检索结果-内蒙古大学图书馆

4th International Conference on Artificial intelligence and Electromechanical Automation, AIEA 2023

作者： Guo, Zicheng Rao, Yuan Xi'an Key Laboratory of Social Intelligence and Complexity Data Processing School of Software Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China

ISBN: (纸本)9781510666412

Text style transfer is mainly to modify the text style to suit various application scenarios without changing the semantic meaning of the text, which is a great significant issue in natural language processing. To expedite research progress, this survey conducts a systematic review of existing literature. Drawing from a vast body of research, this survey first extracts the essential connotations of style information in text of varying granularity across different tasks, and then provide a clear definition of text style transfer, summarize the main challenges at present and comprehensively codify and discuss the current datasets used for evaluation, as well as their indicators. Moreover, this survey compares the mechanisms, advantages, and shortcomings of unsupervised classical methods across word, sentence, and paragraph levels. Finally, the future directions of fighting are also given, hoping to facilitate more comprehensive solutions. © 2023 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A dual-stream spatial-temporal detector for action recognition 4

A dual-stream spatial-temporal detector for action recogniti...

引用

4th International Conference on Computer Vision and Pattern Analysis, ICCPA 2024

作者： Wei, Pingping Li, Jiale Liu, Peiran Li, Li Xu, Yifei Wang, Ling State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiao-Tong University Xi’an710049 China School of Software Xi’an Jiao-Tong University Shaanxi Xi’an710049 China Shaanxi Joint Key Laboratory for Artifact Intelligence Shaanxi 710054 China Xi’an Key Laboratory for Social Intelligence and Complex Data Processing Shaanxi 710054 China Alltuu Inc. Zhejiang Hangzhou310000 China

ISBN: (纸本)9781510682528

In response to the issue that existing human action recognition models can not make full use of complementary information from different modalities, this thesis proposes a multi-path attention module MA to form the MA-GCN model. modalities, this thesis proposes a dual-stream human action recognition model SRHAR that fuses skeleton data and RGB data. This model utilizes LAF proposed in this thesis to fuse skeleton features and RGB features. The introduction of skeleton modality enables the RGB modality to obtain the RGB features. The introduction of skeleton modality enables the RGB modality to obtain complementary information, resulting in more accurate prediction results. This algorithm focuses more on recognition accuracy and has a slower recognition speed, but achieves leading performance in terms of accuracy on public datasets. © 2024 SPIE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Improving Knowledge Graph Completion Using Soft Rules and Adversarial Learning

引用

Chinese Journal of Electronics 2021年第4期30卷 623-633页

作者： TANG Caifang RAO Yuan YU Hualei SUN Ling CHENG Jiamin WANG Yutian Xi'an Key Laboratory of Social Intelligence and Complexity Data Processing School of Software EngineeringXi'an Jiaotong University Shaanxi Joint Key Laboratory for Artifact Intelligence School of Software EngineeringXi'an Jiaotong University School of Software Engineering Xi'an Jiaotong University

Knowledge graph is a useful resources and tools for describing entities and relationships in natural language processing tasks. However, the existing knowledge graph are incomplete. Therefore, knowledge graph completion technology has become a research hotspot in the field of artificial intelligence, but the traditional knowledge graph embedding method does not fully take into account the role of logic rules and the effect of false negative samples on knowledge *** on the logic rules of knowledge and the role of adversarial learning in knowledge embedding, we proposes a model to improve the completion of knowledge graph:soft Rules and graph adversarial learning(RUGA). Firstly,the traditional knowledge graph embedding model is trained as generator and discriminator by using adversarial learning method, and high-quality negative samples are obtained. Then these negative samples and the existing positive samples together constitute the label triple in the injection rule model. The whole model will benefit from both high-quality samples and logical rules. In addition,we evaluated the performance of link prediction task and triple classification task on Freebase and Yago datasets respectively. Finally, the experimental results show that the model can effectively improve the effect of knowledge graph completion.

关键词： Knowledge graph Knowledge embedding Knowledge graph completion Adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Hierarchical Topic-to-Essay Generation 12

Transformer-based Hierarchical Topic-to-Essay Generation

引用

12th International Conference on Identification, Information and Knowledge in the internet of Things, IIKI 2021

作者： He, Wangbo Rao, Yuan Xi'an Key Laboratory of Social Intelligence and Complexity Data Processing School of Software Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China Shaanxi Joint Key Laboratory for Artifact Intelligence School of Software Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China

With the development of 5G network and Internet of things (IOT), a large amount of information is required. In this work, we focus on Topic-to-Essay Generation (TEG), which aims to generate the text based on the topics. Existing methods utilize the RNN-based models, and it's not so useful to capture the long dependencies in the text. The information of topics is insufficient to generate a long text and the existing methods also suffer from the problem about the topic relevance of the text. To fill these gaps, we propose a Transformer-based Hierarchical Topic-to-Essay Generation Model (THTEG), and the experimental results on a real dataset show that our model performs better than the baselines in terms of automatic evaluation and human evaluation. © 2022 The Authors. Published by Elsevier B.V.

关键词： Essay generation Text generation Transformer

来源：评论

学校读者我要写书评

暂无评论

Hybrid Siamese Masked Autoencoders as Unsupervised Video Summarizer

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Xu, Yifei Wu, Zaiqiang Li, Li Li, Siqi Li, Wenlong Li, Mingqi Rao, Yuan Deng, Shuiguang Xi’an Jiao-tong University School of Software Shaanxi Xi’an710054 China Xi’an Jiaotong University Suzhou Institute Jiangsu Suzhou215000 China Shaanxi Joint Key Laboratory for Artifact Intelligence Shaanxi Xi’an710054 China Xi’an Key Laboratory for Social Intelligence and Complex Data Processing Shaanxi Xi’an710054 China Alltuu Inc Zhejiang Hangzhou310000 China College of Computer Science and Technology in Zhejiang University Zhejiang Hangzhou310027 China

Video summarization aims to seek the most important information from a source video while still retaining its primary content. In practical application, unsupervised video summarizers are acknowledged for their flexibility and superiority without requiring annotated data. However, they are looking for the determined rules on how much each frame is essential enough to be selected as a summary. Unlike conventional frame-based scoring methods, we propose a shot-level unsupervised video summarizer termed Hybrid Siamese Masked Autoencoders (H-SMAE) from a higher semantic perspective. Specifically, our method consists of Multi-view Siamese Masked Autoencoders (MV-SMAE) and Shot Diversity Enhancer (SDE). MV-SMAE tries to recover the masked shots from original frame feature and three unmasked shot subsets with elaborate Siamese masked autoencoders. Inspired by the masking idea in MAE, MV-SMAE introduces a Siamese architecture to model prior references to guide the reconstruction of masked shots. Besides, SDE improves the diversity of generated summary by minimizing the repelling loss among selected shots. Afterward, these two modules are fused followed by 0-1 knapsack algorithm to produce a video summary. Experiments on two challenging and diverse datasets demonstrate that our approach outperforms other state-of- the-art unsupervised and weakly-supervised methods, and even generates comparable results with several excellent supervised methods. The source code of H-SMAE is available at https://***/wzq0214/H-SMAE. © 1991-2012 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Graph Explicit Attention Network Based on Predefined Strategy 12

Graph Explicit Attention Network Based on Predefined Strateg...

引用

12th International Conference on Identification, Information and Knowledge in the internet of Things, IIKI 2021

作者： Zhang, xiangbo Rao, Yuan Sun, Ling Lab of Social Intelligence and Complexity Data Processing School of Software Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China Shannxi Joint Key Laboratory for Artifact Intelligence Sub-Lab of Xi'an Jiaotong University China Research Institute of Xi'an Jiaotong University Shenzhen China

Graph attention network (GAT) has achieved great success in graph representation learning in recent years. However, the lower Physical properties of GAT in training process severely affects the application of attention mechanism in graph domain. Particularly, the attention coefficients and the multi-head mechanism are calculated or introduced in the process of model training, which obviously increases the storage complexity. In this paper, we present a graph explicit attention network (GEAT), a novel graph attention architecture that leverage predefined strategy to calculate attention coefficients, which combine global structural and node feature information. In this way, GEAT can effectively reduce the storage complexity, improve the training efficiency and alleviate the over-smoothing problem of attention scores. Experiments on benchmark datasets — Core, Citeseer and Pubmed — demonstrate that our model outperforms the state-of-the-art methods with a clear margin in challenging classifcation tasks, while being computationally efficient. © 2022 The Authors. Published by Elsevier B.V.

关键词： Attention mechanism Deep Learning Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Hierarchical Topic-to-Essay Generation

引用

Procedia Computer Science 2022年 202卷 414-421页

作者： Wangbo He Yuan Rao Xi’an Key Laboratory of Social Intelligence and Complexity Data Processing School of Software Engineering Xi’an Jiaotong University Xi’an Shaanxi 710049 China Shaanxi Joint Key Laboratory for Artifact Intelligence School of Software Engineering Xi’an Jiaotong University Xi’an Shaanxi 710049 China

With the development of 5G network and Internet of things (IOT), a large amount of information is required. In this work, we focus on Topic-to-Essay Generation (TEG), which aims to generate the text based on the topics. Existing methods utilize the RNN-based models, and it’s not so useful to capture the long dependencies in the text. The information of topics is insufficient to generate a long text and the existing methods also suffer from the problem about the topic relevance of the text. To fill these gaps, we propose a Transformer-based Hierarchical Topic-to-Essay Generation Model (THTEG), and the experimental results on a real dataset show that our model performs better than the baselines in terms of automatic evaluation and human evaluation.

关键词： Essay generation text generation Transformer

来源：评论

学校读者我要写书评

暂无评论

Graph Explicit Attention Network Based on Predefined Strategy

引用

Procedia Computer Science 2022年 202卷 422-429页

作者： xiangbo Zhang Yuan Rao Ling Sun Lab of Social Intelligence and Complexity Data Processing School of Software Engineering Xi’an Jiaotong University Xi’an Shaanxi 710049 China Shannxi Joint Key Laboratory for Artifact Intelligence(Sub-Lab of Xi’an Jiaotong University) China Research Institute of Xi’an Jiaotong University Shenzhen China

关键词： Deep Learning Graph neural network Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Pre-trained Language Embedding-based Contextual Summary and Multi-scale Transmission Network for Aspect Extraction 8

Pre-trained Language Embedding-based Contextual Summary and ...

引用

8th International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2019

作者： Feng, Cong Rao, Yuan Nazir, Ambreen Wu, Lianwei He, Long Research Institute of Xi’an Jiaotong University Shenzhen China Lab of Social Intelligence and Complex Data Processing School of Software Engineering Xi’an Jiao Tong University Xi’an China Shaanxi Joint Key Laboratory for Artifact Intelligence Xi’an Jiao Tong University Xi’an China

With the development of IOT and 5G technology, people’s demand for information acquisition is more inclined to accuracy, intelligence and timeliness. How to help designer obtain the real-time information of specific product reviews from the massive online consumers and upgrade the new design strategy has become a hot topic for research. In this paper, we define the problem as an aspect extraction task, and propose a novel deep learning model that comprises of three modules: pre-training language model embedding, multi-scale transmission network and contextual summary, which aims to provide an end-to-end solution without any additional supervision. To this end, we adopt BERT to overcome the disadvantage of traditional embedding methods, which cannot combine contextual information. Multi-scale transmission network is proposed to integrate the Bi-GRU and a group of CNN networks to extract sequential and local features of words respectively. Contextual summary is a tailor-made representation distilled from the input sentence, conditioned on each current word, and thus can assist aspect prediction. Experimental results over three benchmark SemEval datasets clearly illustrate that our model can achieve the state-of-the-art performance. © 2020 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/)

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

SLBCNN: A Improved Deep Learning Model for Few-Shot Charge Prediction 8

SLBCNN: A Improved Deep Learning Model for Few-Shot Charge P...

引用

8th International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2019

作者： Li, Xue Rao, Yuan Wang, Wanzhen Feng, Cong Research Institute of Xi’an Jiaotong University Shenzhen China Lab of Social Intelligence and Complex Data Precessiong School of Software Engineering Xi’an Jiao Tong University Xi’an China Shaanxi Joint Key Laboratory for Artifact Intelligence Xi’an Jiaotong University Xi’an China

Traditional prediction methods of legal judgment rarely work well on few-shot charge prediction task, which is intended to predict possible crimes, laws and terms according to a given few-shot case description. A major challenge in developing an efficient few-shot charge prediction algorithm is how to effectively use all available features contained in the typical cases. To this end, we proposed a novel few-shot charge prediction method based on deep learning framework, named Semi-supervised Learning with BERT-text-Convolutional neural network (i.e. SLBCNN), which utilizes the Attribute-Tri-Training method to extract the features from the few-shot case data. Experiments on three datasets of Criminal-S, Criminal-M, and Criminal-L demonstrate that SLBCNN achieves the state-of-the-art performance, boosting the F1 by 5.2%, 4.2%, and 1.5%, respectively. © 2020 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/)

关键词： Forecasting

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：