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

72 篇 期刊文献
35 篇 会议

馆藏范围

107 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

101 篇 工学
- 74 篇 计算机科学与技术...
- 37 篇 电气工程
- 13 篇 软件工程
- 12 篇 信息与通信工程
- 5 篇 机械工程
- 5 篇 动力工程及工程热...
- 4 篇 仪器科学与技术
- 4 篇 控制科学与工程
- 4 篇 测绘科学与技术
- 4 篇 石油与天然气工程
- 3 篇 土木工程
- 3 篇 生物医学工程（可授...
- 2 篇 材料科学与工程（可...
- 2 篇 电子科学与技术（可...
- 2 篇 交通运输工程
- 2 篇 船舶与海洋工程
- 1 篇 光学工程
- 1 篇 化学工程与技术
- 1 篇 核科学与技术
18 篇 医学
- 16 篇 临床医学
- 2 篇 基础医学(可授医学...
17 篇 理学
- 5 篇 物理学
- 5 篇 地球物理学
- 3 篇 生物学
- 2 篇 数学
- 2 篇 化学
- 1 篇 大气科学
- 1 篇 统计学（可授理学、...
7 篇 管理学
- 6 篇 管理科学与工程(可...
2 篇 教育学
- 2 篇 心理学(可授教育学...
2 篇 农学
1 篇 艺术学

主题

107 篇 positional encod...
20 篇 transformer
15 篇 transformers
12 篇 deep learning
9 篇 self-attention
8 篇 encoding
5 篇 graph neural net...
5 篇 feature extracti...
5 篇 attention mechan...
4 篇 task analysis
4 篇 image classifica...
4 篇 training
3 篇 lstm
3 篇 neural fields
3 篇 image captioning
3 篇 neural networks
3 篇 convolution
3 篇 multi-task learn...
3 篇 image coding
3 篇 transformer netw...

机构

3 篇 northwestern pol...
3 篇 beijing jiaotong...
2 篇 univ chinese aca...
2 篇 chinese acad sci...
2 篇 natl ctr appl ma...
2 篇 chongqing normal...
2 篇 univ elect sci &...
2 篇 univ wolverhampt...
2 篇 edinburgh napier...
1 篇 city univ hong k...
1 篇 jilin univ dept ...
1 篇 univ moratuwa de...
1 篇 hefei univ sch a...
1 篇 peking univ thir...
1 篇 guangdong univ e...
1 篇 univ elect sci &...
1 篇 chittagong univ ...
1 篇 sun yat sen univ...
1 篇 guilin univ elec...
1 篇 csic upm ctr aut...

作者

2 篇 adeel ahsan
2 篇 ma sugang
2 篇 ramasinghe samee...
2 篇 lin chunyu
2 篇 zheng jianqiao
2 篇 sun wei
2 篇 lucey simon
2 篇 pang yanwei
2 篇 sun hanqing
2 篇 wang zhicai
2 篇 hou zhiqiang
2 篇 yang you
2 篇 yang xiaobao
2 篇 chen lei
2 篇 agarwal manvi
2 篇 cao jiale
2 篇 hussain amir
2 篇 liao kang
2 篇 li xueqian
2 篇 niazi sajawal gu...

语言

102 篇 英文
5 篇 其他
1 篇 德文
1 篇 法文

检索条件"主题词=Positional encoding"

共 107 条记录，以下是81-90 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：

An Improved Transformer Model Based Graph Node Classification Method 41

An Improved Transformer Model Based Graph Node Classificatio...

引用

第41届中国控制会议

作者： Xin Li Weichang Chen Zhaoyi Ma Pan Zhu School of Internet of Things Nanjing University of Posts and Telecommunications

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In recent years,Transformer models have been widely developed in various fields,such as natural language processing(NLP) and computer vision(CV).However,its application in graph data structures is still *** is crucial to develop an improved Transformer model for graph *** the weakness that the original Graph Transformer(GT) is difficult to capture location information of nodes significantly,this paper combines node positional embedding in each layer's ***,in order to select more efficient neighbor nodes,a mask matrix is introduced to reconstruct attention score ***,the group normalization is applied to provide faster training speed and better generalization performance.A number of experiments on two reference graph datasets demonstrate that the proposed GT model has better performance compared to other standard GNNs and original GT.

关键词： Transformer positional encoding mask matrix group normalization GNNs

来源：评论

学校读者我要写书评

暂无评论

A Data-to-Text Generation Model with Deduplicated Content Planning 1

引用

10th CCF Big Data Conference (BigData)

作者： Wang, Mengda Cao, Jianjun Yu, Xu Nie, Zibo Nanjing Univ Informat Sci & Technol Sch Comp Sci Nanjing Peoples R China Natl Univ Def Technol Res Inst 63 Nanjing Peoples R China

ISBN: (数字)9789811983313

ISBN: (纸本)9789811983306;9789811983313

Texts generated in data-to-text generation tasks often have repetitive parts. In order to get higher quality generated texts, we choose a data-to-text generation model with content planning, and add coverage mechanisms to both the content planning and text generation stages. In the content planning stage, a coverage mechanism is introduced to remove duplicate content templates, so as to remove sentences with the same semantics in the generated texts. In the text generation stage, the coverage mechanism is added to remove the repeated words in the texts. In addition, in order to embed the positional association information in the data into the word vectors, we also add positional encoding to the word embedding. Then the word vectors are fed to the pointer network to generate content template. Finally, the content template is inputted into the text generator to generate the descriptive texts. Through experiments, the accuracy of the content planning and the BLEU of the generated texts have been improved, which verifies the effectiveness of our proposed data-to-text generation model.

关键词： Data-to-text generation Content planning Coverage mechanism positional encoding

来源：评论

学校读者我要写书评

暂无评论

Improving Graph Neural Network with Learnable Permutation Pooling 22

Improving Graph Neural Network with Learnable Permutation Po...

引用

22nd IEEE International Conference on Data Mining (ICDM)

作者： Jin, Yu Jaja, Joseph F. Univ Maryland Dept Elect & Comp Engn College Pk MD 20742 USA

ISBN: (纸本)9798350346091

Graph neural networks (GNN) have achieved great success in various graph-related applications. Most existing graph neural network models follow the message-passing neural network (MPNN) paradigm where the graph pooling function forms a critical component that directly determines the model effectiveness. In this paper, we propose PermPool, a new graph pooling function that provably improves the GNN model expressiveness. The method is based on the insight that the distribution of node permuations, when defined properly, forms characteristic encoding of graphs. We propose to express graph representations as the expectation of node permutations with a general pooling function. We show that the graph representation remains invariant to node-reordering and has strong expressive power than MPNN models. In addition, we propose novel permutation modeling and sampling techniques that integrate PermPool into the differentiable neural network models. Empirical results show that our method outperformed other pooling methods in benchmark graph classification tasks.

关键词： Graph neural network Permutation modeling Pooling Function positional encoding

来源：评论

学校读者我要写书评

暂无评论

Effect of Adding positional Information on Convolutional Neural Networks for End-to-End Speech Recognition 21

Effect of Adding Positional Information on Convolutional Neu...

引用

Interspeech Conference

作者： Park, Jinhwan Sung, Wonyong Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea

ISBN: (纸本)9781713820697

Attention-based models with convolutional encoders enable faster training and inference than recurrent neural network-based ones. However, convolutional models often require a very large receptive field to achieve high recognition accuracy, which not only increases the parameter size but also the computational cost and run-time memory footprint. A convolutional encoder with a short receptive field length can suffer from looping or skipping problems when the input utterance contains the same words as nearby sentences. We believe that this is due to the insufficient receptive field length, and try to remedy this problem by adding positional information to the convolution-based encoder. It is shown that the word error rate (WER) of a convolutional encoder with a short receptive field size can be reduced significantly by augmenting it with positional information. Visualization results are presented to demonstrate the effectiveness of adding positional information. The proposed method improves the accuracy of attention models with a convolutional encoder and achieves a WER of 10.60% on TED-LIUMv2 for an end-to-end speech recognition task.

关键词： speech recognition convolutional networks positional encoding

来源：评论

学校读者我要写书评

暂无评论

ADSE: Adversarial Debiasing Framework Based on Sinusoidal Embedding for Sequential Recommendation

ADSE: Adversarial Debiasing Framework Based on Sinusoidal Em...

引用

IEEE International Conference on Web Services (IEEE ICWS)

作者： Bai, Qifeng Lin, Nankai He, Junheng Chen, Zhijin Zhou, Dong Yang, Aimin Guangdong Univ Technol Guangzhou Peoples R China Lingnan Normal Univ Zhanjiang Peoples R China

ISBN: (纸本)9798350368567;9798350368550

Sequential recommendation plays a key role in recommender systems, where the goal is to predict a user's future points of interest by analyzing his or her historical interactions. This process not only requires the system to be able to accurately identify and recommend items that are likely to be of interest to the user but also ensures that all items receive equal exposure to prevent over-concentration or marginalization of items due to algorithmic bias. To address these challenges, in this paper, we propose a novel Adversarial Debiasing framework based on Sinusoidal Embedding for sequential recommendation, ADSE. This framework employs sinusoidal position embeddings to extract positional information between sequences more precisely and utilizes a dropout strategy to optimize the handling of cold-start sequences, aiming to resolve the cold-start issue while maintaining the semantics of the original sequences. Additionally, adversarial training was incorporated to reduce implicit bias due to assuming interactions in the calculation of exposure.

关键词： Sequential Recommendation Adversarial Training Exposure Bias Dropout positional encoding

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Fine-Tuned Transformer for Gait Recognition

Multi-Level Fine-Tuned Transformer for Gait Recognition

引用

International Conference on Virtual Reality, Human-Computer Interaction and Artificial Intelligence (VRHCIAI)

作者： Wu, Huimin Zhao, Aite Qingdao Univ Coll Comp Sci & Technol Qingdao Peoples R China

ISBN: (纸本)9781665491822

Gait Recognition aims to identify individuals by their walking patterns. Abundant spatial and temporal characteristics are contained in human walking for indicating unique personal identity. There have been a large number of existing gait recognition approaches achieving good performance via the analysis of spatial and temporal characteristics. However, most of them directly concatenate the separately extracted temporal features and spatial ones for gait recognition, rarely considering the overall spatiotemporal structure and the inner connection between them. Therefore, we establish a Multi-Level Fine-tuned Transformer trained on sequential gait data, to capture and analyze the overall spatiotemporal information for gait recognition. Specifically, we first design a point-level spatial feature extractor for spatial feature extraction of frames of the gait sequence, based on typical Transformer architecture with positional encoding and multi-head self-attention mechanism. Subsequently, a frame-level temporal feature extractor is employed for the overall spatiotemporal features by learning dynamic information of the extracted spatial features from frames. Moreover, fine-tuned strategy is followed in the process of model training, to profoundly explore intra-frame spatial information, as well as global spatiotemporal features of the whole walking sequence. Extensive experiments conducted on three public datasets (normal and abnormal gait) show promising classification results, compared with several state-of-the-art techniques.

关键词： gait recognition gait sequences spatiotemporal Transformer network positional encoding

来源：评论

学校读者我要写书评

暂无评论

CompactETA: A Fast Inference System for Travel Time Prediction 20

CompactETA: A Fast Inference System for Travel Time Predicti...

引用

26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Fu, Kun Meng, Fanlin Ye, Jieping Wang, Zheng Didi Chuxing AI Labs Beijing Peoples R China

ISBN: (纸本)9781450379984

Computing estimated time of arrival (ETA) is one of the most important services for online ride-hailing platforms like DiDi and Uber. With billions of service queries per day on such platforms, a fast inference ETA module ensures the efficiency of the overall decision system to guarantee satisfied user experience, as well as saving significant operating cost. In this paper, we develop a novel ETA learning system named as CompactETA, which provides an accurate online travel time inference within 100 microseconds. In the proposed method, we encode high order spatial and temporal dependency into sophisticated representations by applying graph attention network on a spatiotemporal weighted road network graph. We further encode the sequential information of the travel route by positional encoding to avoid the recurrent network structure. The properly learnt representations enable us to apply a very simple multi-layer perceptron model for online real-time inference. Evaluation of both offline experiments and online A/B testing verifies that CompactETA reduces the inference latency by more than 100 times compared to a state-of-the-art system, while maintains competing prediction accuracy.

关键词： estimated time of arrival low-latency system graph attention network positional encoding

来源：评论

学校读者我要写书评

暂无评论

Robust Point Cloud Processing Through positional Embedding 11

Robust Point Cloud Processing Through Positional Embedding

引用

International Conference in 3D Vision (3DV)

作者： Zheng, Jianqiao Li, Xueqian Ramasinghe, Sameera Lucey, Simon Univ Adelaide Adelaide SA 5005 Australia Amazon Seattle WA USA

ISBN: (纸本)9798350362466;9798350362459

End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment. Methods like PointNet [17], or the more recent point cloud transformer [7]- and its variants-all employ learned per-point embeddings. Despite impressive performance, such approaches are sensitive to out-of-distribution (OOD) noise and outliers. In this paper, we explore the role of an analytical per-point embedding based on the criterion of bandwidth. The concept of bandwidth enables us to draw connections with an alternate per-point embedding-positional embedding, particularly random Fourier features. We present compelling robust results across downstream tasks such as point cloud classification and registration with several categories of OOD noise.

关键词： point cloud transformers point clouds positional encoding

来源：评论

学校读者我要写书评

暂无评论

SPAIN-NET: SPATIALLY-INFORMED STEREOPHONIC MUSIC SOURCE SEPARATION 47

SPAIN-NET: SPATIALLY-INFORMED STEREOPHONIC MUSIC SOURCE SEPA...

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Petermann, Darius Kim, Minje Indiana Univ Dept Intelligent Syst Engn Bloomington IN 47408 USA

ISBN: (纸本)9781665405409

With the recent advancements of data driven approaches using deep neural networks, music source separation has been formulated as an instrument-specific supervised problem. While existing deep learning models implicitly absorb the spatial information conveyed by the multi-channel input signals, we argue that a more explicit and active use of spatial information could not only improve the separation process but also provide an entry-point for many user-interaction based tools. To this end, we introduce a control method based on the stereophonic location of the sources of interest, expressed as the panning angle. We present various conditioning mechanisms, including the use of raw angle and its derived feature representations, and show that spatial information helps. Our proposed approaches improve the separation performance compared to location agnostic architectures by 1.8 dB SI-SDR in our Slakh-based simulated experiments. Furthermore, the proposed methods allow for the disentanglement of same-class instruments, for example, in mixtures containing two guitar tracks. Finally, we also demonstrate that our approach is robust to incorrect source panning information, which can be incurred by our proposed user interaction.

关键词： music source separation positional encoding panning conditioning neural networks

来源：评论

学校读者我要写书评

暂无评论

CONTEXTUAL LAND-COVER MAP TRANSLATION WITH SEMANTIC SEGMENTATION

CONTEXTUAL LAND-COVER MAP TRANSLATION WITH SEMANTIC SEGMENTA...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Baudoux, Luc Inglada, Jordi Mallet, Clement Univ Gustave Eiffel LaSTIG IGN ENSG Champs Sur Marne France Univ Toulouse CESBIO CNES CNRS IRD INRAE UPS Toulouse France

ISBN: (纸本)9781665403696

This paper presents a framework for translating a land-cover map into another one in a supervised way. This links to numerous applications (updating, completion, etc.). Conversely to existing approaches, we jointly perform spatial and semantic transformation without any prior knowledge. The proposed method assumes that: i) examples of the source and target maps already exist, ii) the spatial resolution of the source map is equal or higher than the target one. The translation is performed using an asymmetric Convolutional Neural Network with positional encoding. Experimental results show the effectiveness of the method in retrieving a yearly version of Corine Land Cover (CLC) at country-scale (France) using an existing high-resolution map and with similar accuracy than existing CLC maps (similar to 80%).

关键词： Land-cover mapping operational translation semantic segmentation positional encoding U-Net Corine Land Cover

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11页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：