检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Gao, Guangwei Xu, Guoan Yu, Yi Xie, Jin Yang, Jian Yue, Dong Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China Digital Content and Media Sciences Research Division National Institute of Informatics Tokyo101-8430 Japan Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China College of Automation and College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing210023 China School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China

In recent years, how to strike a good trade-off between accuracy, inference speed, and model size has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones. In this study, we devise a novel lightweight network using a multi-scale context fusion (MSCFNet) scheme, which explores an asymmetric encoderdecoder architecture to alleviate these problems. More specifically, the encoder adopts some developed efficient asymmetric residual (EAR) modules, which are composed of factorization depth-wise convolution and dilation convolution. Meanwhile, instead of complicated computation, simple deconvolution is applied in the decoder to further reduce the amount of parameters while still maintaining the high segmentation accuracy. Also, MSCFNet has branches with efficient attention modules from different stages of the network to well capture multiscale contextual information. Then we combine them before the final classification to enhance the expression of the features and improve the segmentation efficiency. Comprehensive experiments on challenging datasets have demonstrated that the proposed MSCFNet, which contains only 1.15M parameters, achieves 71.9% Mean IoU on the Cityscapes testing dataset and can run at over 50 FPS on a single Titan XP GPU configuration. Copyright © 2021, 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

Learning fair face representation with progressive cross transformer

arXiv

引用

arXiv 2021年

作者： Li, Yong Sun, Yufei Cui, Zhen Shan, Shiguang Yang, Jian Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology

Face recognition (FR) has made extraordinary progress owing to the advancement of deep convolutional neural networks. However, demographic bias among different racial cohorts still challenges the practical face recognition system. The race factor has been proven to be a dilemma for fair FR (FFR) as the subject-related specific attributes induce the classification bias whilst carrying some useful cues for FR. To mitigate racial bias and meantime preserve robust FR, we abstract face identityrelated representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition. Originating from the signal decomposition theory, we attempt to decouple face representation into i) identity-related components and ii) noisy/identity-unrelated components induced by race. As an extension of signal subspace decomposition, we formulate face decoupling as a generalized functional expression model to cross-predict face identity and race information. The face expression model is further concretized by designing dual cross-transformers to distill identity-related components and suppress racial noises. In order to refine face representation, we take a progressive face decoupling way to learn identity/racespecific transformations, so that identity-unrelated components induced by race could be better disentangled. We evaluate the proposed PCT on the public fair face recognition benchmarks (BFW, RFW) and verify that PCT is capable of mitigating bias in face recognition while achieving state-of-the-art FR performance. Besides, visualization results also show that the attention maps in PCT can well reveal the race-related/biased facial regions. © 2021, CC BY-NC-SA.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Shortest Path Query Approach for Encrypted Graphs Based on Padding Dictionary Structure

A Shortest Path Query Approach for Encrypted Graphs Based on...

引用

Chinese Automation Congress (CAC)

作者： Ming Yang Kaiyang Zhang Chao Mu Xin Wang Yuanlong Liu Heng Zhang Key Laboratory of Computing Power Network and Information Security Shandong Computer Science Center Ministry of Education 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 State Grid Shandong Electric Power Company Jinan China School of Computer Engineering Jiangsu Ocean University Lianyungang China

Hybrid intelligence has emerged as an innovative approach that synergistically combines the strengths of human intelligence and artificial intelligence (AI) to address complex problems. In this paradigm, knowledge graphs play a pivotal role by supplying vital background information and contextual understanding to hybrid intelligence systems. However, due to limitations in local storage capacity, managing large-scale graph data often requires outsourcing to cloud servers. Nevertheless, the use of untrusted cloud servers poses a risk of potential user data leaks. To address these concerns, this paper presents an encryption scheme specifically designed to protect graph data, enabling queries involving intermediate nodes in the shortest path between two nodes within the graph. The proposed scheme ensures the privacy and security of outsourced data by employing a novel method that utilizes padding dictionary structure encryption. This method ensures strict limitations on the cloud server's capabilities, restricting it solely to query operations, it effectively prevents any compromise of user data or unauthorized access to sensitive information, users can securely store and process their graph data on servers, significantly reducing the potential risk of data leakage and unauthorized breaches. To validate the feasibility and effectiveness of the proposed solution, practical experiments were conducted using real-world data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Existence of ternary perfect sequences with a few zero elements

Existence of ternary perfect sequences with a few zero eleme...

引用

International Workshop on Signal Design and Its Applications in Communications (IWSDA)

作者： Xudong Li Pingzhi Fan Wai Ho Mow School of Mathematics and Computer Engineering Xihua University Chengdu China Provincial Key Laboratory of Information Coding and Transmission Institute of Mobile Communications Southwest Jiaotong University Chengdu China Department of Electronic & Computer Engineering Hong Kong University of Science and Technology Hong Kong China

Ternary perfect sequences, which include the binary perfect sequences as special cases, are introduced. The new notions of elementary transformations on ternary perfect sequences are brought forward. Necessary conditions for ternary perfect sequences with k zero elements are proposed. It is proved that there exist no ternary perfect sequences of even lengths with one zero element, and no ternary perfect sequences of odd lengths with two zero elements. It is also proved that there exist no ternary perfect sequences of any length with two adjacent zero elements. An efficient search algorithm for ternary perfect sequences is given.

关键词： Correlation Equations Energy efficiency Educational institutions Algorithm design and analysis information theory computers

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Noise-Guided Progressive Network for Image Splicing Detection and Localization

SSRN

引用

SSRN 2024年

作者： Zhang, Dengyong Jiang, Ningjing Li, Feng Chen, Jiaxin Liao, Xin Yang, Gaobo Ding, Xiangling Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha410114 China School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410114 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China School of Computer and Communication Engineering Hunan University of Science and Technology Hunan Xiangtan411201 China

Image splicing can easily be used in illegal activities, which may have negative impact on society. Therefore, detecting splicing images and precisely localizing tampered regions are challenging tasks. In this work, we propose a dual-branch Multi-Scale Noise-Guided Progressive Network (MSNP-Net). The multi-resolution branch extracts deep semantic features of images while suppressing redundant noise. A multi-scale noise-guided branch is designed to capture more subtle tampering artifacts and guide the network to strengthen the learning of spatial structure features. The two branches complement and restrict each other. The features of different scales are fused in a gradual mechanism, and the feature expression is aggregated through the spatial channel feature aggregation module (SCAM). A large number of experiments show that the MSNP-Net proposed in this paper has better completeness and lower false alarm rate for the detection and localization of spliced images. It can achieve more refined detection results, and has good stability and robustness. Significantly outperforms other state-of-the-art methods. © 2024, 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

Cycle extendability of hamiltonian strongly chordal graphs

arXiv

引用

arXiv 2020年

作者： Rong, Guozhen Li, Wenjun Wang, Jianxin Yang, Yongjie School of Computer Science and Engineering Central South University Changsha China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha China Faculty of Human and Business Sciences Saarland University Saarbrücken Germany

In 1990, Hendry conjectured that all Hamiltonian chordal graphs are cycle extendable. After a series of papers confirming the conjecture for a number of graph classes, the conjecture is yet refuted by Lafond and Seamone in 2015. Given that their counterexamples are not strongly chordal graphs and they are all only 2-connected, Lafond and Seamone asked the following two questions: (1) Are Hamiltonian strongly chordal graphs cycle extendable? (2) Is there an integer k such that all k-connected Hamiltonian chordal graphs are cycle extendable? Later, a conjecture stronger than Hendry’s is proposed. In this paper, we resolve all these questions in the negative. On the positive side, we add to the list of cycle extendable graphs two more graph classes, namely, Hamiltonian 4-FAN-free chordal graphs where every induced K5 − e has true twins, and Hamiltonian {4-FAN, A}-free chordal graphs. Copyright © 2020, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Enhancing Programming Course Quality through Human Posture Recognition and Screen Content Detection

Enhancing Programming Course Quality through Human Posture R...

引用

information Science and Education (ICISE-IE), International Conference on

作者： Xiaopan Chen Haiyang Bai Xiaoke Zhu Lingyuan Dong School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

The evaluation of programming course instruction is a key component of educational management. However, relying solely on supervising teachers for assessment poses challenges in comprehensive evaluation and providing feedback on students' classroom learning status. Additionally, a significant amount of monitoring video data from programming courses in Chinese universities remains underutilized. To address these challenges, this paper combines traditional educational management with artificial intelligence and proposes an intelligent algorithm for detecting students' learning status in programming courses. We first establish a dual YOLO network model to analyze students' postures and screen content in programming classroom monitoring videos, thereby identifying their behaviors. Subsequently, we develop a Programming Classroom Student Behavior Recognition System (PCSBS) that integrates data collection, student behavior detection, and result visualization functionalities. Experimental results demonstrate that the system can accurately provide feedback on students' programming course learning status, offering graded results that assist supervising teachers in their classroom instructional evaluation tasks to enhance educational management efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Performance Distributed Control Law for Large-Scale Linear Systems: A Partitioned Distributed Observer Approach

arXiv

引用

arXiv 2024年

作者： Xu, Haotian Liu, Shuai Shi, Ling Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

In recent years, the distributed-observer-based distributed control law has shown powerful ability to arbitrarily approximate the centralized control performance. However, the traditional distributed observer requires each local observer to reconstruct the state information of the whole system, which is unrealistic for large-scale scenarios. To fill this gap, this paper develops a greedy-idea-based large-scale system partition algorithm, which can significantly reduce the dimension of local observers. Then, the partitioned distributed observer for large-scale systems is proposed to overcome the problem that the system dynamics are difficult to estimate due to the coupling between partitions. Furthermore, the two-layer Lyapunov analysis method is adopted and the dynamic transformation lemma of compact errors is proved, which solves the problem of analyzing stability of the error dynamic of the partitioned distributed observer. Finally, it is proved that the distributed control law based on the partitioned distributed observer can also arbitrarily approximate the control performance of the centralized control law, and the dimension of the local observer is greatly reduced compared with the traditional method. The simulation results show that when the similarity between the physical network and the communication network is about 80%, the local observer dimension is greatly reduced by 90% and the relative error between the performance of the distributed control law and that of the centralized control law is less than 1%. © 2024, CC BY.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Learning Latent Semantic Attributes for Zero-Shot Object Detection

Learning Latent Semantic Attributes for Zero-Shot Object Det...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Kang Wang Lu Zhang Yifan Tan Jiajia Zhao Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineer Institute Beijing China

ISBN: (数字)9781728192284

ISBN: (纸本)9781728185361

Zero-shot Object Detection (ZSD) aims to locate and classify instances of unseen categories. Existing methods focus on learning the mapping from visual space to semantic space, while the learning of discriminative representations for ZSD has not gained enough attention. In this paper, we demonstrate the necessity to learn discriminative semantic representations for ZSD, and propose a new end-to-end framework for this task. Our framework is able to learn discriminative semantic representations in an augmented space introduced for both user-defined and latent attributes, and refine the user-defined attributes with the help of unseen and external classes. The proposed method is extensively evaluated on two challenging ZSD datasets, and the experimental results show that our method significantly outperforms several existing methods.

关键词： Visualization Conferences Semantics Object detection Tools Boosting Task analysis

来源：评论

学校读者我要写书评

暂无评论

Semantic Relation-Based Cross Attention Network for Image-Text Retrieval

Semantic Relation-Based Cross Attention Network for Image-Te...

引用

IEEE International Conference on Systems, Man and Cybernetics

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)9781665410205

ISBN: (纸本)9781665410212

Image-text retrieval refers to querying the text or image of another modality given an image or text, and its key lies in the ability to accurately measure the similarity between text and image. Most of the existing retrieval methods only utilize the intramodal relations of each modality or the intermodal relations of the two modalities to perform the retrieval task. To address the above problems, we integrate the intra-modal and inter-modal relations and propose a Semantic Relation-based Cross Attention Network(SRCAN). In our proposed method, we first mine the possible intra-modal associations between regions in an image and between words in a text to obtain features with semantic relationships, and then capture the fine-grained associations between segments through the cross-attention mechanism. Finally, we balance the intra-modal and inter-modal relationships to improve the performance of the model. Our proposed method is experimentally validated on two datasets, Flickr30K and MS-COCO, and the experimental results show that our method achieves superior results.

关键词： Image segmentation Semantics Bidirectional control Feature extraction Cognition Feeds Cybernetics

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：