检索结果-内蒙古大学图书馆

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Xiangdong Sun Xulong Guo Yin Li Yongliang Zhang Yingsong Li School of Electronic Information Engineering Inner Mongolia University Hohhot China Inner Mongolia Branch of National Computer Network Emergency Response Technical Team/Coordination Center of China Inner Mongolia University Hohhot China Peng Cheng Laboratory Shenzhen China School of Transportation Institute Inner Mongolia University Hohhot China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China

ISBN: (数字)9798350384437

ISBN: (纸本)9798350384444

A low-profile, high-gain, wideband circularly polarized folded transmitarray antenna (CPFTA) is proposed, and a polarization-selective linear-to-circular polarization (LP-CP) conversion element is introduced. The CPFTA consists of a linearly polarized (LP) magnetoelectric dipole antenna and a circularly polarized (CP) helical patch antenna. The CPFTA demonstrates excellent performance with a 3dB gain bandwidth of 29.5% and a 3dB axial ratio (AR) bandwidth of 40.9%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-Organizing Coverage Method of Swarm Robots Based on Dynamic Virtual Force

SSRN

引用

SSRN 2024年

作者： Wang, Qiuzhen Zheng, Yue Zou, Juan Liu, Yuan Jianquan, Ouyang Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Computer Science School of Cyberspace Science of Xiangtan University Hunan Province Xiangtan China Faculty of School of Computer Science School of Cyberspace Science of Xiangtan University Xiangtan411105 China

Swarm robots often cover designated areas to complete specific tasks, such as forest firefighting or ocean oil spill cleaning. The robot has the ability for local perception and limitedcommunication with surrounding robots, then it is difficult to cope with coverage tasks indynamic environments. This paper proposes a self-organization algorithm for swarm robotsbased on Dynamic Virtual Force (DVF) to cover the dynamic area. One robot in the swarmcan locally perceive the surrounding robots and dynamically select some adjacent robots togenerate virtual repulsion to control its own movement. The swarm robot can be deployed quicklyand uniformly in unknown areas, while being able to adapt itself to changes in dynamic ***, it can adaptively cover parts of an area with different densities, which are dividedaccording to the needs of the area, and different densities require different numbers of robots tobe assigned. We design several groups of simulation experiments, and the results show that thealgorithm achieves good coverage performance and verifies the effectiveness and superiority ofthe method based on DVF. © 2024, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

LDG: Lightweight Deformable 3D Gaussians for Single-View Dynamic Scene Reconstruction

LDG: Lightweight Deformable 3D Gaussians for Single-View Dyn...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Youhong Peng Weixing Xie Jinwen Li Shaoqi Wu Zefeng Wang Bingbing Hu Junfeng Yao Center for Digital Media Computing School of Film School of Informatics Xiamen University China National Institute for Data Science in Health and Medicine Xiamen University China Ministry of Culture and Tourism Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent deformable 3D Gaussians methods achieve high-quality reconstruction and real-time rendering. However, they require multi-view information and are not applicable to single-view dynamic scenes captured from mobile phones. Additionally, the high-dimensional hidden layer of deformation MLP and the excessive number of Gaussian primitives and attributes impose significant storage pressure, greatly limiting their practical application. To address the issues, we propose a novel Lightweight Deformable 3D Gaussians teacher-student framework. Specifically, we initialize Gaussian primitives with an initialization strategy designed for single-view scenes, and then optimize the teacher model using color and depth information. For the trained teacher model, we distill deformation MLP, prune Gaussian primitives and Gaussian attributes, and finally obtain a student model with low storage and high efficiency. Public benchmark experiments demonstrate the effectiveness of our framework, showing a compression rate exceeding 4× while maintaining satisfactory rendering quality. Project page: https://***/ldg/.

关键词： Deformable models Training Three-dimensional displays Deformation Memory management Color Rendering (computer graphics) Real-time systems Mobile handsets Speech processing

来源：评论

学校读者我要写书评

暂无评论

Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data

arXiv

引用

arXiv 2024年

作者： Chen, Yin Li, Jia Zhang, Yu Hu, Zhenzhen Shan, Shiguang Wang, Meng Hong, Richang School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot. This temporal analysis provides richer information and promises greater recognition capability. However, current DFER methods often exhibit unsatisfied performance largely due to fewer training samples compared to SFER. Given the inherent correlation between static and dynamic expressions, we hypothesize that leveraging the abundant SFER data can enhance DFER. To this end, we propose Static-for-Dynamic (S4D), a unified dual-modal learning framework that integrates SFER data as a complementary resource for DFER. Specifically, S4D employs dual-modal self-supervised pre-training on facial images and videos using a shared Vision Transformer (ViT) encoder-decoder architecture, yielding improved spatiotemporal representations. The pre-trained encoder is then fine-tuned on static and dynamic expression datasets in a multi-task learning setup to facilitate emotional information interaction. Unfortunately, vanilla multitask learning in our study results in negative transfer. To address this, we propose an innovative Mixture of Adapter Experts (MoAE) module that facilitates task-specific knowledge acquisition while effectively extracting shared knowledge from both static and dynamic expression data. Extensive experiments demonstrate that S4D achieves a deeper understanding of DFER, setting new state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65%, 58.44%, and 76.68%, respectively. Additionally, a systematic correlation analysis between SFER and DFER tasks is presented, which further elucidates the potential benefits of leveraging SFER. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Combining State Detection with Knowledge Transfer for Constrained Multi-objective Optimization

Combining State Detection with Knowledge Transfer for Constr...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Jinhua Zheng Kaixi Yang Juan Zou Shengxiang Yang Key Laboratory of Intelligent Computing and Information Processing Xiangtan University China School of Computer Science and Informatics De Montfort University U.K

The main challenge in studying constrained multi-objective optimization problems (CMOPs) is reasonably balancing convergence, diversity, and feasibility. One of the most successful solutions to this challenge is the co-evolutionary frame-work, an algorithm in which multiple populations cooperate and complement each other, with different but interdependent populations addressing different but related problems. However, the effectiveness of existing algorithms for information exchange between various populations is not apparent. This paper proposes a new algorithm named SDKT using population state detection and knowledge transfer. The method has dual stages (i.e., knowledge acquisition and knowledge reception) and dual populations. Specifically, by restarting the strategy, these two populations (i.e., mainPop and auxPop) first explore more feasible regions with and without constraints. Then, in the knowledge receiving stage, ma i nPop and auxPop provide effective information to promote each other's approach to constrained PF (CPF) and unconstrained PF (UPF), respectively. Extensive experiments on three well-known test suites and three real-world problem studies fully demonstrate that SDKT is more competitive than five state-of-the-art constrained multi-objective evolutionary algorithms.

关键词： Knowledge acquisition Sociology Diversity reception Evolutionary computation Statistics Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

An object detection network for locating and recognizing cluttered garbage 23

An object detection network for locating and recognizing clu...

引用

Proceedings of the 2023 11th International Conference on Information Technology: IoT and Smart City

作者： Guanjun Ji Shuxin Liu SHANGHAI DIANJI UNIVERSITY SCHOOL OF ELECTRICAL ENGINEERINGShangHai?China China SHANGHAI DIANJI UNIVERSITY SCHOOL OF ELECTRICAL ENGINEERINGShangHai China and The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions?Wuyi University??Fujian?China China

ISBN: (纸本)9798400709043

The research on garbage classification have made remarkable achievements in the latest work. However, due to the complexity of the location elements of the garbage background, there are still many difficulties in the accuracy of garbage location detection. For complex backgrounds, it is easy to cause false detection and missed detection. In response to the above problems, we explored the improved YOLOv5n network , added the ContextAggregation module and replaced GIOU with Focal-EIOU, and replaced C3 with C3SAC to improve feature extraction for contextual information. The improved algorithm has been proved by experiments to increase mAP by 2.3%. The accuracy rate of Plastic bowl, Power banks, Cardboard boxes, Tea leaves, Plastic hangers and so on has reached more than 80%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compact Broadband Absorptive Bandstop Filter Based on Microstrip 2

Compact Broadband Absorptive Bandstop Filter Based on Micros...

引用

2020 2nd International Conference on Artificial Intelligence Technologies and Application, ICAITA 2020

作者： Lu, Qi Wu, Xianliang Wang, Chao Key Lab of Intelligent Computing and Signal Processing Ministry of Education AnHui University AnHui University Heifei AnHui230000 China

A compact broadband absorptive band rejection filter (ABSF) based on microstrip line is proposed. The filter consists of a pair of coupled wires and is loaded with a resistor. The coupling line of the filter has an open stub. The transmission zero point can be adjusted by adjusting the width of the coupling line. The center frequency can be adjusted by changing the length of the intermediate coupling line. Absorption performance can be achieved through loaded resistors. In this way, the signal not input in the filter will be dissipated in the filter and will not be reflected. When F0=3.8 GHz, 26% of the 20 dB bandwidth covers 3.15 GHz-4.2 GHz, the rejection depth of the stopband is less than-40 dB, and the in-band absorption is less than-10 dB. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Notch filters

来源：评论

学校读者我要写书评

暂无评论

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning 39

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Hu, Gangqiang Lu, Jianfeng Han, Jianmin Cao, Shuqin Liu, Jing Fu, Hao School of Computer Science and Technology Zhejiang Normal University China School of Computer Science and Technology Wuhan University of Science and Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China

ISBN: (纸本)157735897X

Due to the sensitivity of data, Federated Learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized FL, clients’ communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges inherent in real-world scenarios. To tackle this issue, we propose a TRust-Aware clIent scheduLing mechanism called TRAIL, which assesses client states and contributions, enhancing model training efficiency through selective client participation. We focus on a semi-decentralized FL framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we propose an adaptive hidden semi-Markov model to estimate clients’ communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7% in test accuracy and a reduction of 15.3% in training loss. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Weighted Flat Lattice Transformer-based Knowledge Extraction Architecture for Chinese Named Entity Recognition

A Weighted Flat Lattice Transformer-based Knowledge Extracti...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hengwei Zhang Yuejia Wu Jian-Tao Zhou Inner Mongolia University College of Computer Science Hohhot China Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Named Entity Recognition (NER) is one of the contents of Knowledge Extraction (KE) that transforms data into knowledge representation. However, Chinese NER faces the problem of lacking clear word boundaries that limit the effectiveness of the KE. Although the flat lattice Transformer (FLAT) framework, which converts lattice structure into a flat structure including a set of spans, can effectively improve this problem and obtain advanced results, there still exist the problems of insensitivity to entity importance weights and insufficient feature learning. This paper proposes a weighted flat lattice Transformer architecture for Chinese NER, namely WFLAT. The WFLAT first adds a weight matrix into self-attention calculation, which can obtain finer-grained partitioning of entities to improve experimental performance, and then adopts a multi-layer Transformer encoder with each layer using a multi-head self-attention mechanism. Extensive experimental results on benchmarks demonstrate that our proposed KE model can obtain state-of-the-art performance for the Chinese NER task.

关键词： Representation learning Computational modeling Memory management Lattices Named entity recognition Transforms Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Stfi: Structure-Aware and Time-Frequency Domain Interaction Network for Deformable Medical Image Registration

SSRN

引用

SSRN 2025年

作者： Hu, Rui Wang, Nian Zhang, Yuxin Li, Teng Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China Advanced Imaging Research Center University of Texas Southwestern Medical Center 5323 Harry Hines Blvd Dallas75390 United States School of Cyber Science and Engineering Southeast University No.2 Southeast University Road Nanjing211189 China

Deformable image registration is crucial in medical image analysis. Recently, unsupervised methods using intensity matching have shown promising results without labeled data. However, these methods still face challenges: (1) They often encounter local optima when handling anatomical structures with significant variations in intensity distribution;(2) Time domain convolution in decoders leads to loss of high-frequency fine features, limiting the effectiveness of generating fine deformation vector fields. To address these issues, we propose a novel structure-aware and time-frequency domain interaction (STFI) network. STFI integrates a structure-aware frequency domain loss and a time-frequency domain interaction module. The former leverages principal structural information from the weighted phase spectrum to guide the registration process, thereby reducing the risk of local optima. The latter processes and amalgamates information from both the time and frequency domains, effectively preserving high-frequency details. The efficacy and adaptability of our approach have been demonstrated on two types of data, offering a new perspective on exploiting time-frequency domain information for medical image registration. © 2025, The Authors. All rights reserved.

关键词： Image registration

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：