检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Feng, Yongxiang He, Weihua You, Kaichao Liu, Bing Zhang, Ziyang Wang, Yaoyuan Li, Minglei Lou, Yihang Li, Jiawei Li, Guoqi Liao, Jianxing Huawei Technologies Co. Ltd. Advanced Computing and Storage Lab China Peking University School of Electronics Engineering and Computer Science China Huawei Technologies Co. Ltd. Language & Speech Innovation Lab China Huawei Technologies Co. Ltd. GoTen AI Lab Department of Intelligent Vision China Huawei Technologies Co. Ltd. Department of Production Automation Development China Chinese Academy of Sciences Institute of Automation China

ISBN: (纸本)9781728163277

Deploying deep learning models to new environments is very challenging. Domain adaptation (DA) is a promising paradigm to solve the problem by collecting and adapting to unlabeled data in new environments. Though research efforts have led to steady performance improvement over the past decade, DA algorithms are still hard to deploy, as training on unlabeled new data makes tuning difficult and not feasible for inference-only devices. To make DA practical, in this paper we study a new problem named Test-time Training-Free Domain Adaptation (TTDA), where trained models must adapt to a single input (mimicking the test-time scenario) without training. By exploiting spatial activation that was previously overlooked and simply averaged out, we propose a simple method based on Feature Statistics Transformation (FST) on-the-fly for each test example. The proposed algorithm is tested in the TTDA setting on two standard DA benchmarks. Surprisingly, it surpasses or performs on par with state-of-the-art DA methods, even though they require additional training. We envision that this training-free paradigm has the potential to bring DA to embedded devices and would be of interest to audience of community. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models 38

FIRE: A Dataset for Feedback Integration and Refinement Eval...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deepwalk-aware graph convolutional networks

引用

Science China(Information Sciences) 2022年第5期65卷 81-95页

作者： Taisong JIN Huaqiang DAI Liujuan CAO Baochang ZHANG Feiyue HUANG Yue GAO Rongrong JI Media Analytics and Computing Lab Department of Computer Science and Technology School of InformaticsXiamen University Media Analytics and Computing Lab Department of Artificial Intelligence School of InformaticsXiamen University School of Automation Science and Electrical Engineering Beihang University Tencent Youtu Lab School of Software Tsinghua University

Graph convolutional networks(GCNs) provide a promising way to extract the useful information from graph-structured data. Most of the existing GCNs methods usually focus on local neighborhood information based on specific convolution operations, and ignore the global structure of the input data. To extract the latent representation for the graph-structured data more effectively, we introduce a deepwalk strategy into GCNs to efficiently explore the global graph information. This strategy can complement the local neighborhood information of a graph, resulting in the more robust representation for the graph *** fusion of the local neighboring and global structured information of a graph can further facilitate deep feature learning at the output layer of GCNs for node classification. Experimental results show that the proposed model has achieved state-of-the-art results on three benchmark datasets including Cora, Citeseer,and Pubmed citation networks.

关键词： graph convolutional networks global information fusion node classification

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Average Consensus with Improved Accuracy-Privacy Trade-off

arXiv

引用

arXiv 2023年

作者： Wang, Lei Liu, Weijia Guo, Fanghong Qiao, Zixin Wu, Zhengguang College of Control Science and Engineering Zhejiang University Hangzhou China Department of Automation Zhejiang University of Technology Hangzhou China Shanghai Institute of Computing Technology Shanghai China

This paper studies the average consensus problem with differential privacy of initial states, for which it is widely recognized that there is a trade-off between the mean-square computation accuracy and privacy level. Considering the trade-off gap between the average consensus algorithm and the centralized averaging approach with differential privacy, we propose a distributed shuffling mechanism based on the Paillier cryptosystem to generate correlated zero-sum randomness. By randomizing each local privacy-sensitive initial state with an i.i.d. Gaussian noise and the output of the mechanism using Gaussian noises, it is shown that the resulting average consensus algorithm can eliminate the gap in the sense that the accuracy-privacy trade-off of the centralized averaging approach with differential privacy can be almost recovered by appropriately designing the variances of the added noises. We also extend such a design framework with Gaussian noises to the one using Laplace noises, and show that the improved privacy-accuracy trade-off is preserved. © 2023, CC BY-NC-SA.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Technical Framework for Selection of Autonomous UAV Navigation Technologies and Sensors

引用

Computers, Materials & Continua 2021年第8期68卷 2771-2790页

作者： Izzat Al-Darraji Morched Derbali Houssem Jerbi Fazal Qudus Khan Sadeeq Jan Dimitris Piromalis Georgios Tsaramirsis Department of Automated Manufacturing University of BaghdadBaghdadIraq Department of Mechanical Engineering University of KirkukIraq Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Industrial Engineering College of EngineeringUniversity of Ha’ilHail1234Saudi Arabia Department of Computer Science&IT University of Engineering&Technology PeshawarPakistan Department of Automation University of West AtticaAthensGreece Abu Dhabi Women’s College Higher Colleges of TechnologyAbu DhabiUAE

The autonomous navigation of an Unmanned Aerial Vehicle(UAV)relies heavily on the navigation *** UAV’s level of autonomy depends upon the various navigation systems,such as state measurement,mapping,and obstacle *** the correct components is a critical part of the design ***,this can be a particularly difficult task,especially for novices as there are several technologies and components available on the market,each with their own individual advantages and *** example,satellite-based navigation components should be avoided when designing indoor *** them in the design brings no added value to the final product and will simply lead to increased cost and power *** issue is the number of vendors on the market,each trying to sell their hardware solutions which often incorporate similar *** aim of this paper is to serve as a guide,proposing various methods to support the selection of fit-for-purpose technologies and components whilst avoiding system layout *** paper presents a study of the various navigation technologies and supports engineers in the selection of specific hardware solutions based on given *** selection methods are based on easy-to-follow flow charts.A comparison of the various hardware components specifications is also included as part of this work.

关键词： UAV navigation sensors selection UAV navigation autonomous navigation UAV development navigation sensors study navigation systems mapping systems obstacle-avoidance systems

来源：评论

学校读者我要写书评

暂无评论

BiRP: Learning Robot Generalized Bimanual Coordination Using Relative Parameterization Method on Human Demonstration

BiRP: Learning Robot Generalized Bimanual Coordination Using...

引用

IEEE Conference on Decision and Control

作者： Junjia Liu Hengyi Sim Chenzui Li Kay Chen Tan Fei Chen Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong SAR Department of Computing The Hong Kong Polytechnic University Hong Kong SAR

Human bimanual manipulation can perform more complex tasks than a simple combination of two single arms, which is credited to the spatio-temporal coordination between the arms. However, the description of bimanual coordination is still an open topic in robotics. This makes it difficult to give an explainable coordination paradigm, let alone applied to robotics. In this work, we divide the main bimanual tasks in human daily activities into two types: leader-follower and synergistic coordination. Then we propose a relative parameterization method to learn these types of coordination from human demonstration. It represents coordination as Gaussian mixture models from bimanual demonstration to describe the change in the importance of coordination throughout the motions by probability. The learned coordinated representation can be generalized to new task parameters while ensuring spatio-temporal coordination. We demonstrate the method using synthetic motions and human demonstration data and deploy it to a humanoid robot to perform a generalized bimanual coordination motion. We believe that this easy-to-use bimanual learning from demonstration (LfD) method has the potential to be used as a data augmentation plugin for robot large manipulation model training. The corresponding codes are open-sourced in https://***/Skylark0924/Rofunc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preserving Location Privacy of IoT Devices in Heterogeneous Edge computing Architecture Through Deniability-Based Authentication

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Ali, Ikram Li, Jianqiang Chen, Jie Chen, Yong Ullah, Shamsher Wakeel, Abdul Shenzhen University National Engineering Laboratory of Big Data System Computing Technology Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China National University of Sciences and Technology Military College of Signals Department of Electrical Engineering Islamabad Pakistan

Edge computing moves cloud services closer to consumer Internet of Things (IoT) devices, reducing latency and bandwidth usage. This setup enables faster responses but also introduces new security challenges, particularly concerning location privacy when sender and receiver use different security techniques. The authentication process in such architectures can expose the location of IoT devices. To address this issue, researchers have proposed various privacy-preserving schemes. However, these are computationally heavy for IoT devices. To tackle this issue, we propose two novel heterogeneous deniable authentication schemes: HDA-IoT-I and HDA-IoT-II. These schemes use public-key infrastructure and identity-based cryptography to protect the location privacy of IoT devices in heterogeneous edge computing environments. Our schemes enable the designated edge device to verify the source of a message without being able to prove its origin to a third party, thus preserving privacy. Additionally, they incorporate a batch verification method, which speeds up the verification of multiple deniable authenticators. The proposed schemes are formally proven secure in the random oracle model based on the hardness assumption of elliptic curve inverse computational Diffie-Hellman problem. The performance evaluation demonstrate that our schemes significantly enhance computational and communication efficiency, making them suitable for IoT devices. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decoding Model for BCI Human-Machine Interaction 42

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decodi...

引用

42nd Chinese Control Conference, CCC 2023

作者： Yan, Weidong Xu, Zhaoliang Li, Yang Beihang University The Department of Automation Science and Electrical Engineering Beijing100191 China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Advanced Institute of Information Technology Peking University Hangzhou310000 China

ISBN: (纸本)9789887581543

In this study, a multi-degree-of-freedom (Multi-DOF) robot (MDR) system based on a LightGBM-driven electroencephalogram (EEG) decoding model is designed and developed to assist subjects with hand motor dysfunction in their daily activities and neurorehabilitation. The system mainly consists of a motor imagery electroencephalogram (MI-EEG) evoking layer, an intention decoding layer, and an interaction executive layer. The MI-EEG evoking layer initially displays a virtual reality (VR) motion imagination scenario, instructing the subjects to imagine a real hand gripping movement, simultaneously collecting the electrical EEG signals and preprocessing the EEG signals. Secondly, in the intention decoding layer, a network combining temporal-spectral feature fusion and LightGBM (TSFF-LightGBM) for MI-BCI classification is used to more effectively boost brain decoding accuracy and decrease decoding time. Finally, in the interaction executive layer, the Multi-DOF wearable robot is developed to offer hand grasp motion kinesthetic feedback and visual feedback synced with MI. The following are the key benefits of the proposed MDR system: (1) We propose a new lightweight network structure more suitable for brain computer interface (BCI) interaction systems, achieving more accurate decoding and shorter identification time in different data sets, which helps to improve the practicability of the system and promote the practical clinical application of BCI rehabilitation technology. (2) We integrate BCI, VR, a wearable Multi-DOF robot, motion kinesthetic feedback, and visual feedback to improve human-machine interaction. Compared to the most recent investigations, the average accuracy of the MDR system on the publicly accessible datasets BCI IV 2a and HGD reached 75.89% and 93.53%, respectively. © 2023 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

A Multi-Head Convolution Network with Attention Consistency for Facial Expression Recognition 42

A Multi-Head Convolution Network with Attention Consistency ...

引用

42nd Chinese Control Conference, CCC 2023

作者： Liu, Wenkang Sun, Mingyi Li, Yang Beihang University The Department of Automation Science and Electrical Engineering Beijing100191 China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Peking University Advanced Institute of Information Technology Hangzhou310000 China

ISBN: (纸本)9789887581543

In recent years, the demand for facial expression recognition applications has increased rapidly, and its research has received extensive attention from researchers. However, the current recognition methods based on deep learning ignore the idea of multiple head attention and semantic consistency, resulting in the model only paying attention to the local area of the feature map. In addition, the model's inconsistent attention to the images before and after the flip, resulting the poor robustness, poor interpretation, and other shortcomings in the model. To address the above problems, we propose an Affinity Separation Loss (ASLoss), which improves the separability of samples through clustering. Moreover, a Separate Multi-head Attention block (SMA), and a Zonal Loss (ZLoss) are also designed to decentralize the model's attention. Experimental results demonstrate that our proposed MACNet method achieves competitive recognition performance on two public datasets RAF-DB and FERPlus. © 2023 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Exploring Innovations in Autonomous Robotics and Mechatronics: Application in Manufacturing and Healthcare

Exploring Innovations in Autonomous Robotics and Mechatronic...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： T.Grace Shalini L. Ganeshabu Priyanka Chemudugunta Nagendar Yamsani Ch.Ashok Kumar A. Athiraja Department of Computational Intelligence School of Computing SRM Institute of Science and Technology (SRMIST)Kattankulathur Chengalpattu Tamil Nadu India Department of Robotics and Automation Rajalakshmi Engineering College Rajalakshmi Nagar Thandalam Mevalurkuppam Chennai Tamil Nadu India Department of Robotics and Automation Karpaga Vinayaga College of Engineering and Technology Chengalpattu Tamil Nadu India Department of School of Computer Science and Artificial Engineering SR University Warangal India Department of Mechanical Engineering Malla Reddy Engineering College Main Campus Maisammaguda Hyderabad Telangana India Department of CSE (AIML) Malla Reddy College of Engineering Secunderabad Telangana India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

Autonomous robotics and mechatronics have drastically changed the manufacturing and healthcare sectors by increasing productivity, precision, and flexibility. This work addresses the pressing need for new methods to advance these sectors by merging intelligent algorithms with autonomous systems. A hybrid strategy was employed, combining Deep Reinforcement Learning (DRL) and Adaptive Control Systems (ACS), to develop and optimize robotic operations. Extensive studies were conducted to assess the success of this strategy, which demonstrated a 25% reduction in operating expenses and a 30% increase in production efficiency in manufacturing settings. The method produced a precision rate of about 99% in the healthcare industry, which is significantly better than the 93% average of current systems. It also reduced patient recovery times by an estimated 20%. These results highlight the improved performance and promise of ACS with DRL combination in autonomous robotics, which may have revolutionary implications for the manufacturing and healthcare industries. The success, highlighted by economic and medical benefits, demonstrates the efficacy of our methodology and provides a strong platform for future developments in autonomous robotics and mechatronics.

关键词： Industries Technological innovation Mechatronics Service robots Scalability Medical services Manufacturing Adaptive control Tuning Testing

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：