检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Feng, Yi Zhang, Ruge Du, Jiayuan Chen, Qijun Fan, Rui College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China High-Performance Computer Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

— Optical flow and disparity are two informative visual features for autonomous driving perception. They have been used for a variety of applications, such as obstacle and lane detection. The concept of "U-V-Disparity" has been widely explored in the literature, while its counterpart in optical flow has received relatively little attention. Traditional motion analysis algorithms estimate optical flow by matching correspondences between two successive video frames, which limits the full utilization of environmental information and geometric constraints. Therefore, we propose a novel strategy to model optical flow in the collision-free space (also referred to as drivable area or simply freespace) for intelligent vehicles, with the full utilization of geometry information in a 3D driving environment. We provide explicit representations of optical flow and deduce the quadratic relationship between the optical flow component and the vertical coordinate. Through extensive experiments on several public datasets, we demonstrate the high accuracy and robustness of our model. Additionally, our proposed freespace optical flow model boasts a diverse array of applications within the realm of automated driving, providing a geometric constraint in freespace detection, vehicle localization, and more. We have made our source code publicly available at https://***/FSOF. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Research on Word Alignment Based on Embedded Bilingual Words 2021

Research on Word Alignment Based on Embedded Bilingual Words

引用

2nd International Conference on computing and Data Science, CONF-CDS 2021

作者： Wang, Shuang Guo, Qi Wan, Fucheng Key Laboratory of China's Ethnic Languages and Intelligent Processing of Gansu Province Northwest Minzu University Lanzhou China China's Ethnic Information Technology Research Institute Northwest Minzu University Lanzhou China

ISBN: (纸本)9781450389570

Word alignment is one of the most important problems in machine translation. Many machine translation technology solutions require parallel corpus to achieve word level alignment. However, the current mainstream word alignment methods and tools need to maintain a large-scale word translation probability table, which will generate huge network transmission overhead in distributed environment, which is not conducive to parallelization, and exists in the face of large-scale data sets large performance issues. The extensive development of deep learning and the deep application of word embedding technology in natural language processing have opened up a new way for word alignment algorithm. With the advent of bilingual word embedding, it is possible to use word embedding to calculate lexical similarity across languages. In this paper, bilingual word embedding is proposed to calculate the probability of lexical translation, and then word alignment is achieved. Compared with the large word translation probability tables in traditional methods, lightweight word vector tables have a significant advantage in transmission costs, and they are more suitable for large-scale corpus scenarios and distributed computing environments. © 2021 ACM.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Perturbation Synergy Attack for Person Re-identification

arXiv

引用

arXiv 2024年

作者： Gong, Yunpeng Zhong, Zhun Qu, Yansong Luo, Zhiming Ji, Rongrong Jiang, Min School of Informatics Xiamen University China School of Computer Science and Information Engineering Hefei University of Technology China Department of Artificial Intelligence Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Key Laboratory of Digital Protection and Intelligent Processing of Intangible CulturalHeritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University Fujian Xiamen361005 China

In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images. However, the safety of cross-modality scenarios, which are more commonly encountered in practical applications involving images captured by infrared cameras, has not received adequate attention. The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities. For instance, infrared images are typically grayscale, unlike visible images that contain color information. Existing attack methods have primarily focused on the characteristics of the visible image modality, overlooking the features of other modalities and the variations in data distribution among different modalities. This oversight can potentially undermine the effectiveness of these methods in image retrieval across diverse modalities. This study represents the first exploration into the security of cross-modality ReID models and proposes a universal perturbation attack specifically designed for cross-modality ReID. This attack optimizes perturbations by leveraging gradients from diverse modality data, thereby disrupting the discriminator and reinforcing the differences between modalities. We conducted experiments on three widely used cross-modality datasets, namely RegDB, SYSU, and LLCM. The results not only demonstrate the effectiveness of our method but also provide insights for future improvements in the robustness of cross-modality ReID systems. © 2024, CC BY-NC-ND.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Learning Shape-Appearance Based Attributes Representation for Facial Attribute Recognition with Limited Labeled Data

Learning Shape-Appearance Based Attributes Representation fo...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Kunyan Li Jie Zhang Shiguang Shan Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing Technology Beijing CAS China University of Chinese Academy of Sciences Beijing China Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (纸本)9781665431774

The Facial Attribute Recognition (FAR) is a challenging task especially when there exists limited labeled data, which may lead the mainstream fully-supervised FAR methods to be no longer in force. To tackle this problem, we propose a novel unsupervised learning framework named Shape-Appearance Based Attributes Representation Learning (SABAL) by leveraging large-scale unlabeled face data. Considering face attributes are mainly determined by 3D shape and facial appearance, we decouple a face image into 3D shape and appearance features by two branch networks, i.e., 3D Shape Branch and Facial Appearance Branch. 3D Shape Branch and Facial Appearance Branch are jointly trained with orthogonal loss and 2D face reconstruction loss to obtain robust facial representations containing 3D-geometry and texture information, which are beneficial for attributes recognition. Finally, the unsupervised learnt features are transferred to the FAR task by fine-tuning on limited labeled data from CelebA. Extensive experiments show that we achieve comparable results to state-of-the-art methods.

关键词： Representation learning Three-dimensional displays Image recognition Shape Face recognition Lead Task analysis

来源：评论

学校读者我要写书评

暂无评论

Tiny noise, big mistakes: adversarial perturbations induce errors in brain–computer interface spellers

引用

National Science Review 2021年第4期8卷 78-90页

作者： Xiao Zhang Dongrui Wu Lieyun Ding Hanbin Luo Chin-Teng Lin Tzyy-Ping Jung Ricardo Chavarriaga Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Civil Engineering and Mechanics Huazhong University of Science and Technology Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Swartz Center for Computational Neuroscience Institute for Neural ComputationUniversity of California San Diego Center for Advanced Neurological Engineering Institute of Engineering in Medicine University of California San Diego ZHAW Data Lab Zürich University of Applied Sciences

An electroencephalogram(EEG)-based brain–computer interface(BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g. amyotrophic lateral sclerosis patients, who have no other effective means of communication with another person or a *** studies so far focused on making EEG-based BCI spellers faster and more reliable; however, few have considered their security. This study, for the first time, shows that P300 and steady-state visual evoked potential BCI spellers are very vulnerable, i.e. they can be severely attacked by adversarial perturbations,which are too tiny to be noticed when added to EEG signals, but can mislead the spellers to spell anything the attacker wants. The consequence could range from merely user frustration to severe misdiagnosis in clinical applications. We hope our research can attract more attention to the security of EEG-based BCI spellers, and more broadly, EEG-based BCIs, which has received little attention before.

关键词： electroencephalogram brain-computer interfaces BCI spellers adversarial examples

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional Parameter Estimation in RIS-aided MU-MIMO Channels

arXiv

引用

arXiv 2025年

作者： Mo, Linlin Song, Yi Saggese, Fabio Lu, Xinhua Wang, Zhongyong Popovski, Petar Academy for Electronic Information Discipline Studies Nanyang Institute of Technology Nanyang473000 China Key Laboratory of Grain Information Processing and Control Ministry of Education Henan Engineering Research Center of Grain Condition Intelligent Detection and Application Henan University of Technology Zhengzhou450001 China School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China Department of Electronic Systems Aalborg University Aalborg9220 Denmark

We address the channel estimation problem in reconfigurable intelligent surface (RIS) aided broadband systems by proposing a dual-structure and multi-dimensional transformations (DS-MDT) algorithm. The proposed approach leverages the dual-structure features of the channel parameters to assist users experiencing weaker channel conditions, thereby enhancing estimation performance. Moreover, given that the channel parameters are distributed across multiple dimensions of the received tensor, the proposed algorithm employs multidimensional transformations to effectively isolate and extract distinct parameters. The numerical results demonstrate the proposed algorithm reduces the normalized mean square error (NMSE) by up to 10 dB while maintaining lower complexity compared to state-of-the-art methods. © 2025, CC BY.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Tibetan Syllable Component Recognization with Memristor

Tibetan Syllable Component Recognization with Memristor

引用

Neuromorphic computing (ICNC), International Conference on

作者： Yutong Liu Jiarun Shen Yongbin Yu Ban Ma-Bao Thupten Tsering Xiangxiang Wang Cheng Huang Nyima Tashi School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China YiBin Institute University of Electronic Science and Technology of China Yibin China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Normal University Yibin China Department of Ophthalmology University of Texas Southwestern Medical Center Dallas USA School of Information Science and Technology Tibet University Chengdu China

ISBN: (数字)9798331508661

ISBN: (纸本)9798331508678

This paper highlights a Tibetan syllable component recognization method by using memristors. Firstly, a memristor crossbar array with an external control circuit is designed to present both elevated device density and the potential for parallel computing. Then a syllable component recognization method is implemented to classify syllable into seven types, prefix letter, root letter, superscript letter, subscript letter, vowel letter, suffix letter, and farther suffix letter, matching Tibetan characters by computing total current value in memristor crossbar array. Finally, Tibetan characters is re-encoded in binary according to the last two digits of their Unicode, and input by controlling the voltage in memristor crossbar array. Experiments demonstrate that our method recognizes general Tibetan syllable components.

关键词： Deep learning Machine learning algorithms Neuromorphic engineering Memristors Parallel processing Character recognition Voltage control Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning based Collaborative Modelling of Heterogeneous Data for Few-shot Fault Diagnosis

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Zhong, Kai Zhu, Hengchang Zhang, Xiaoming Huang, Darong Han, Min Anhui University Institutes of Physical Science and Information Technology Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Hefei 230601 China Anhui University Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui Provincial Engineering Research Center for Unmanned System and Intelligent Technology School of Artificial Intelligence Anhui Hefei 230601 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian 116024 China

Few-shot diagnosis has received extensive attention recently. Existing methods rarely consider the consistency within and between heterogeneous data, leading to suboptimal diagnosis performance. To address this issue, a contrastive learning based collaborative modelling for few-shot diagnosis is proposed. First of all, a heterogeneous data enhancement workflows with distribution consistency assessment is designed to acquire sufficient industrial process information, which can also mitigate the inconsistency between enhanced data and original data. Following this, convolutional networks with customized structures are used to extract the multimodal features from heterogeneous signals. After that, the collaborative modelling and diagnosis module is devised through the joint optimization of contrastive loss and cross entropy loss, which can shorten the distance of similar samples in feature space and retain cross structure consistency. Finally, the effectiveness and superiority of the proposed method are substantiated through simulated and the real world cases. © 2020 IEEE.

关键词： collaborative modelling contrastive learning Few-shot diagnosis heterogeneous data

来源：评论

学校读者我要写书评

暂无评论

Optimal Sequential False Data Injection Attack Scheme: Finite-Time Inverse Convergence

Optimal Sequential False Data Injection Attack Scheme: Finit...

引用

IEEE Conference on Decision and Control

作者： Xiaoyu Luo Chongrong Fang Chengcheng Zhao Peng Cheng Jianping He The Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China The State Key Laboratory of Industrial Control Technology Institute of Cyberspace Research Zhejiang University China

In this paper, we explore the relationship between the injected attack signal and the attack selection strategy in networked control systems where the adversary desires to steer the system state to the expected malicious one. We construct a sequential attack framework, i.e., the injected false data varies with the sampling time in discrete-time systems, and then derive an optimal sequential FDI attack strategy. The optimal sequential FDI attack strategy reveals the strongly coupled relationship between the injected attack signal and the attack selection strategy. Furthermore, we prove the finite-time inverse convergence of the critical parameters in the injected optimal attack signal by discrete-time Lyapunov analysis, which enables the efficient off-line design of the attack strategy and saves computing sources. Extensive simulations are conducted to show the effectiveness of the injected optimal sequential attack and the relationship between the attack signal and the attack selection strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tibetan Syllable Component Recognization with Memristor 3

Tibetan Syllable Component Recognization with Memristor

引用

3rd International Conference on Neuromorphic computing, ICNC 2024

作者： Liu, Yutong Shen, Jiarun Yu, Yongbin Ma-Bao, Ban Tsering, Thupten Wang, Xiangxiang Huang, Cheng Tashi, Nyima School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China YiBin Institute University of Electronic Science and Technology of China Yibin China Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application Yibin China University of Texas Southwestern Medical Center Department of Ophthalmology Dallas United States School of Information Science and Technology Tibet University Chengdu China

ISBN: (纸本)9798331508661

关键词： Semantics

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：