Beijing Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Chinese Acad Sci Inst Automat Beijing Peoples R China Tsinghua Univ Dept Automat Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Beijing Peoples R China

ISBN: (纸本)9798400701085

Dynamic facial expression recognition (DFER) is essential to the development of intelligent and empathetic machines. Prior efforts in this field mainly fall into supervised learning paradigm, which is severely restricted by the limited labeled data in existing datasets. Inspired by recent unprecedented success of masked autoencoders (e.g., VideoMAE), this paper proposes MAE-DFER, a novel self-supervised method which leverages large-scale self-supervised pretraining on abundant unlabeled data to largely advance the development of DFER. Since the vanilla Vision Transformer (ViT) employed in VideoMAE requires substantial computation during fine-tuning, MAE-DFER develops an efficient local-global interaction Transformer (LGI-Former) as the encoder. Moreover, in addition to the standalone appearance content reconstruction in VideoMAE, MAE-DFER also introduces explicit temporal facial motion modeling to encourage LGI-Former to excavate both static appearance and dynamic motion information. Extensive experiments on six datasets show that MAE-DFER consistently outperforms state-of-the-art supervised methods by significant margins (e.g., +6.30% UAR on DFEW and +8.34% UAR on MAFW), verifying that it can learn powerful dynamic facial representations via large-scale self-supervised pre-training. Besides, it has comparable or even better performance than VideoMAE, while largely reducing the computational cost (about 38% FLOPs). We believe MAE-DFER has paved a new way for the advancement of DFER and can inspire more relevant research in this field and even other related tasks. Codes and models are publicly available at https://***/sunlicai/MAE-DFER.

关键词： Dynamic facial expression recognition masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

ROBUST FACE RECOGNITION BASED ON AN ANGLE-AWARE LOSS AND masked autoencoder PRE-TRAINING 49

ROBUST FACE RECOGNITION BASED ON AN ANGLE-AWARE LOSS AND MAS...

引用

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

作者： Choi, Jaehyeop Kim, Youngbaek Lee, Younghyun NCSOFT Corp Vision AI Lab NC Res Seongnam South Korea

ISBN: (纸本)9798350344868;9798350344851

Despite the advances in deep learning techniques, accurate identification using face recognition (FR) systems remains challenging owing to changes in face angles, bad lighting, and occlusions. To address these problems, we propose an optimized approach to improve the robustness of feature extraction models that are used in FR systems. The proposed method leverages an angle-aware loss function, inspired by ArcFace, that provides a large margin for significantly rotated faces. Additionally, a pre-trained weight initialization was derived from a masked autoencoder to enhance the ability of the model to cope with various poor conditions. The experimental results indicate that the proposed method outperforms existing face recognition methods in both normal and adverse environments.

关键词： Face recognition angle-aware loss function masked autoencoder weight initialization feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Representation Learning Method for MTC Using masked autoencoder 23

An Unsupervised Representation Learning Method for MTC Using...

引用

23rd IEEE International Conference on Communication Technology, ICCT 2023

作者： Xu, Ke Zhang, Xixi Huang, Shennan Zhang, Lanping Shi, Shengnan College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9798350325959

Malware traffic classification (MTC) is one of the promising methods to ensure the cybersecurity, which involves identifying and categorizing network traffic to distinguish between benign and malicious activity. Traditional MTC methods, such as port-based and DPI-based approaches, have become obsolete due to their limitations. The deep learning (DL) based methods attract much attention due to their strong feature mining ability. Nevertheless, these methods depend on abundant labeled training samples, which can be expensive to obtain. To address this problem, this paper proposes a novel unsupervised method for MTC with the framework of masked autoencoder. The proposed method is able to mine features from large amounts of unlabeled data, eliminating the reliance on labels. The random mask strategy in the method can effectively reduce the redundant information in the sample, which accelerates the training process and improves the classification performance. Experiments show that our method surpasses the performance of existing unsupervised MTC methods by directly applying the features extracted from the model after pre-training to clustering. Moreover, it also can achieve good classification performance with supervised fine-tuning on a small labeled dataset. © 2023 IEEE.

关键词： Malware traffic classification (MTC) masked autoencoder transformer unsupervised learning

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12页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：