检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Zhen Yang Hongxia Zhao Ping Jian School of Computer Science and Technology Beijing Institute of Technology Beijing China Institute of Automation Academy of Sciences Beijing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Image paragraph captioning aims to describe given images by generating natural paragraphs. Unfortunately, the paragraphs generated by existing methods typically suffer from poor coherence since the visual information is inevitably lost after the pooling operation, which maps numerous visual features to only one global vector. On the other hand, the pooled vectors make it harder for the language models to interact with details in images, leading to generic or even wrong descriptions of visual details. In this paper, we propose a simple yet effective module called Visual Information Enhancement Module (VIEM) to prevent the visual information loss in visual features pooling. Meanwhile, to model the inter-sentence dependency, a fusion gate mechanism, which makes the most of the nonpooled features by fusing visual vectors with textual information, is introduced into the language model to furthermore improve the paragraph coherence. In experiments, the visual information loss is quantitatively measured through a mutual information based method. Surprisingly, the results indicates that such loss in VIEM is only approximately 50% of that in pooling, effectively demonstrating the efficacy of VIEM. Moreover, extensive experiments on Stanford image-paragraph dataset show that the proposed method achieves promising performance compared with existing methods 1 .

关键词： Visualization Reviews Neural networks Estimation Coherence Logic gates Vectors

来源：评论

学校读者我要写书评

暂无评论

Personality-Guided Multimodal Sentiment Analysis

Personality-Guided Multimodal Sentiment Analysis

引用

Artificial Intelligence technology (ACAIT), Asian Conference on

作者： Kang Zhu Xuefei Liu Heng Xie Cong Cai Ruibo Fu Jiangyan Yi Jianhua Tao Zhengqi Wen Cunhang Fan Zhao Lv Computer Science and Technology Anhui University Hefei China Institute of Automation Chinese Academy of Sciences Beijing China Computer Science and Technology Beijing Institute of Technology Beijing China Department of Automation Tsinghua University Beijing China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

In recent years, text-based multimodal sentim-ent recognition has made significant advancements; however, it faces numerous challenges when it comes to personalized sentiment product applications. As is well known, personality is directly related to sentiment Neuroticism predicts higher negative sentiment and lower positive affect, and conscientiousness, by contrast, is inversely associated with negative sentiment. Therefore, treating texts with different expressive styles equally will lead to biased sentiment analysis results. To address this issue, we incorporate personality information into textual sentiment representation. In this paper, we propose the PGMSA (Personality-Guided MSA) framework. This framework consists of two modules. The first module involves the interaction between personality and sentiment. It aims to obtain personalized textual sentiment representations. The second module of the framework designs a multi-channel filtering module. This module utilizes personalized textual sentiment representations for information filtering in other modalities. To demonstrate the effectiveness of the PGMSA framework, we conducted extensive experiments on two datasets and achieved state-of-the-art experimental results.

关键词： Measurement Sentiment analysis Visualization Face recognition Information filters Artificial intelligence Faces

来源：评论

学校读者我要写书评

暂无评论

Adaptive Visual-Aided 4D Radar Odometry Through Transformer-Based Feature Fusion

Adaptive Visual-Aided 4D Radar Odometry Through Transformer-...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Yuanfan Zhang Renxiang Xiao Ziyang Hong Liang Hu Jie Liu School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Automation School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Institute for AI Research Harbin Institute of Technology Harbin China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Multimodal sensor fusion has been successfully utilized in many odometry and localization methods as it increases both estimate accuracy and robustness in application scenarios. To address the challenge of odometry under varying-weather conditions, we propose a novel visual 4D radar fusion based odometry in an unsupervised deep learning approach. In our method, we adopt transformer-based cascaded decoders to facilitate efficient feature extraction of images and radar point clouds. Considering that radars are weather-agnostic and information-rich cameras are susceptible to adverse weathers, we deliberately introduce an adaptive attention-based feature fusion mechanism, in which the attention shifts dynamically to adapt to changing weather conditions based on the amount of information content in image features. Through extensive comparative experiments, our method surpasses different state-of-the-art single-modal odometry estimation methods. Our code and trained model will be released publicly.

关键词： Point cloud compression Visualization Meteorological radar Accuracy Radar imaging Transformers Robustness Odometry Unsupervised learning Meteorology

来源：评论

学校读者我要写书评

暂无评论

Social Force Embedded Mixed Graph Convolutional Network for Multi-Class Trajectory Prediction

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第9期9卷 5571-5580页

作者： Du, Quancheng Wang, Xiao Yin, Shouguo Li, Lingxi Ning, Huansheng University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Anhui University School of Artificial Intelligence Hefei230031 China Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Institute of Automation Beijing100190 China Indiana University-Purdue University Indianapolis School of Electrical and Computer Engineering IndianapolisIN46202 United States

Accurate prediction of agent motion trajectories is crucial for ensuring the safety and reliability of autonomous driving systems. Current research predominantly focuses on traditional deep learning methods, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), which use relative distances to predict the trajectories of a single class of agents. However, in complex traffic scenarios, the motion behaviors of diverse traffic participants exhibit highly stochastic. Sole reliance on relative distances may not sufficiently capture nuanced interaction patterns between different classes of road users. To address this challenge, we propose a novel multi-class trajectory prediction method named the social force embedded mixed graph convolutional network (SFEM-GCN). SFEM-GCN comprises three graph topologies: the semantic graph (SG), position graph (PG), and velocity graph (VG). These graphs encode various social force relationships among different classes of agents in complex scenes. Specifically, SG utilizes one-hot encoding of agent-class information to guide the construction of graph adjacency matrices based on semantic information. PG and VG create adjacency matrices to capture motion interaction relationships between different classes of agents. These graph structures are then integrated into a mixed graph, where learning is conducted using a spatio-temporal graph convolutional neural network (ST-GCNN). To further enhance prediction performance, we adopt temporal convolutional networks (TCNs) to generate the predicted trajectory with fewer parameters. Extensive experiments on the widely recognized open-source dataset demonstrate that SFEM-GCN surpasses state-of-the-art methods in terms of accuracy and robustness. © 2016 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Point Tree Transformer for Point Cloud Registration

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Wang, Meiling Chen, Guangyan Yang, Yi Yuan, Li Yue, Yufeng Beijing Institute of Technology School of Automation Beijing100081 China Peking University School of Electrical and Computer Engineering China

Point cloud registration is a fundamental task in the fields of computer vision and robotics. Recent advancements in transformer-based methods have demonstrated enhanced performance in this domain. However, the standard attention mechanisms employed in these approaches tend to incorporate numerous points of low relevance, and therefore struggle to focus their attention weights on sparse yet meaningful points. This inefficiency leads to limited local structure modeling capabilities and quadratic computational complexity. To overcome these limitations, we propose the Point Tree Transformer (PTT), a novel transformer-based approach for point cloud registration that efficiently extracts comprehensive local and global features while maintaining linear computational complexity. The PTT constructs hierarchical feature trees from point clouds in a coarse-to-dense manner, and introduces a novel Point Tree Attention (PTA) mechanism. This mechanism adheres to the tree structure to facilitate the progressive convergence of attended regions toward salient points. Specifically, each tree layer selectively identifies a subset of relevant points with the highest attention scores, and subsequent layers focus attention on areas of significant relevance, derived from the child points of the selected point set. The feature extraction process additionally incorporates coarse point features that capture high-level semantic information, thus facilitating local structure modeling and the progressive integration of multiscale information. Consequently, the PTA enables the model to focus on essential local structures and extract intricate local information while maintaining linear computational complexity. Extensive experiments conducted on the 3DMatch, ModelNet40, and KITTI datasets demonstrate that our method outperforms state-of-the-art methods in terms of performance. © 1991-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Autoencoder and Teaching-learning-based Optimizer for Mobile Edge Computing System Optimization Problems

Autoencoder and Teaching-learning-based Optimizer for Mobile...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Xu, Dian Zhou, Mengchu Yuan, Haitao Institute of Systems Engineering Macau University of Science and Technology Macao China New Jersey Institute of Technology Department of Electrical and Computer Engineering Newark United States School of Automation Science and Electrical Engineering Beihang University Beijing China

ISBN: (纸本)9798350337020

By using an autoencoder as a dimension reduction tool, an Autoencoder-embedded Teaching-Learning Based Optimization (ATLBO) has been proved to be effective in solving high-dimensional computationally expensive problems through several widely used function problems. However, the following two crucial issues have not been resolved, 1) ATLBO should be verified by solving real-life optimization problems;and 2) how autoencoder parameters and structures impact AEO's performance. In this work, ATLBO is verified by an energy consumption minimization problem (ECM) in mobile edge computing systems. To design an effective autoencoder for ATLBO, this work proposes a parameter tuning optimization strategy for autoencoders. By using the proposed Autoencoder Parameter Tuning (APT) strategy, ATLBO can enjoy higher robustness than those without it. The experimental results show that it is three to six times better than state-of-the-art methods in solving ECM. We consider the strategy-induced overhead and take the execution time as the primary criterion to evaluate them. In addition, the experimental results show that, against the conventional wisdom that higher-accuracy auto encoders bring higher system performance, lower-accuracy ones can actually assist ATLBO in locating the best solutions. This work promotes a novel application of autoencoders in optimization theory and practice. © 2023 IEEE.

关键词： autoencoder Autoencoder-embedded teaching-learning based optimization (ATLBO) High-dimensional expensive problems (HEPs) Mobile edge computing systems

来源：评论

学校读者我要写书评

暂无评论

A New Federated Learning Framework Against Gradient Inversion Attacks 39

A New Federated Learning Framework Against Gradient Inversio...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Pengxin Zeng, Shuang Chen, Wenhao Zhang, Xiaodan Ren, Weihong Zhou, Yuyin Qu, Liangqiong School of Computing and Data Science The University of Hong Kong Hong Kong Department of Mathematics The University of Hong Kong Hong Kong College of Computer Science Beijing University of Technology China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering UC Santa Cruz United States

ISBN: (纸本)157735897X

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to Gradient Inversion Attacks (GIA) and, consequently, a variety of privacy-preserving methods have been integrated into FL to thwart such attacks, such as Secure Multi-party Computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP). Despite their ability to protect data privacy, these approaches inherently involve substantial privacy-utility trade-offs. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy preserve FL framework that effectively "breaks the direct connection" between the shared parameters and the local private data to defend against GIA. Specifically, we propose a Hypernetwork Federated Learning (HyperFL) framework that utilizes hypernetworks to generate the parameters of the local model and only the hypernetwork parameters are uploaded to the server for aggregation. Theoretical analyses demonstrate the convergence rate of the proposed HyperFL, while extensive experimental results show the privacy-preserving capability and comparable performance of HyperFL. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A New Lightweight Attention-Based Model for Emotion Recognition on Distorted Social Media Face Images 1

引用

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Roy, Ayush Shivakumara, Palaiahnakote Pal, Umapada Gornale, Shivanand S. Liu, Cheng-Lin Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Faculty of Computer Science and Information Technology University of Malaya Kula Lumpur Malaysia Department of Computer Science Rani Channamma University Belagavi India Institute of Automation of Chinese Academy of Sciences Beijing China

ISBN: (数字)9783031476372

ISBN: (纸本)9783031476365

The recognition of human emotions remains a challenging task for social media images. This is due to distortions created by different social media conflict with the minute changes in facial expression. This study presents a new model called the Global Spectral-Spatial Attention Network (GSSAN), which leverages both local and global information simultaneously. The proposed model comprises a shallow Convolutional Neural Network (CNN) with an MBResNext block, which integrates the features extracted from MobileNet, ResNet, and DenseNet for extracting local features. In addition, to strengthen the discriminating power of the features, GSSAN incorporates Fourier features, which provide essential cues for minute changes in the face images. To test the proposed model for emotion recognition using social media images, we conduct experiments on two widely-used datasets: FER-2013 and AffectNet. The same benchmark datasets are uploaded and downloaded to create a distorted social media image dataset to test the proposed model. Experiments on distorted social media images dataset show that the model surpasses the accuracy of SOTA models by 0.69% for FER-2013 and 0.51% for AffectNet social media datasets. The same inference can be drawn from the experiments on standard datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Ontology Mapping-Based Semantic Reasoning with OPC UA for Heterogeneous Industrial Devices

Ontology Mapping-Based Semantic Reasoning with OPC UA for He...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Bi, Jing Wu, Rina Yuan, Haitao Wang, Ziqi Zhang, Jia Zhou, MengChu College of Computer Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Southern Methodist University Dept. of Computer Science in Lyle School of Engineering DallasTX United States New Jersey Institute of Technology Dept. of Electrical and Computer Engineering NewarkNJ United States

ISBN: (纸本)9781665410205

The advent of smart manufacturing in Industry 4.0 signifies the arrival of the era of connections. As an excellent communication protocol, Object linking and embedding for Process Control Unified Architecture (OPC UA) can address most semantic heterogeneity issues. However, its semantics are not formally defined at the application layer. To address the information silo problem caused by semantic heterogeneity, a method named Querying of Ontology Mapping-based OPC UA (QOMOU) is proposed. It extracts the information models of OPC UA servers into resource description framework triples, utilizes web ontology language for semantic enrichment and inference, and employs a semantic similarity model for event ontology mapping to improve query efficiency. The method's effectiveness is validated through functional queries using the SPARQL protocol in Apache Jena. The query efficiency is 5% higher on average compared to both structured query and extensible markup languages. Moreover, by employing a keyword-matching algorithm, the query accuracy of the existing heterogeneous data integration scheme is improved by 4% on average. This enhancement can boost the operational efficiency of Internet of Things systems based on the OPC UA architecture. © 2024 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

MobileResNet: A Generalized Lightweight Model for Accurate Leaf Disease Detection Across Diverse Plant Types 21

MobileResNet: A Generalized Lightweight Model for Accurate L...

引用

21st IEEE India Council International Conference, INDICON 2024

作者： Pal, Rikathi Ghoshal, Somoballi Chakrabarti, Amlan Indian Institute of Science Department of Computer Science and Automation Bangalore India A.K. Choudhury School of Information Technology University of Calcutta Kolkata India

ISBN: (纸本)9798350391282

Leaf disease detection is vital for effective and productive agriculture. Although many models exist for detecting leaf diseases, they are often optimized for specific leaf types and diseases. This paper proposes a generalized, simplified, and lightweight two-step model architecture called MobileResNet, which can detect diseases from images of any leaf type. Our model first identifies the plant type from the leaf image and then diagnoses the specific disease affecting it. MobileResNet enhances feature extraction by leveraging both standard convolution and depth-wise separable convolution and incorporating skip connections at strategic points to improve gradient flow and ensure efficient training. Our model performs exceptionally well on 18 varieties of major Indian crops, surpassing eight existing state-of-the-art deep learning architectures. This approach achieves 99.75% accuracy in leaf type identification and over 98% accuracy in identifying leaf disease types across various leading Indian crops, setting a new benchmark in the field. © 2024 IEEE.

关键词： Depthwise Separable Convolution Global Average Pooling Neural Networks Skip Connections

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：