检索结果-内蒙古大学图书馆

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Zhai, Sheping Gao, Mingyang Yang, Rui Kang, Xinnian Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

Unlike the traditional unimodal sentiment analysis, multimodal sentiment analysis can jointly process features between different modalities. Existing multimodal sentiment analysis methods simply extract features from text and images ignoring the influence of emoticons that may be contained in text and scene information in images on sentiment polarity judgment. At the same time, the unimodal feature fusion stage does not fully fuse the features of each modality resulting in low accuracy of sentiment analysis. Therefore, this paper proposes a multimodal sentiment analysis model based on multicategorical relative fusion of images and texts. which separates text content and emoji in the word embedding stage in the feature extraction stage, the traditional emoji sentiment dictionary is queried to obtain their sentiment scores and attention mechanism is introduced to extract scene features and object features of images respectively;in the feature fusion stage, the emoji sentiment scores. mixed image. The final multimodal features are obtained by fusion the emoji sentiment scores. mixed image features and text features with layer normalization. The experiments on the dataset Yelp show that the improvement of the model in the feature extraction and feature fusion stages effectively improves the accuracy and F1 value of multimodal sentiment analysis in which the accuracy increases by 4.7 percentage points on the New York dataset and the F1 value reaches 85.7% on the San Francisco dataset. © 2023 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Hash Retrieval with Category Semantics 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Xu, Mengying Lai, Hanjiang Yin, Jian Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

ISBN: (数字)9783031533051

ISBN: (纸本)9783031533044

With the multi-medal resource springing up, the field of cross-modal research has witnessed rapid advancement. Among these, Cross-Modal Hash retrieval has attracted attention due to its time-saving capabilities during the retrieval process. However, most existing cross-modal hash retrieval methods focus on capturing the relationship between modalities and often train in a one-to-one correspondence manner. Consequently, they often neglect the comprehensive distribution of the entire dataset. In response, we propose a novel approach that introduces semantic relationships between categories to capture class relationships and enable the measurement of the full distribution. First, the original image and text are encoded to obtain respective representations. Then, these are fused to generate a joint representation, which is passed through a classification head to obtain category semantics. The semantic information is used to allocate hash centers from a Hadamard matrix. Meanwhile, the image and text representations are fed into a hash layer to produce hash codes. We train the network with a modal matching loss for alignment, as well as center and class loss to capture the full data distribution. Extensive evaluations on two benchmark databases demonstrate that our approach achieves competitive performance compared to state-of-the-art methods. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Edge Computing Task Scheduling with Joint Blockchain and Task Caching in Industrial Internet

引用

Computers, Materials & Continua 2023年第4期75卷 2101-2117页

作者： Yanping Chen Xuyang Bai Xiaomin Jin Zhongmin Wang Fengwei Wang Li Ling School of Computer Science and Technology Xi’an University of Posts and TelecommunicationsXi’an710121China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’anShaanxi710121China ZTE Corporation Shenzhen51805China

Deploying task caching at edge servers has become an effectiveway to handle compute-intensive and latency-sensitive tasks on the industrialinternet. However, how to select the task scheduling location to reduce taskdelay and cost while ensuring the data security and reliable communicationof edge computing remains a challenge. To solve this problem, this paperestablishes a task scheduling model with joint blockchain and task cachingin the industrial internet and designs a novel blockchain-assisted cachingmechanism to enhance system security. In this paper, the task schedulingproblem, which couples the task scheduling decision, task caching decision,and blockchain reward, is formulated as the minimum weighted cost problemunder delay constraints. This is a mixed integer nonlinear problem, which isproved to be nonconvex and NP-hard. To solve the optimal solution, thispaper proposes a task scheduling strategy algorithm based on an improvedgenetic algorithm (IGA-TSPA) by improving the genetic algorithm initializationand mutation operations to reduce the size of the initial solutionspace and enhance the optimal solution convergence speed. In addition,an Improved Least Frequently Used algorithm is proposed to improve thecontent hit rate. Simulation results show that IGA-TSPA has a faster optimalsolution-solving ability and shorter running time compared with the existingedge computing scheduling algorithms. The established task scheduling modelnot only saves 62.19% of system overhead consumption in comparison withlocal computing but also has great significance in protecting data security,reducing task processing delay, and reducing system cost.

关键词： Edge computing task scheduling blockchain task caching industrial security

来源：评论

学校读者我要写书评

暂无评论

Controllability of neighborhood Corona product networks

引用

Science China(Information Sciences) 2024年第12期67卷 327-328页

作者： Bo LIU Xuan LI Qiang ZHANG Junjie HUANG Housheng SU Ministry of Education Key Laboratory for Intelligent Analysis and Security Governance of Ethnic Languages School of Information Engineering Minzu University of China School of Mathematical Sciences Inner Mongolia University Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology

Controlling networks aims to study the models, structures,and related dynamics of complex networks. The primary problem of controlling networks is to determine whether they are controllable. Nowadays, controllability has been widely studied and applied to system engineering and control theory, power systems, aerospace, and quantum systems. Various classical criteria include the Gram matrix criterion, Kalman rank criterion, and PBH test.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application study of oil pipe entity recognition combined with Deep Reinforcement Learning: Named Entity Recognition combined with Deep Reinforcement Learning 6

Application study of oil pipe entity recognition combined wi...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Guan, Wei Liu, Shijie Ma, Li Xi'an University of Posts and Telecommunications Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing China

ISBN: (纸本)9798400707674

Aiming at the problems of inaccurate extraction of entity feature information and mislabeling of recognition results in the construction of knowledge graphs in the field of oil pipe failure using traditional methods, this paper proposes a research method of BERT-BiLSTM-CRF named entity recognition combined with deep reinforcement learning. The method firstly uses the BERT (Bidirectional encoder representations from transformers) pre-training model to obtain the word vectors of the input sequence semantics;secondly, the trained word vectors are fed into the bi-directional long short- term memory network (BiLSTM) to further obtain contextual features and output the maximum probability sequence annotation results according to the labeling rules of conditional random fields (CRF) and sequence decoding ability;finally, the BERT-BiLSTM-CRF model is supplemented with the deep reinforcement learning-based labeling Finally, the BERT-BiLSTM-CRF-DRL model is added to the BERT-BiLSTM-CRF model to form the framework of named entity recognition model in oil pipe failure domain. The model is compared with other 2 named entity recognition models on a self-built oil pipe data-set, and the experimental results show that the accuracy, recall and F1 values of the model reach 90.5%, 92.7% and 91.9%, respectively, and the entity recognition is better than the other 2 models. © 2023 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Visual Question Answering Model Based on Relationship graphs and Co-Attention 6

Visual Question Answering Model Based on Relationship graphs...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Guan, Wei Yang, Xueli Ma, Li Xi'an University of Posts and Telecommunications Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing China

ISBN: (纸本)9798400707674

Visual Question Answering is a very challenging tasks in the fiield of AI. The existing model is not accurate enough to judge the relationship between problem words, image objects and the association between problem and image objects, meanwhile, the interpretability of the model needs to be improved. In response, this paper proposes a visual question answering model based on relationship graph and co-attention. Relational features can be obtained by constructing a relational graph using the relationships between the problem and the image, and between the objects of the image, and by dynamically updating the relational graph using a graph attention network guided by the problem. Then, the obtained features are fused using co- attention to obtain richer ***, these features are used to make answer prediction. The model is experimented on the VQA2.0 dataset, and the experimental results show that the model improved the accuracy of the visual question answering model to some extent compared with the existing models. © 2023 ACM.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Robust primary quantization step estimation on resized and double JPEG compressed images

引用

Multimedia Tools and Applications 2025年第12期84卷 11097-11118页

作者： Zhang, Lei Chen, XuGuang Niu, YaKun Zuo, XianYu Wang, Huaqing School of Computer and Information Engineering Henan Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Kaifeng Henan Henan Kaifeng475004 China National Internet Emergency Center Henan Zhengzhou450000 China

As one of the most important forensic tasks, reconstruction of the original information in tampered images is a key step for tampering detection and localization. Currently, a number of methods have been designed to estimate the primary quantization steps of double compressed JPEG images. However, the estimation in the presence of resizing operation remains a challenge. In this paper, we propose a robust primary quantization steps estimation method on resized and double JPEG compressed images. Specifically, the distribution of Discrete Cosine Transform (DCT) coefficients is firstly analyzed on the inverse resized image. Then, a maximum likelihood function together with a filtering strategy is designed to obtain the primary quantization step on Alternating Current (AC) bands. In addition, we find the prominent peak in the Discrete Fourier Transform (DFT) spectrum of the distribution of Direct Current (DC) coefficients is nonlinearly related to the step. Based on this observation, a mapping function derived from the geometric fitting is proposed to estimate the step on DC band. Experimental results demonstrate the proposed method provides superior estimation performance. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

CA-WGE: A two-view graph neural network-based knowledge graph completion approach combining common sense perception 6

CA-WGE: A two-view graph neural network-based knowledge grap...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Guan, Wei Lian, Xiaoru Ma, Li Xi'an University of Posts and Telecommunications Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing China

ISBN: (纸本)9798400707674

The knowledge graph completion algorithm can make the knowledge graph more complete and is currently a research hotspot in the field of artificial intelligence. The knowledge graph completion model is mainly defined in three aspects, the way of negative example generation, the design of scoring function and the design of loss function. The previous knowledge graph completion models only rely on factual view data to predict the missing links between entities and ignore the valuable common sense knowledge, and there is invalid negative sampling in knowledge graph embedding techniques;on the other hand, the existing graph neural network-based knowledge graph embedding models mainly consider capturing the graph structure around entities, and the relational representation is only used to update the entity embedding, which may miss the potentially useful information about the relational structure of potentially useful information. To address the above challenges, this paper proposes a two-view graph neural network-based knowledge graph completion model combined with common sense awareness. Common knowledge is first automatically extracted from fact triples with entity concepts to facilitate high-quality negative sampling, and then positive and weighted negative triples are fed into the two-view graph neural network-based knowledge graph embedding model to capture entity- and relationship-centric graph structures and learn vector representations of entities and relationships, and then the learned entity and relationship representations are fed into a weighted score function to return the final the final score. Extensive experimental and ablation studies on four datasets, FB15K, FB15K237, NELL995, and DBpedia-242, show that the model achieves better performance compared to the state-of-the-art models. © 2023 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Dialogue Generation for Heterogeneous Graph Neural on Networks Incorporating External Knowledge 6

Dialogue Generation for Heterogeneous Graph Neural on Networ...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Guan, Wei Guo, Shuaiqian Ma, Li Xi'an University of Posts and Telecommunications Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing China

ISBN: (纸本)9798400707674

In recent years, with the improvement of hardware computing power and the rapid development of deep learning theory, the field of dialogue generation has also entered the era of deep learning. However, because it is difficult to generate content-rich and recovery statements by learning semantics only from dialogue corpus, many models are prone to generate responses that are weakly scalable to the topic of the input dialogue or generic responses that lack knowledge information. To address the above issues, a Heterogeneous Graph Neural Network Incorporating External Knowledge Dialogue Generation Model (HEDG) is proposed. First, we build up the external knowledge into a knowledge graph, and find the relevant external knowledge in the knowledge graph according to the entities in the input conversation according to certain rules. This external knowledge and the historical conversation context are then used as inputs to the heterogeneous graph encoder, and the conversation content and the corresponding external knowledge are represented by a Heterogeneous Graph Neural Network (HGNN). Finally, a decoder with Transformer structure as the main body is used to generate a response that is relevant to the conversation context with some knowledge extension by taking the encoded heterogeneous graphical representation as input. The experimental results show that the model has higher relevance and diversity compared with existing comparison models, and can effectively integrate external knowledge. © 2023 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Infusing knowledge into CLIP via low-rank matrix for video-text retrieval

Infusing knowledge into CLIP via low-rank matrix for video-t...

引用

2024 International Conference on image, Signal processing, and Pattern Recognition, ISPP 2024

作者： Zhang, Daqing Yin, Jian School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

ISBN: (纸本)9781510680425

Video-text retrieval has been a crucial task with the exponential growth of video. Recent methods that leverage the pretrained CLIP model in the video-text retrieval task have demonstrated remarkable performance, surpassing many approaches trained on large-scale video-text datasets. However, these works ignore the performance-efficiency trade-off in the pursuit of better performance. Additionally, a completely new model is typically necessary for each task because many existing works fully fine-tune the pre-trained backbone. Therefore, to yield a compact and transferable model, we propose LoCLIP, a framework that transfers knowledge from CLIP in a parameter-efficient manner. Inspired by LoRA, we incorporate only a small set of trainable low-rank matrices per task, allowing adaptation to new tasks by simply replacing these matrices. In this way, we can acquire task-specific knowledge without compromising the prior knowledge stored in the pre-trained backbone. To demonstrate the effectiveness of our LoCLIP, we conduct extensive experiments and achieve comparable performance with state-of-the-art CLIP-based video-text retrieval methods while updating only a few parameters. © 2024 SPIE.

关键词： Video recording

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：