检索结果-内蒙古大学图书馆

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

来源：评论

学校读者我要写书评

暂无评论

Time-multiplexing Method Using Dual Ferroelectric Liquid Crystal Shutters for Light Field 3D Display

Time-multiplexing Method Using Dual Ferroelectric Liquid Cry...

引用

International Conference on Display technology, 2024

作者： Sun, Zhi-Bo Yuan, Zheng-Nan Huo, Yi-Peng Dong, Shou-Cheng Cheung, Alex Vashchenko, Valerii Vashchenko, Olena Srivastava, Abhishek Kwok, Hoi-Sing State Key Laboratory of Advanced Displays and Optoelectronics Technologies Center for Display research Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Road Kowloon Hong Kong

In light field displays, the resolution loss is a serious problem, leading to insufficient image depth, display size, and resolution. Here, we achieve a high refresh time multiplexing method that can effectively increase the display resolution by up to 32 times. Ferroelectric Liquid Crystal (FLC) with a fast response at 2 kHz and an optimized charge compensation method is proposed in this *** is very promising for light field 3D displays in the future. © 2024 John Wiley and Sons Inc. All rights reserved.

关键词： Time division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition 24

Generating Action-conditioned Prompts for Open-vocabulary Vi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Jia, Chengyou Luo, Minnan Chang, Xiaojun Dang, Zhuohang Han, Mingfei Wang, Mengmeng Dai, Guang Dang, Sizhe Wang, Jingdong School of Computer Science and Technology MOEKLINNS Lab Xi'an Jiaotong University Shaanxi Xi'an China University of Science and Technology of China Anhui Hefei China School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China ReLER Lab AAII University of Technology Sydney SydneyNSW Australia Zhejiang University of Technology College of Computer Science and Technology China SGIT AI Lab State Grid Corporation of China Beijing China Baidu Inc Beijing China United Arab Emirates Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China SGIT AI Lab State Grid Corporation of China China School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798400706868

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability. © 2024 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

The Methodology of Mask Detection Employing the YOLOv7 Framework

The Methodology of Mask Detection Employing the YOLOv7 Frame...

引用

Neural Networks, Information and Communication Engineering (NNICE), International Conference on

作者： Fucheng Zhang Pinfang Tian School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Key Laboratory of Intelligent Information Processing and Real-TimeIndustrial Systems Wuhan China

In the current field of object detection, the YOLOv7 model demonstrates significant advantages in terms of both detection speed and accuracy. However, the model shows deficiencies in focussing on key information, and its loss function's sensitivity to bounding boxes results in suboptimal performance in densely populated environments and small target detection scenarios. To address these issues, this study proposes a mask target detection method based on YOLOv7. By integrating a channel attention mechanism into the YOLOv7 model, this method enhances the model's focus on important information in images, effectively reducing interference from background factors. Additionally, the method incorporates Normalized Wasserstein Distance (NWD) into the loss function to optimize the model's evaluation of small target detection. Experimental verification shows that the improved model maintains its original detection speed while increasing the overall accuracy to 92.1%, a 2.9% improvement over the original YOLOv7 model. It achieves a 3.3% increase in the mAP.5 metric. This indicates that the optimised YOLOv7 model has superior detection capabilities, allowing it to perform mask-wearing detection tasks more rapidly and accurately in natural environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Domain generalization using pseudo triplet network learning for vibration signal-based fault diagnosis 15

Domain generalization using pseudo triplet network learning ...

引用

15th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024

作者： Liu, Jianing Cao, Hongrui Dhupia, Jaspreet Singh Choudhury, Madhurjya Dev Xi'an Jiaotong University State Key Laboratory for Manufacturing Systems Engineering Xi'an China University of Auckland Department of Mechanical and Mechatronics Engineering Auckland New Zealand Birla Institute of Technology and Science Department of Mechanical Engineering Pilani India

ISBN: (纸本)9798350354010

Domain generalization (DG) based intelligent fault diagnosis has developed rapidly in recent years owing to the need for applying trained neural networks to unseen domains. However, models trained using DG often suffer from performance degradation when in presence of nonstationary working conditions. To address this challenge, this work proposes a DG based intelligent fault diagnosis approach based on a vibration response mechanism guided pseudo triplet network, which extracts suitable features that correlate well with the health conditions. Firstly, the proposed approach estimates the cyclic spectral correlation maps of vibration signals to provide vibration response mechanism of different health conditions. Then, a pseudo triplet neural network is designed to calculate the distance between the representations of the prior input, the negative input from the representation of the main input. The prior input is the specific part of the cyclic spectral correlation map with the selected carrier band and it guides the network focus on the fault-related features. Finally, the proposed approach is evaluated through experiments conducted on data collected from nonstationary working conditions. © 2024 IEEE.

关键词： domain generalization nonstationary working conditions pseudo triplet network vibration response mechanism

来源：评论

学校读者我要写书评

暂无评论

RankDNN: Learning to Rank for Few-Shot Learning 37

RankDNN: Learning to Rank for Few-Shot Learning

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Guo, Qianyu Haotong, Gong Wei, Xujun Fu, Yanwei Yu, Yizhou Zhang, Wenqiang Ge, Weifeng Nebula AI Group School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Academy for Engineering & Technology Fudan University Shanghai China Department of Computer Science The University of Hong Kong Hong Kong

ISBN: (纸本)9781577358800

This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification. In comparison to image classification, ranking relation classification is sample efficient and domain agnostic. Besides, it provides a new perspective on few-shot learning and is complementary to state-of-the-art methods. The core component of our deep neural network is a simple MLP, which takes as input an image triplet encoded as the difference between two vector-Kronecker products, and outputs a binary relevance ranking order. The proposed RankMLP can be built on top of any state-of-the-art feature extractors, and our entire deep neural network is called the ranking deep neural network, or RankDNN. Meanwhile, RankDNN can be flexibly fused with other post-processing methods. During the meta test, RankDNN ranks support images according to their similarity with the query samples, and each query sample is assigned the class label of its nearest neighbor. Experiments demonstrate that RankDNN can effectively improve the performance of its baselines based on a variety of backbones and it outperforms previous state-of-the-art algorithms on multiple few-shot learning benchmarks, including miniImageNet, tieredImageNet, Caltech-UCSD Birds, and CIFAR-FS. Furthermore, experiments on the cross-domain challenge demonstrate the superior transferability of *** code is available at: https://***/guoqianyu-alberta/RankDNN. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robotic Grinding Skills Learning Based on Geodesic Length Dynamic Motion Primitives

arXiv

引用

arXiv 2025年

作者： Ke, Shuai Zhao, Huan Li, Xiangfei Wei, Zhiao Yin, Yecan Ding, Han State Key Laboratory of Intelligent Manufacturing Equipment and Technology Department of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

Learning grinding skills from human craftsmen by imitation learning has emerged as a prominent research topic in the field of robotic machining. Given their robust trajectory generalization ability and resilience to various external disturbances and environmental changes, Dynamical Movement Primitives (DMPs) provide a promising skills learning solution for the robotic grinding. However, challenges arise when directly applying DMPs to grinding tasks, including low orientation accuracy, inaccurate synchronization of position, orientation, and force, and the inability to generalize surface trajectories. To address these issues, this paper proposes a robotic grinding skills learning method based on geodesic length DMPs (Geo-DMPs). First, a normalized two-dimensional weighted Gaussian kernel function and intrinsic mean clustering algorithm are proposed to extract surface geometric features from multiple demonstration trajectories. Then, an orientation manifold distance metric is introduced to exclude the time factor from the classical orientation DMPs, thereby constructing Geo-DMPs for the orientation learning to improve the orientation trajectory generation accuracy. On this basis, a synchronization encoding framework for position, orientation, and force skills is established, using a phase function related to geodesic length. This framework enables the generation of robotic grinding actions between any two points on the surface. Finally, experiments on robotic chamfer grinding and free-form surface grinding demonstrate that the proposed method exhibits high geometric accuracy and good generalization capabilities in encoding and generating grinding skills. This method holds significant implications for learning and promoting robotic grinding skills. To the best of our knowledge, this may be the first attempt to use DMPs to generate grinding skills for position, orientation, and force on model-free surfaces, thereby presenting a novel approach to robotic grinding skills

关键词： intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Advanced surface engineering of titanium materials for biomedical applications:From static modification to dynamic responsive regulation

引用

Bioactive Materials 2023年第9期27卷 15-57页

作者： Pinliang Jiang Yanmei Zhang Ren Hu Bin Shi Lihai Zhang Qiaoling Huang Yun Yang Peifu Tang Changjian Lin South China Advanced Institute for Soft Matter Science and Technology School of Emergent Soft MatterGuangdong Provincial Key Laboratory of Functional and Intelligent Hybrid Materials and DevicesSouth China University of TechnologyGuangzhou510640China State Key Lab of Physical Chemistry of Solid Surfaces Department of ChemistryCollege of Chemistry and Chemical EngineeringXiamen UniversityXiamen361005China Department of Orthopaedics General Hospital of Chinese PLABeijing100853China Research Institute for Biomimetics and Soft Matter Fujian Provincial Key Laboratory for Soft Functional Materials ResearchCollege of Physical Science and TechnologyXiamen UniversityXiamen361005China

Titanium(Ti)and its alloys have been widely used as orthopedic implants,because of their favorable mechanical properties,corrosion resistance and *** their significant success in various clinical applications,the probability of failure,degradation and revision is undesirably high,especially for the patients with low bone density,insufficient quantity of bone or osteoporosis,which renders the studies on surface modification of Ti still active to further improve clinical *** is discerned that surface physicochemical properties directly influence and even control the dynamic interaction that subsequently determines the success or rejection of orthopedic ***,it is crucial to endow bulk materials with specific surface properties of high bioactivity that can be performed by surface modification to realize the *** article first reviews surface characteristics of Ti materials and various conventional surface modification techniques involving mechanical,physical and chemical treatments based on the formation mechanism of the modified *** conventional methods are able to improve bioactivity of Ti implants,but the surfaces with static state cannot respond to the dynamic biological cascades from the living cells and ***,beyond traditional static design,dynamic responsive avenues are then *** dynamic stimuli sources for surface functionalization can originate from environmental triggers or physiological *** short,this review surveys recent developments in the surface engineering of Ti materials,with a specific emphasis on advances in static to dynamic functionality,which provides perspectives for improving bioactivity and biocompatibility of Ti implants.

关键词： Titanium materials Orthopedic implants Bioactivity Static modification Dynamic responsive regulation

来源：评论

学校读者我要写书评

暂无评论

Fast calculations of vector electromagnetics in 3d periodic structures based on multiple scattering theory and broadband green’s function

引用

Progress in Electromagnetics Research 2024年 179卷 19-36页

作者： Tsang, Leung Liao, Tien-Hao Tan, Shurun Xu, Xiaolan Bai, Xuyang Gao, Ruoxing Radiation Laboratory Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States National Taipei University of Technology Taipei10608 Taiwan Zhejiang University/University of Illinois Urbana-Champaign Institute Zhejiang University Zhejiang Haining314400 China State Key Laboratory of Modern Optical Instrumentation College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL61801 United States Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States

We have developed a fast method of using Multiple Scattering Theory-Broadband Green’s Function (BBGF-MST) for band field calculations. In this paper, we successfully extended the method to the vector electromagnetic case of 3D periodic structures. In the MST-BBGF approach, the broadband transformation to vector spherical waves for 3D is derived using the Broadband Green’s function. The band eigenvalue problem is expressed in terms of the single scatterer T matrix which is independent of the periodic lattice nor the Bloch vector. For the first five bands, the dimension of the KKR eigen equation is merely 6, as 6 vector spherical waves are utilized for the scattered waves. We make extensive comparisons of the results with the commercial software COMSOL in both accuracy and computation efficiency. The CPU requirement on a standard laptop for the MST-BBGF method is merely 0.309 seconds for the first 5 bands. The MST-BBGF method is accurate and is at least two orders of magnitude faster than commercial software COMSOL. In the band field calculations, we employ the approach of extended coefficient to use the low order eigenvector of 6 to extend to 240 vector spherical wave coefficients without the need of recalculating the eigenvalue nor the eigenvector of the KKR equation. The extended coefficients approach gives accurate band field solutions for the entire (0, 0, 0) cell. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Further study on indecomposable cryptographic functions

引用

Frontiers of computer science 2023年第2期17卷 237-239页

作者： Zhongqiu WANG Shixiong XIA Fengrong ZHANG Mine Digitization Engineering Research Center of Ministry of Education China University of Mining and TechnologyXuzhou 221116China State Key Laboratory of Cryptology P.0.Box 5159Beijing 100878China Research Center of Innovation on Intelligent Prevention of Disaster and Emergency Rescure China University of Mining and TechnologyXuzhou 221116China School of Computer Science and Technology China University of Mining and TechnologyXuzhou 221116China

1 Introduction Boolean functions have important applications in stream ciphers and block *** the last decades,the constructions of cryptographic Boolean functions have paid a lot of attention[1,2].Direct sum is a well-known secondary construction of cryptographic functions[3].By using the direct sum,a lot of functions with high nonlinearities can be obtained[4,5].However,the direct sum of two functions are decomposable functions,which have numerous null secondorder derivatives(which represents a potential weakness with respect to the higher order differential attack)[6].(In)decomposable functions were also studied in[7]by Zheng and Zhang under the name(non)separable *** provided some sufficient conditions that the functions are indecomposable[7].

关键词： functions functions indecomposable

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：