检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Wu, Anran Xiao, Luwei Wu, Xingjiao Yang, Shuwen Xu, Junjie Zhuang, Zisong Xie, Nian Jin, Cheng He, Liang School of Computer Science and Technology East China Normal University Shanghai200062 China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200062 China School of Computer Science Fudan University Shanghai200433 China Huawei Noah’s Ark Lab Shenzhen518126 China

Visually-situated languages such as charts and plots are omnipresent in real-world documents. These graphical depictions are human-readable and are often analyzed in visually-rich documents to address a variety of questions that necessitate complex reasoning and common-sense responses. Despite the growing number of datasets that aim to answer questions over charts, most only address this task in isolation, without considering the broader context of document-level question answering. Moreover, such datasets lack adequate common-sense reasoning information in their questions. In this work, we introduce a novel task named document-level chart question answering (DCQA). The goal of this task is to conduct document-level question answering, extracting charts or plots in the document via document layout analysis (DLA) first and subsequently performing chart question answering (CQA). The newly developed benchmark dataset comprises 50,010 synthetic documents integrating charts in a wide range of styles and includes 699,051 questions that demand a high degree of reasoning ability and common-sense understanding. Besides, we present the development of a potent question-answer generation engine that employs table data, a rich color set, and question templates to produce a vast array of reasoning question-answer pairs automatically. Based on DCQA, we devise an OCR-free transformer for document-level chart-oriented understanding, capable of DLA and answering complex reasoning and common-sense questions over charts. Our DCQA dataset is expected to foster research on understanding visualizations in documents, especially for scenarios that require complex reasoning for charts in the visually-rich document. We implement and evaluate several baselines, and our proposed method achieves comparable results. © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Context-aware Multi-level Question Embedding Fusion for visual question answering

引用

information Fusion 2024年 102卷

作者： Li, Shengdong Gong, Chen Zhu, Yuqing Luo, Chuanwen Hong, Yi Lv, Xueqiang School of Information Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Zhejiang Lab Zhejiang Hangzhou311121 China Department of Computer Science California State University Los Angeles CA90032 United States School of Information Science and Technology Beijing Forestry University Beijing100083 China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration 100083 China Beijing Key Laboratory of Internet Culture and Digital Dissemination Research Beijing Information Science and Technology University 100101 China

Question model has been widely concerned as the cornerstone of constructing Visual Question Answering (VQA) models. Existing question models attempt to exploit word context to extract multi-level concepts for modeling multi-level questions. However, they still have many defects. For example, most question models utilize simple fusion methods to fuse shallow modules and extract parameter-unshared low-level concepts, leading to poor modeling of multi-level questions;although some question models use deep bidirectional Transformer encoder in external knowledge transfer and BERT for multi-level questions, their complexity is still high. To solve these issues, we propose a novel low-complex multi-level contextual question model, termed Context-aware Multi-level Question Embedding Fusion (CMQEF). We formalize its concepts and theories, deduce its modeling process, optimization process and feature extraction process, analyze its low complexity and high expressiveness, and prove that it defines a new way to solve parameter non-sharing for extracting parameter-shared multi-level concepts and optimize the tradeoff between expressiveness and complexity in question models. Extensive experiments on VQAv2 and VQA-CPv2 validate that comparing with the state-of-the-art, our CMQEF outperforms it on SANs and UpDn, reduces the language priors of SANs and UpDn, and has preferable interpretability and applicability. Our code is available at https://***/lsdruc/CMQEF-for-VQA. © 2023 The Author(s)

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Divide and Conquer: Hybrid Pre-training for Person Search

arXiv

引用

arXiv 2023年

作者： Tian, Yanling Chen, Di Liu, Yunan Yang, Jian Zhang, Shanshan PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Artificial Intelligence Dalian Maritime University China

Large-scale pre-training has proven to be an effective method for improving performance across different tasks. Current person search methods use ImageNet pre-trained models for feature extraction, yet it is not an optimal solution due to the gap between the pre-training task and person search task (as a downstream task). Therefore, in this paper, we focus on pretraining for person search, which involves detecting and reidentifying individuals simultaneously. Although labeled data for person search is scarce, datasets for two sub-tasks person detection and re-identification are relatively abundant. To this end, we propose a hybrid pre-training framework specifically designed for person search using sub-task data only. It consists of a hybrid learning paradigm that handles data with different kinds of supervisions, and an intra-task alignment module that alleviates domain discrepancy under limited resources. To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data. Extensive experiments demonstrate that our pre-trained model can achieve significant improvements across diverse protocols, such as person search method, finetuning data, pre-training data and model backbone. For example, our model improves ResNet50 based NAE by 10.3% relative improvement w.r.t. mAP. Our code and pre-trained models are released for plug-and-play usage to the person search community (https://***/personsearch/PretrainPS). Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Charging Out Rectangle: Quadrangle IoU for Scene Text Detection under Balanced Supervision 25

Charging Out Rectangle: Quadrangle IoU for Scene Text Detect...

引用

Proceedings of the 4th International Conference on computer, Artificial Intelligence and Control Engineering

作者： Min Ma Xiangnan Zhang Wang Bin Qiuli Wang Kexing Che School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China Key Laboratory of Intelligent Information Processing Corporation Key Laboratory of Aperture Array and Space Application The 38th Research Institute of China Electronics Technology Group Hefei Anhui China Government and Enterprise Division China Unicom Shandong Branch Jinan Shandong China School of Electronic Engineering Xidian University Xi' an Shaanxi China

ISBN: (纸本)9798400712647

In the past few years, text detection approaches have been able to cope with more and more challenging complex scenes. In this field, the arbitrary shape and various scale of text instances are the two most frequently mentioned topics. Among the existing methods, the bounding box prediction methods based on Intersection over Union (IoU) are efficient, but can only handle multi-oriented rectangles. Although arbitrary shape text detection methods have been proposed, these methods are often aimed at curved text. Besides, the post-processing is usually cumbersome. Considering that the affine transformation phenomenon caused by out-plane rotation is more frequent than curved text in real scenario, we design a quadrangle IoU (QIoU) loss to efficiently predict arbitrary convex quadrangle text. Furthermore, we analyze the challenge of variable scale in text detection from the perspective of unbalanced supervision information, and propose a cross-scale knowledge distillation (CSKD) method to improve the detection accuracy of large-scale text. An extensive ablation study demonstrates the effectiveness and superiority of the proposed strategies. During inferring, our method does not consume extra time. Using the basic feature pyramid network for feature extraction, our method achieves state-of-the-art results on several popular datasets for scene text detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedDLM: A Fine-Grained Assessment Scheme for Risk of Sensitive information Leakage in Federated Learning-based Android Malware Classifier

FedDLM: A Fine-Grained Assessment Scheme for Risk of Sensiti...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Changnan Jiang Chunhe Xia Chen Chen Huacheng Li Tianbo Wang Xiaojian Li Beijing Key Lab. of Network Technology Beihang University Beijing China Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing Guangxi Normal University Guilin China School of Cyber Science and Technology Beihang University Beijing China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China College of Computer Science and Information Technology Guangxi Normal University Guilin China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

In the traditional centralized Android malware classification framework, privacy concerns arise as it requires collecting users’ app samples containing sensitive information directly. To address this problem, new classification frameworks based on Federated Learning (FL) have emerged for privacy preservation. However, research shows that these frameworks still face risks of indirect information leakage due to adversary inference. Unfortunately, existing research lacks an effective assessment of the extent and location of this leakage risk. To bridge the gap, we propose the FedDLM, which provides a fine-grained assessment of the risk of sensitive information leakage in an FL-based Android malware classifier. FedDLM estimates attackers’ theoretical maximum inference ability from the information theory perspective to gauge the degree of leakage risk in the classifier effectively. It precisely identifies critical positions in the shared gradient where the leakage risk exists by utilizing characteristics of class activation in classifiers. Through extensive experiments on the Androzoo dataset, FedDLM demonstrates its superior effectiveness and precision compared to baseline methods in evaluating the risk of sensitive information leakage. The evaluation results provide valuable insights into information leakage problems in classifiers and targeted privacy protection methods.

关键词： Meters Privacy Federated learning information leakage Malware Security Risk management

来源：评论

学校读者我要写书评

暂无评论

HF-Mid: A Hybrid Framework of Network Intrusion Detection for Multi-type and Imbalanced Data

HF-Mid: A Hybrid Framework of Network Intrusion Detection fo...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Weidong Zhou Tianbo Wang Guotao Huang Xiaopeng Liang Chunhe Xia Xiaojian Li Beijing Key Lab. of Network Technology Beihang University Beijing China School of Cyber Science and Technology Beihang University Beijing China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Guangxi Collaborative Innovation Center of Multi-source Information Integration and Intelligent Processing Guangxi Normal University Guilin China College of Computer Science and Information Technology Guangxi Normal University Guilin China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

The data-driven deep learning methods have brought significant progress and potential to intrusion detection. However, there are two thorny problems caused by the characteristics of intrusion data: "multi-type features" and "data imbalance". The former means that forcefully and improperly transforming intrusion features from distinct metric spaces can result in semantic loss and noise. The latter indicates that the intrusion data is imbalanced in quantity and quality due to its complex spatial distribution. We propose a Hybrid Framework for Multi-type and Imbalance Data (HF-Mid) to address the above two problems. Firstly, we divide the intrusion features into equivalent and non-equivalent groups, and then embed them sequentially using Supervised Paragraph Vector-Distributed Memory (SPV-DM), which excels at modeling co-occurrence relationships, and Deep Neural Network (DNN), which is suitable for modeling non-linear relationships, thereby solving the "multitype features" problem. Secondly, we adopt a low-noise collective matrix factorization (CMF) model to fuse the two obtained features for dimensionality reduction. Finally, we employ a multiple classifier to detect intrusion. During the classifier training stage, we design a genetic algorithm-based proportional sampling method to select high-quality samples in each training batch. thus addressing the "data imbalance" problem. The experimental results demonstrate the proposed framework exhibits an overall improvement of 5.9% and 1.5% in terms of accuracy and false positive rate on average, respectively.

关键词： Training Privacy Fuses Noise Semantics Artificial neural networks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MOTION MATTERS: A NOVEL MOTION MODELING FOR CROSS-VIEW GAIT FEATURE LEARNING

arXiv

引用

arXiv 2022年

作者： Li, Jingqi Gao, Jiaqi Zhang, Yuzhen Shan, Hongming Zhang, Junping Shanghai Key Lab of Intelligent Information Processing School of Computer Science China Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China

As a unique biometric that can be perceived at a distance, gait has broad applications in person authentication, social security and so on. Existing gait recognition methods suffer from changes in viewpoint and clothing and barely consider extracting diverse motion features, a fundamental characteristic in gaits, from gait sequences. This paper proposes a novel motion modeling method to extract the discriminative and robust representation. Specifically, we first extract the motion features from the encoded motion sequences in the shallow layer. Then we continuously enhance the motion feature in deep layers. This motion modeling approach is independent of mainstream work in building network architectures. As a result, one can apply this motion modeling method to any backbone to improve gait recognition performance. In this paper, we combine motion modeling with one commonly used backbone (GaitGL) as GaitGL-M to illustrate motion modeling. Extensive experimental results on two commonly-used cross-view gait datasets demonstrate the superior performance of GaitGL-M over existing state-of-the-art methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

An RTDNN-Based Hybrid Precoding and Combining Joint Optimization Algorithm for MUPC-MIMO Systems

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Liu, Fulai Liu, Yubiao Yang, Xianghuan Duan, Zhuoyao Shi, Baozhu Ji, Li Du, Ruiyan Northeastern University at Qinhuangdao Lab of Key Technology of Millimeter-wave Large-scale MIMO System Hebei Key Laboratory of Marine Perception Network and Data Processing Qinhuangdao066004 China Hebei University College of Mathematics and Information Science Baoding071002 China Northeastern University School of Computer Science and Engineering Shenyang110819 China Qinhuangdao Vocational and Technical College Qinhuangdao066100 China School of Computer Science and Engineering Northeastern University Shenyang110004 China

To achieve a satisfactory balance between energy efficiency (EE) and spectral efficiency (SE) for hybrid precoding and combining (HPC), this paper presents a two-stage joint optimization HPC algorithm based on residual deep neural network (DNN) for multi-user partially connected (MUPC) structure, namely RTDNN algorithm. In the proposed algorithm, a two-stage framework is designed to optimize analog and digital coders at the transmitter and receiver simultaneously, which can effectively preserve coupling relationship of coders between the transmitter and receiver. Specially, the RTDNN architecture is mainly divided into two stage networks, which includes analog stage and digital stage networks. The analog stage network is developed to obtain the optimal analog precoder and combiner simultaneously. On this basis, the digital stage network is constructed to solve the digital precoder and combiner concurrently. To further improve the prediction accuracy of RTDNN-based HPC, residual modules are adopted into the developed two stage networks. Moreover, the proposed RTDNN is trained with unsupervised learning. Simulation results show that the EE of the proposed algorithm is at least enhanced by 0.6 bits/Hz/J with satisfactory SE than other methods. © 2017 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN

arXiv

引用

arXiv 2023年

作者： Xu, Guoan Li, Juncheng Gao, Guangwei Lu, Huimin Yang, Jian Yue, Dong The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210049 China The Kyushu Institute of Technology Kitakyushu804-8550 Japan The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210049 China

In the past decade, convolutional neural networks (CNNs) have shown prominence for semantic segmentation. Although CNN models have very impressive performance, the ability to capture global representation is still insufficient, which results in suboptimal results. Recently, Transformer achieved huge success in NLP tasks, demonstrating its advantages in modeling long-range dependency. Recently, Transformer has also attracted tremendous attention from computer vision researchers who reformulate the image processing tasks as a sequence-to-sequence prediction but resulted in deteriorating local feature details. In this work, we propose a lightweight real-time semantic segmentation network called LETNet. LETNet combines a U-shaped CNN with Transformer effectively in a capsule embedding style to compensate for respective deficiencies. Meanwhile, the elaborately designed Lightweight Dilated Bottleneck (LDB) module and Feature Enhancement (FE) module cultivate a positive impact on training from scratch simultaneously. Extensive experiments performed on challenging datasets demonstrate that LETNet achieves superior performances in accuracy and efficiency balance. Specifically, It only contains 0.95M parameters and 13.6G FLOPs but yields 72.8% mIoU at 120 FPS on the Cityscapes test set and 70.5% mIoU at 250 FPS on the CamVid test dataset using a single RTX 3090 GPU. Source code will be available at https://***/IVIPlab/LETNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Online Prototype Learning for Online Continual Learning

Online Prototype Learning for Online Continual Learning

引用

International Conference on computer Vision (ICCV)

作者： Yujie Wei Jiaxin Ye Zhizhong Huang Junping Zhang Hongming Shan Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University MOE Frontiers Center for Brain Science Fudan University Shanghai Center for Brain Science and Brain-Inspired Technology

Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based methods have shown promising performance. Unlike previous methods that focus on sample storage or knowledge distillation against catastrophic forgetting, this paper aims to understand why the online learning models fail to generalize well from a new perspective of shortcut learning. We identify shortcut learning as the key limiting factor for online CL, where the learned features may be biased, not generalizable to new tasks, and may have an adverse impact on knowledge distillation. To tackle this issue, we present the online prototype learning (OnPro) framework for online CL. First, we propose online prototype equilibrium to learn representative features against shortcut learning and discriminative features to avoid class confusion, ultimately achieving an equilibrium status that separates all seen classes well while learning new classes. Second, with the feedback of online prototypes, we devise a novel adaptive prototypical feedback mechanism to sense the classes that are easily misclassified and then enhance their boundaries. Extensive experimental results on widely-used benchmark datasets demonstrate the superior performance of OnPro over the state-of-the-art baseline methods. Source code is available at https://***/weilllllls/OnPro.

关键词：

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：