检索结果-内蒙古大学图书馆

5th CAA International Conference on Vehicular Control and Intelligence, CVCI 2021

作者： Zou, Ke Zhou, Tianle Zhou, Zou Ren, Kai Li, Yanhong Jiang, Xi Yuan, Xuedong Sichuan University National Key Laboratory of Fundamental Science on Synthetic Vision Chengdu China Sichuan University College of Computer Science Chengdu China Guilin University of Electronic Technology School of Information and Communication Guilin China

ISBN: (纸本)9781665408462

Track-to-track association (T2TA) is an essential part in situational awareness of advanced driving assistant systems. The accuracy of track-to-track association methods may degrade by missed detections and measurement bias. Although the local track geometry preservation algorithm has been proposed to improve the performance of T2TA, it may be affected as the target detection decreases. In this study, we proposed second version of the local track geometry preservation algorithm, called LTGPv2, which introduces another local track structure descriptor for T2TA. The local tracks of one sensor are represented by Gaussian mixture model (GMM) centroids, and are fitted to the corresponding local tracks of the other sensor. The T2TA problem is formulated as a maximum likelihood estimation problem with two local track geometry constraints to avoid the degradation of T2TA performance caused by missing detection. Then, an expectation-maximization (EM) algorithm is applied to solve it. Simulation results demonstrate that LTGPv2 obtain better performance than the state-of-the-art methods. © 2021 IEEE.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

From early biological models to CNNs: do they look where humans look?

From early biological models to CNNs: do they look where hum...

引用

International Conference on Pattern Recognition

作者： Marinella Iole Cadoni Andrea Lagorio Enrico Grosso Tan Jia Huei Chan Chee Seng Computer Vision Laboratory University of Sassari Sassari Italy Faculty of Computer Science and Information Technology Center of Image and Signal Processing University of Malaya

Early hierarchical computational visual models as well as recent deep neural networks have been inspired by the functioning of the primate visual cortex system. Although much effort has been made to dissect neural networks to visualize the features they learn at the individual units, the scope of the visualizations has been limited to a categorization of the features in terms of their semantic level. Considering the ability humans have to select high semantic level regions of a scene, the question whether neural networks can match this ability, and if similarity with humans attention is correlated with neural networks performance naturally arise. To address this question we propose a pipeline to select and compare sets of feature points that maximally activate individual networks units to human fixations. We extract features from a variety of neural networks, from early hierarchical models such as HMAX up to recent deep convolutional neural netwoks such as Densnet, to compare them to human fixations. Experiments over the ETD database show that human fixations correlate with CNNs features from deep layers significantly better than with random sets of points, while they do not with features extracted from the first layers of CNNs, nor with the HMAX features, which seem to have low semantic level compared with the features that respond to the automatically learned filters of CNNs. It also turns out that there is a correlation between CNN's human similarity and classification performance.

关键词： Visualization Correlation Databases Neural networks Semantics Pipelines Visual systems

来源：评论

学校读者我要写书评

暂无评论

HLS-based Hardware Acceleration on the Zynq SoC: A Real-Time Face Detection and Recognition System 9

HLS-based Hardware Acceleration on the Zynq SoC: A Real-Time...

引用

9th IEEE International Conference on sciences of Electronics, Technologies of information and Telecommunications, SETIT 2022

作者： Kortli, Yassin Gabsi, Souhir Jridi, Maher Lew Yan Voon, Lew F. C. Atri, Mohamed University of Monastir Electronic and Micro-Electronic Laboratory Faculty of Sciences of Monastir Tunisia L@Bisen Vision-AD Team Yncrea Ouest Carquefou44470 France Universite de Bourgogne Laboratoire ImViA France King Khalid University College of Computer Science Abha61421 Saudi Arabia

ISBN: (数字)9781728184425

ISBN: (纸本)9781728184425

Face detection and recognition system (FDRS) is widely used in modern biometric security systems. In this paper, we implement a new model of FDRS to identify human faces under different poses. Particularly, we propose the Viola-Jones detector to locate and detect human faces and the VanderLugt correlator (VLC) technique for identification. We propose two implementations based on Zync SOC. A set of experiments has been considered using the PHPID database where the faces ranging from -30° to +30°. For more details, see [4]. © 2022 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

FERI: Feature Enhancement and Relational Interaction for Image-text Matching

FERI: Feature Enhancement and Relational Interaction for Ima...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yu Zhang Jianqiang Zhang Gongpeng Song Qin Lu Shuo Zhao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processing images, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method.

关键词： computer vision Fuses Image matching Semantics Feature extraction Natural language processing

来源：评论

学校读者我要写书评

暂无评论

GM-DF: Generalized Multi-Scenario Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be available on https://***/laiyingxin2/GM-DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multimodal Knowledge Graph Completion Method Based on Integrated Modality Adversarial Training and Relation-Enhanced Attention Mechanism

Multimodal Knowledge Graph Completion Method Based on Integr...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Ruijia Zhang Zheng Dong Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Negative sampling (NS) is widely used in knowledge graph completion (KGC) to generate negative triples for contrastive learning during training. However, existing NS methods are not suitable when multimodal information is incorporated into KGC models. Due to their complex design, these methods are also inefficient. In this paper, we propose the integration of Modality-Aware Adversarial Training (IMAT) to generate higher-quality negative samples for Multimodal Knowledge Graph Completion (MMKGC), and introduce a Relation-Enhanced Cross-modal Attention (RECA) mechanism to evaluate bidirectional attention weights between multimodal features using relational information, thereby improving the model's ability to identify hard negative samples. Our approach represents a joint design of MMKGC models and training strategies, surpassing 16 recent MMKGC methods and achieving new state-of-the-art results on three public MMKGC benchmarks.

关键词： Training Federated learning Design methodology Computational modeling Semantics Focusing Knowledge graphs Contrastive learning Sampling methods Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Conversational Human-computer Interface for Smart Energy System Simulation Environments 23

A Conversational Human-Computer Interface for Smart Energy S...

引用

Proceedings of the Winter Simulation Conference

作者： Gabriel Dengler Peter Bazan Reinhard German Pooia Lalbakhsh Ariel Liebmann Laboratory of Computer Networks and Communication Systems Friedrich-Alexander-Universität Erlangen-Nürnberg Martensstr Erlangen Germany Department of Data Science and AI Faculty of Information Technology Monash University Clayton Australia

ISBN: (纸本)9798350369663

This paper introduces a conversational framework that enhances the usability of smart energy system simulations. This study is centered around OpenAI's Generative Pre-trained Transformer (GPT), a fine-tuned conversational model that allows users to communicate with the system in a natural way. Therefore, users can describe their simulation scenarios in plain language and GPT seamlessly translates these descriptions into Python scripts, used as inputs to the simulation environment, in our case, AnyLogic Simulation Software. Our framework is based on the i7-AnyEnergy core framework to compute distribution flows and relevant statistics. The proposed human-machine interface facilitates and accelerates simulation modeling, as demonstrated through the two scenarios we have provided in this paper. Overall, our conversational framework has the potential to significantly improve the user experience of smart energy system simulation environments. By simplifying the interaction between users and complex simulation models, we enable users to obtain valuable insights rapidly and more easily.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similarity Computation Model with Attention Mechanism

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similar...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Shuo Zhao Yiyun Xing Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Text semantic similarity is a crucial research area in Natural Language Processing (NLP). However, traditional methods for calculating the similarity of short Chinese texts often fall short in accuracy and other crucial aspects. The Bidirectional Long Short-Term Memory Network (BiLSTM) has demonstrated remarkable performance in computing the similarity of short Chinese texts by effectively capturing long-range dependencies and semantic information. Additionally, the multi-head attention mechanism considers the interaction between different text locations and semantic information, enhancing the model’s representative capacity. Building upon this foundation, our paper proposes an enhanced model known as SCTbilstmAttRdrop (SCTAR). This model is constructed based on a multilayer BiLSTM architecture and incorporates an SE-gated convolutional module and a convolutional multi-head attention-aware model. We conducted extensive evaluations using two Chinese short text datasets, Chinese-SNLI and CCKS2018_Task3. The experimental results unequivocally demonstrate that our SCTAR model surpasses other common methods in terms of accuracy, precision, recall, and F1 scores when tasked with computing the similarity of Chinese short texts.

关键词： Accuracy Attention mechanisms Computational modeling Semantics Bidirectional control Feature extraction Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

Reliability Measures in Neutrosophic Soft Graphs

引用

Neutrosophic Sets and Systems 2022年 49卷 239-252页

作者： Anirudh, A. Kannan, R. Aravind Sriganesh, R. Sundareswaran, R. Kumar, S. Sampath Shanmugapriya, M. Broumi, Said Dept. of Computer Science Sri Sivasubramaniya Nadar College of Engineering India Dept. of Electrical and Electronics Engineering. Sri Sivasubramaniya Nadar College of Engineering India Dept. of Mathematics Sri Sivasubramaniya Nadar College of Engineering India Laboratory of Information Processing Faculty of Science Ben M'Sik University Hassan II B.P 7955 Sidi Othman Casablanca Morocco

This paper introduces the concept of reliable nodes in neutrosophic soft graphs by evaluating path-based parameters. A reliable node is defined as one which is least susceptible to changes that are quantized by the indeterminacy and falsity values in a neutrosophic tuple. A new path measure called farness and three novel reliability measures which make use of the same are presented. Farness is defined in terms of a novel score function. The first, proximity reliability of a node, computes the farness of a node to its neighbours. The second, intermediate reliability of a node, computes the fraction of paths of minimal farness that pass through it. The third, crisis reliability of a node, is a hybrid of the two previously defined. It considers the farness of a node to its neighbours taking into account the farness of the neighbours to other nodes in the graph. © 2022. All Rights Reserved.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Semantic-Enhanced Attention Network for Image-Text Matching

Semantic-Enhanced Attention Network for Image-Text Matching

引用

International Conference on computer Supported Cooperative Work in Design

作者： Huanxiao Zhou Yushui Geng Jing Zhao Xishan Ma Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Image-text matching is an important task in cross-modal information processing, which consists of evaluating the similarity between images and text. However, the data of the two modalities have different distributions and representations, which cannot be directly compared. Therefore, the two modalities need to be processed separately. Most existing image-text matching methods extract image fragments and text fragments separately, using an attention mechanism to establish relationships between regions in the image and words in the text. Subsequently, they aggregate the similarity of these images and text fragments. Regardless, not all fragment alignment is meaningful, and irrelevant fragment alignment will bring redundancy and reduce retrieval accuracy. In addition to that, there are contextual relationships between image regions and between text words, which should also be taken into account. In this paper, we simultaneously consider these two aspects and propose a Semantic-Enhanced Attention Network (SEAN). It first focuses on each modality, mining contextual relationships between fragments within each modality and aggregating contextual information into visual and textual embeddings. Then, we compute the similarity between all image regions and text fragments, focusing all attention on the region-word pairs with the highest similarity. Finally, we summarize these to infer the similarity between the image and text. Our method achieves competitive results on two generalized image text retrieval datasets, Flickr30K and MS-COCO.

关键词： Visualization Attention mechanisms Federated learning Computational modeling Aggregates Semantics Redundancy

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：