检索结果-内蒙古大学图书馆

Exploring Sparse Spatial Relation in graph inference for Text-Based VQA

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 5060-5074页

作者： Zhou, Sheng Guo, Dan Li, Jia Yang, Xun Wang, Meng Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei 230601 Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230026 Peoples R China

Text-based visual question answering (TextVQA) faces the significant challenge of avoiding redundant relational inference. To be specific, a large number of detected objects and optical character recognition (OCR) tokens result in rich visual relationships. Existing works take all visual relationships into account for answer prediction. However, there are three observations: (1) a single subject in the images can be easily detected as multiple objects with distinct bounding boxes (considered repetitive objects). The associations between these repetitive objects are superfluous for answer reasoning;(2) two spatially distant OCR tokens detected in the image frequently have weak semantic dependencies for answer reasoning;and (3) the co-existence of nearby objects and tokens may be indicative of important visual cues for predicting answers. Rather than utilizing all of them for answer prediction, we make an effort to identify the most important connections or eliminate redundant ones. We propose a sparse spatial graph network (SSGN) that introduces a spatially aware relation pruning technique to this task. As spatial factors for relation measurement, we employ spatial distance, geometric dimension, overlap area, and DIoU for spatially aware pruning. We consider three visual relationships for graph learning: object-object, OCR-OCR tokens, and object-OCR token relationships. SSGN is a progressive graph learning architecture that verifies the pivotal relations in the correlated object-token sparse graph, and then in the respective object-based sparse graph and token-based sparse graph. Experiment results on TextVQA and ST-VQA datasets demonstrate that SSGN achieves promising performances. And some visualization results further demonstrate the interpretability of our method.

关键词： Visual question answering text-based visual question answering graph inference spatial relation relation learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge enhanced graph inference network based entity-relation extraction and knowledge graph construction for industrial domain

引用

Frontiers of Engineering Management 2024年第1期11卷 143-158页

作者： Zhulin HAN Jian WANG College of Electronic and Information Engineering Tongji UniversityShanghai 200092China

With the escalating complexity in production scenarios, vast amounts of production information are retained within enterprises in the industrial domain. Probing questions of how to meticulously excavate value from complex document information and establish coherent information links arise. In this work, we present a framework for knowledge graph construction in the industrial domain, predicated on knowledge-enhanced document-level entity and relation extraction. This approach alleviates the shortage of annotated data in the industrial domain and models the interplay of industrial documents. To augment the accuracy of named entity recognition, domain-specific knowledge is incorporated into the initialization of the word embedding matrix within the bidirectional long short-term memory conditional random field (BiLSTM-CRF) framework. For relation extraction, this paper introduces the knowledge-enhanced graph inference (KEGI) network, a pioneering method designed for long paragraphs in the industrial domain. This method discerns intricate interactions among entities by constructing a document graph and innovatively integrates knowledge representation into both node construction and path inference through TransR. On the application stratum, BiLSTM-CRF and KEGI are utilized to craft a knowledge graph from a knowledge representation model and Chinese fault reports for a steel production line, specifically SPOnto and SPFRDoc. The F1 value for entity and relation extraction has been enhanced by 2% to 6%. The quality of the extracted knowledge graph complies with the requirements of real-world production environment applications. The results demonstrate that KEGI can profoundly delve into production reports, extracting a wealth of knowledge and patterns, thereby providing a comprehensive solution for production management.

关键词： knowledge graph construction industrial BiLSTM-CRF document-level relation extraction graph inference

来源：评论

学校读者我要写书评

暂无评论

Context-Aware graph inference With Knowledge Distillation for Visual Dialog

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第10期44卷 6056-6073页

作者： Guo, Dan Wang, Hui Wang, Meng Hefei Univ Technol HFUT Key Lab Knowledge Engn Big Data Minist Educ Hefei 230601 Peoples R China Hefei Univ Technol HFUT Intelligent Interconnected Syst Lab Anhui Prov Hefei 230601 Peoples R China Hefei Univ Technol HFUT Sch Comp Sci & Informat Engn Hefei 230601 Peoples R China Hefei Univ Technol HFUT Sch Artificial Intelligence Hefei 230601 Peoples R China

Visual dialog is a challenging task that requires the comprehension of the semantic dependencies among implicit visual and textual contexts. This task can refer to the relational inference in a graphical model with sparse contextual subjects (nodes) and unknown graph structure (relation descriptor);how to model the underlying context-aware relational inference is critical. To this end, we propose a novel context-aware graph (CAG) neural network. We focus on the exploitation of fine-grained relational reasoning with object-level dialog-historical co-reference nodes. The graph structure (relation in dialog) is iteratively updated using an adaptive top-K message passing mechanism. To eliminate sparse useless relations, each node has dynamic relations in the graph (different related K neighbor nodes), and only the most relevant nodes are attributive to the context-aware relational graph inference. In addition, to avoid negative performance caused by linguistic bias of history, we propose a pure visual-aware knowledge distillation mechanism named CAG-Distill, in which image-only visual clues are used to regularize the joint dialog-historical contextual awareness at the object-level. Experimental results on VisDial v0.9 and v1.0 datasets show that both CAG and CAG-Distill outperform comparative methods. Visualization results further validate the remarkable interpretability of our graph inference solution.

关键词： Visual dialog cross-modal interaction relational reasoning graph inference knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

DGIC: A Distributed graph inference Computing Framework Suitable For Encoder-Decoder GNN 2022

DGIC: A Distributed Graph Inference Computing Framework Suit...

引用

6th International Conference on Innovation in Artificial Intelligence (ICIAI)

作者： Pan, Zeting Chang, Junsheng Natl Univ Def Technol Coll Comp Changsha Peoples R China

ISBN: (纸本)9781450395502

*A graph is a structure that can express the relationship between objects. The emergence of GNN enables deep learning to be applied in the field of graphs. However, most GNNs are trained offline and cannot be directly used in real-time monitoring scenarios such as financial risk control. In addition, due to the large scale of graph data, a single machine often cannot meet actual needs, and there are bottlenecks such as throughput performance. Therefore, we propose a distributed graph inference computing framework, which can be applied to Encoder-Decoder GNN models. We complete the adaptation of the model by disassembling the graph data and using the extension storage and dynamic invocation mechanism to solve the model invocation problem. For inference performance, we implement dynamic graph construction through incremental composition and decouple the inference process to apply to different scenarios, so that GNNs conforming to the Encoder-Decoder style can be applied to the framework. A large number of experiments show that this method has good timeliness while improving the throughput upper limit, and can maintain the model effect of multi-tasking.

关键词： graph inference graph Neural Networks Distributed graph computing

来源：评论

学校读者我要写书评

暂无评论

graph Pooling inference Network for Text-based VQA

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2024年第4期20卷 1-21页

作者： Zhou, Sheng Guo, Dan Yang, Xun Dong, Jianfeng Wang, Meng HeFei Univ Technol 485 Danxia Rd Hefei 230601 Anhui Peoples R China Univ Sci & Technol China 96 JinZhai Rd Hefei 230026 Anhui Peoples R China Zhejiang Gongshang Univ 18Xuecheng StXiasha Higher Educ Pk Hangzhou 310018 Zhejiang Peoples R China

Effectively leveraging objects and optical character recognition (OCR) tokens to reason out pivotal scene text is critical for the challenging Text-based Visual Question Answering (TextVQA) task. graph-based models can effectively capture the semantic relationship among visual entities (objects and tokens) and report remarkable performance in TextVQA. However, previous efforts usually leverage all visual entities and ignore the negative effect of superfluous entities. This article presents a graph Pooling inference Network (GPIN), which is an evolutionary graph learning method to purify the visual entities and capture the core semantics. It is observed that the dense distribution of reduplicative objects and the crowd of semantically dependent OCR tokens usually co-exist in the image. Motivated by this, GPIN adopts an adaptive node dropping strategy to dynamically downscale semantically closed nodes for graph evolution and update. To deepen the comprehension of scene text, GPIN is a dual-path hierarchical graph architecture that progressively aggregates the evolved object graph and the evolved token graph semantics into a graph vector that serves as visual cues to facilitate the answer reasoning. It can effectively eliminate object redundancy and enhance the association of semantically continuous tokens. Experiments conducted on TextVQA and ST-VQA datasets show that GPIN achieves promising performance compared with state-of-the-art methods.

关键词： Text-based visual question answering graph inference graph pooling

来源：评论

学校读者我要写书评

暂无评论

DeviceWatch: A Data-Driven Network Analysis Approach to Identifying Compromised Mobile Devices with graph-inference

引用

ACM TRANSACTIONS ON PRIVACY AND SECURITY 2023年第1期26卷 1-32页

作者： Choo, Euijin Nabeel, Mohamed Alsabah, Mashael Khalil, Issa Yu, Ting Wang, Wei Univ Alberta Dept Comp Sci 2-21 Athabasca Hall Edmonton AB T6G 2E8 Canada Qatar Comp Res Inst HBKU Res ComplexPOB 5825 Doha Qatar Beijing Jiaotong Univ Informat Secur 3 Shangyuancun Beijing 100044 Peoples R China

We propose to identify compromised mobile devices from a network administrator's point of view. Intuitively, inadvertent users (and thus their devices) who download apps through untrustworthy markets are often lured to install malicious apps through in-app advertisements or phishing. We thus hypothesize that devices sharing similar apps would have a similar likelihood of being compromised, resulting in an association between a compromised device and its apps. We propose to leverage such associations to identify unknown compromised devices using the guilt-by-association principle. Admittedly, such associations could be relatively weak as it is hard, if not impossible, for an app to automatically download and install other apps without explicit user initiation. We describe how we can magnify such associations by carefully choosing parameters when applying graph-based inferences. We empirically evaluate the effectiveness of our approach on real datasets provided by a major mobile service provider. Specifically, we show that our approach achieves nearly 98% AUC (area under the ROC curve) and further detects as many as 6 similar to 7 times of new compromised devices not covered by the ground truth by expanding the limited knowledge on known devices. We show that the newly detected devices indeed present undesirable behavior in terms of leaking private information and accessing risky IPs and domains. We further conduct in-depth analysis of the effectiveness of graph inferences to understand the unique structure of the associations between mobile devices and their apps, and its impact on graph inferences, based on which we propose how to choose key parameters.

关键词： Compromised device mobile traffic analysis graph inference

来源：评论

学校读者我要写书评

暂无评论

Following Passive DNS Traces to Detect Stealthy Malicious Domains Via graph inference

引用

ACM TRANSACTIONS ON PRIVACY AND SECURITY 2020年第4期23卷 1–36页

作者： Nabeel, Mohamed Khalil, Issa M. Guan, Bei Yu, Ting Qatar Comp Res Inst POB 34110 Doha Qatar Chinese Acad Sci Collaborat Innovat Ctr 4 South Fourth St Beijing Peoples R China

Malicious domains, including phishing websites, spam servers, and command and control servers, are the reason for many of the cyber attacks nowadays. Thus, detecting them in a timely manner is important to not only identify cyber attacks but also take preventive measures. There has been a plethora of techniques proposed to detect malicious domains by analyzing Domain Name System (DNS) traffic data. Traditionally, DNS acts as an Internet miscreant's best friend, but we observe that the subtle traces in DNS logs left by such miscreants can be used against them to detect malicious domains. Our approach is to build a set of domain graphs by connecting "related" domains together and injecting known malicious and benign domains into these graphs so that we can make inferences about the other domains in the domain graphs. A key challenge in building these graphs is how to accurately identify related domains so that incorrect associations are minimized and the number of domains connected from the dataset is maximized. Based on our observations, we first train two classifiers and then devise a set of association rules that assist in linking domains together. We perform an in-depth empirical analysis of the graphs built using these association rules on passive DNS data and show that our techniques can detect many more malicious domains than the state-of-the-art.

关键词： Malicious domains graph inference passive DNS domain association

来源：评论

学校读者我要写书评

暂无评论

Aligning vision-language for graph inference in visual dialog

引用

IMAGE AND VISION COMPUTING 2021年 116卷 104316-104316页

作者： Jiang, Tianling Shao, Hailin Tian, Xin Ji, Yi Liu, Chunping Soochow Univ Sch Comp Sci & Technol Suzhou Jiangsu Peoples R China

As a cross-media intelligence task, visual dialog calls for answering a sequence of questions based on an image, using the dialog history as context. To acquire correct answers, the exploration of the semantic dependencies among potential visual and textual contents becomes vital. Prior works usually ignored the underlying knowledge hidden in internal and external textual-visual relationships, which resulted in unreasonable inferring. In this paper, we propose an Aligning Vision-Language for graph inference (AVLGI) in visual dialog by combining the internal context-aware information and the external scene graph knowledge. Compared with other approaches, it makes up the lack of structural inference in visual dialog. So the whole system consists of three modules, Inter-Modalities Alignment (IMA), Visual graph Attended by Text (VGAT) and Combining Scene graph and Textual Contents(CSGTC). Specifically, the IMA module aims at representing an image with a set of integrated visual regions and corresponding textual concepts, reflecting certain semantics. And the VGAT module views the visual features with semantic information as observed nodes and measures the weight of importance between each two nodes in visual graph. The CSGTC supplements various relationships between visual objects by introducing additional information of the scene graph. We also qualitatively and quantitatively evaluate the model on VisDial v1.0 dataset, showing our AVLGI outperforms previous state-of-the-art models. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Visual dialog Alignment graph inference Scene graph

来源：评论

学校读者我要写书评

暂无评论

Wavelet-based graph inference using multiple testing 18

Wavelet-based graph inference using multiple testing

引用

Conference on Wavelets and Sparsity XVIII

作者： Achard, Sophie Borgnat, Pierre Gannaz, Irene Roux, Marine Univ Grenoble Alpes CNRS Grenoble INP GIPSA Lab F-38000 Grenoble France UCB Lyon 1 Labe Phys Univ Lyon ENS LyonCNRS F-69342 Lyon France Univ Lyon Inst Camille Jordan CNRS INSA LyonUMR 5208 F-69621 Villeurbanne France

ISBN: (数字)9781510629707

ISBN: (纸本)9781510629707

graph-based representation enables to outline efficiently interactions between sensors and as such has encountered a growing interest. For example in neurosciences, the graph of interactions between brain regions has shed lights on evolution of diseases. In this paper, we describe a whole procedure which estimates the graph from multivariate time series. First correlations using wavelet decomposition of the signals are estimated. Bonferroni (1935)'s procedure on multiple correlation testing is then used. We prove theoretically that the Family Wise Error Rate (FWER) is asymptotically controlled for any graph structures. We implement our approach on small-world graph structures, with signals possibly having long-memory properties. This structure is inspired by real data examples from resting-state functional magnetic resonance imaging. The control is confirmed graphically. Numerical simulations illustrate the behavior of the bias and the power of our proposed approach.

关键词： wavelets multiple testing correlation graph inference

来源：评论

学校读者我要写书评

暂无评论

graph inference by multiple testing with application to Neuroimaging

Graph inference by multiple testing with application to Neur...

引用

作者： Marine Roux COMMUNAUTE UNIVERSITE GRENOBLE ALPES

学位级别：博士

This thesis is motivated by the analysis of the functional magnetic resonance imaging (fMRI). The need for methods to build such structures from fMRI data gives rise to exciting new challenges for mathematics. In this regards, the brain connectivity networks are modelized by a graph and we study some procedures that allow us to infer this graph. More precisely, we investigate the problem of the inference of the structure of an undi- rected graphical model by a multiple testing procedure. The structure induced by both the correlation and the partial correlation are considered. The statistical tests based on the latter are known to be highly dependent and we assume that they have an asymptotic Gaussian distribution. Within this framework, we study some multiple testing procedures that allow a control of false edges included in the inferred graph. First, we theoretically examine the False Discovery Rate (FDR) control of Benjamini and Hochberg's procedure in Gaussian setting for non necessary positive dependent statis- tical tests. Then, we explore both the FDR and the Family Wise Error Rate (FWER) control in asymptotic Gaussian setting. We present some multiple testing procedures, well-suited for correlation (resp. partial correlation) tests, which provide an asymptotic control of the FWER. Furthermore, some first theoretical results regarding asymptotic FDR control are established. Second, the properties of the multiple testing procedures that asymptotically control the FWER are illustrated on a simulation study, for statistical tests based on correlation. We finally conclude with the extraction of cerebral connectivity networks on real data set.

关键词： multiple testing FWER control FDR control Gaussian setting Benjamini-Hochberg procedure neuroscience fMRI data analysis brain connectivity networks graph inference correlation test

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：