检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ye, Maoyuan Zhang, Jing Zhao, Shanshan Liu, Juhua Liu, Tongliang Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computer Science Faculty of Engineering The University of Sydney Australia JD Explore Academy *** China College of Computing & Data Science Nanyang Technological University Singapore

End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection, recognition, and script identification simultaneously. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, our method not only performs well in English scenes but also masters the transcription with complex font structure and a thousand-level character classes, such as Chinese. On the other hand, our DeepSolo++ achieves better performance on the additionally introduced script identification task with a simpler training pipeline compared with previous methods. Extensive experiments on public benchmarks demonstrate that our simple approach achieves better training efficiency compared with Transformer-based models and outperforms the previous state-of-the-art. For example, on ICDAR 2019 ReCTS for Chinese text, our method boosts the 1-NED metric to a new record of 78.3%. On ICDAR 2019 MLT, DeepSolo++ achieves absolute 5.5% H-mean and 8.0% AP improvements on joint detection an

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GPU-based simulation of ocean water using fluid dynamics model and displacement mapping

引用

ICIC Express Letters 2016年第6期10卷 1239-1245页

作者： Xu, Jie Fu, Jinhua Zhang, Hongtao School of Software Zhengzhou University of Light Industry No. 5 Dongfeng Road Zhengzhou450002 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450002 China School of Computer and Communication Engineering Zhengzhou University of Light Industry No. 5 Dongfeng Road Zhengzhou450002 China College of Information Engineering Zhengzhou University No. 100 Kexue Ave. Zhengzhou450000 China

Real-time realistic simulation of liquids like ocean water is an important task nowadays in the field of computer graphics. In this paper, we present a novel method to achieve plausible visual results of ocean water at higher rendering rates. Based on evolution of the density and the velocity, we establish the fluid dynamics model to express properties of the fluid and simulate ocean water efficiently. Also we implement the displacement mapping by utilizing the heightmap and design the shading shader on the GPU (Graphics Processing Unit), which gives a realistic appearance in higher rendering speed. The results show that we can acquire realistic rendering effects such as water color, light reflection, caustics and soft shadow, while achieving a relatively faster speed of rendering. © 2016 ISSN.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Revisiting Token Dropping Strategy in Efficient BERT Pretraining

arXiv

引用

arXiv 2023年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Liu, Xuebo Zhang, Min Du, Bo Tao, Dacheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China Institute of Computing and Intelligence Harbin Institute of Technology China University of Sydney Australia

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training time without degrading much performance on downstream tasks. However, we empirically find that token dropping is prone to a semantic loss problem and falls short in handling semantic-intense tasks (§2). Motivated by this, we propose a simple yet effective semantic-consistent learning method (SCTD) to improve the token dropping. SCTD aims to encourage the model to learn how to preserve the semantic information in the representation space. Extensive experiments on 12 tasks show that, with the help of our SCTD, token dropping can achieve consistent and significant performance gains across all task types and model sizes. More encouragingly, SCTD saves up to 57% of pretraining time and brings up to +1.56% average improvement over the vanilla token dropping. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Fisher+Kernel criterion for discriminant analysis

Fisher+Kernel criterion for discriminant analysis

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Shu Yang Shuicheng Yan Dong Xu Xiaoou Tang Chao Zhang National Laboratory on Machine Perception First Hospital Peking University Beijing China Department of Information Engineering Chinese University of Hong Kong Sha Tin Hong Kong China MOE-Microsoft Key Laboratory of Multimedia Computing and Communication & Department of EEIS University of Science and Technology Hefei Anhui China Microsoft Research Asia Beijing China

ISBN: (纸本)0769523722

We simultaneously approach two tasks of nonlinear discriminant analysis and kernel selection problem by proposing a unified criterion, Fisher+Kernel criterion. In addition, an efficient procedure is derived to optimize this new criterion in an iterative manner. More specifically, original input vector is first transformed into a higher dimensional feature matrix through a battery of nonlinear mappings involved in different kernels. Then, based on the feature matrices, FKC is presented within two coupled projection spaces: one projection space is used to search for the optimal combinations of kernels; while the other encodes the optimal nonlinear discriminating projection directions. Our proposed method is a unified framework for both kernel selection and nonlinear discriminant analysis. Besides, the algorithm potentially alleviates overfitting problem existing in traditional KDA and has no singularity problems in most cases. The effectiveness of our proposed algorithm is validated by extensive face recognition experiments on several datasets.

关键词： Kernel Laboratories Asia Face recognition Linear discriminant analysis Design optimization Chaotic communication Multimedia computing Batteries Couplings

来源：评论

学校读者我要写书评

暂无评论

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge computing Environment

引用

China communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

来源：评论

学校读者我要写书评

暂无评论

Hidden Follower Detection via Refined Gaze and Walking State Estimation

Hidden Follower Detection via Refined Gaze and Walking State...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yaxi Chen Ruimin Hu Danni Xu Zheng Wang Linbo Luo Dengshi Li National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computing the National University of Singapore Singapore School of Cyber Engineering Xidian University Xi’an China School of Artificial Intelligence Jianghan University Wuhan China

Hidden following is following behavior with special intentions, and detecting hidden following behavior can prevent many criminal activities in advance. The previous method uses gaze and spacing behaviors to distinguish hidden followers from normal pedestrians. However, they express gaze behaviors in a coarse-grained way with binary values, making it difficult to accurately depict the gaze state of pedestrians. To this end, we propose the Refined Hidden Follower Detection (RHFD) model by choosing a suitable mapping function based on the principle that the closer the gaze direction is to someone, the more likely it is to gaze at someone, which converts the gaze direction into a continuous estimated gaze state representing the complex and variable gaze behavior of pedestrians. Simultaneously, we introduce variations in the magnitude and direction of pedestrian velocity to refine the representation of pedestrian walking states. Experimental results on the surveillance dataset show that RHFD outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-adaptive method dealing with the end issue of EMD

引用

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2007年第10期35卷 1944-1948页

作者： Shao, Chen-Xi Wang, Jian Fan, Jin-Feng Yang, Ming Wang, Zi-Cai MOE-Microsoft Key Laboratory of Multimedia Computing and Communication University of Science and Technology of China Hefei 230026 China Department of Computer Science and Technology University of Science and Technology of China Hefei 230026 China Control and Simulation Center Harbin Institute of Technology Harbin 150001 China Anhui Province Key Laboratory of Software in Computing and Communication Hefei 230027 China

The empirical mode decomposition (EMD) developed by Huang etc. of NASA is an advanced method for signal analysis. But there is an involved end issue in the course of getting two envelops of the data using spline interpolation. A self-adaptive method to dealing with the end issue is proposed. Generally, it extends the externa sequence near the ends of the data by the most suited sequence in the inner data. For the chosen inner sequence has the most similarity of tendency with the ends, the data extension is reasonable. After the extension, the spline does not swing at both ends of the data. The result of experiment proved that the method can be used to solve the end issue effectively.

关键词： Signal analysis

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Slight Convolutional Neural Network for Vehicle Type Classification

引用

Journal of Physics: Conference Series 2018年第1期1069卷

作者： Haibo Zheng Naijie Gu Xiaoci Zhang Anhui Province Key Laboratory of Computing and Communication Software School of Computer and Technology University of Science and Technology of China Hefei China

With the popularity of small storage embedded devices, recent researches on deep convolutional neural networks no longer only focus on improving the classification accuracy but start to attach great importance to the size of convolutional neural networks. This paper proposes a small deep convolutional neural network for vehicle type classification, based on the Fire module and the residual module. The Fire module is applied to maintain a small number of parameters. The residual module is employed to accelerate the training process and improves the classification accuracy. Experimental results show that our model achieves 95.57% accuracy of vehicle type classification on an open source dataset BIT-Vehicle. This outperforms previous researches and some classical convolutional neural networks such as AlexNet, ResNet-32 and SqueezeNet. What is more, the size of our model is only 5.3 MB, which has 40X fewer parameters than AlexNet and has 15X fewer parameters than ResNet-32.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MISA: Unveiling the Vulnerabilities in Split Federated Learning

MISA: Unveiling the Vulnerabilities in Split Federated Learn...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wei Wan Yuxuan Ning Shengshan Hu Lulu Xue Minghui Li Leo Yu Zhang Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University Cluster and Grid Computing Lab

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users’ devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of *** this paper, we present a novel poisoning attack known as $\color{Fuchsia} {{\text{MISA}}}$. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention.

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：