检索结果-内蒙古大学图书馆

Action quality assessment via moment aware network

Evolving Systems 2025年第2期16卷 1-10页

作者： Han, Jifeng Zhang, Yanduo Lu, Tao Wang, Jiaming Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

Recent action quality assessment methods attempt to decompose the entire video into sub-actions of the same level, which still suffers from information redundancy and lacks certain interpretability. Through studying and analysing the evaluation rules of relevant sports events, we assume that certain critical moments in the actions will significantly impact the assessment of the entire action, if the weight of these critical moments in the evaluation process can be increased, then the results can be more accurate and more persuasive. To validate this idea, we propose a moment-aware approach for action quality assessment, a novel moment-aware module is used to explore the key moments in action globally and locally to obtain more reliable evaluation results. Extensive experiments have shown that our module captures key moments that are close to the focus of human referees, and our method has also achieved favorable results on multiple public AQA benchmarks, the Spearman’s rank correlation reached 0.9360 on FineDiving dataset and 0.8797 on AQA-7 dataset. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

An Efficient Instance Segmentation Based on Layer Aggregation and Lightweight Convolution

引用

Computers, Materials & Continua 2025年第4期83卷 1041-1055页

作者： Hui Jin Shuaiqi Xu Chengyi Duan Ruixue He Ji Zhang College of Mechanical Engineering Chongqing University of TechnologyChongqing400054China Robot and Intelligent Manufacturing Technology Key Laboratory of Chongqing Education Commission of ChinaChongqing400054China

Instance segmentation is crucial in various domains,such as autonomous driving and ***,there is scope for improvement in the detection speed of instance-segmentation algorithms for edge ***,it is essential to enhance detection speed while maintaining high *** this study,we propose you only look once-layer fusion(YOLO-LF),a lightweight instance segmentation method specifically designed to optimize the speed of instance segmentation for autonomous driving *** on the You Only Look Once version 8 nano(YOLOv8n)framework,we introduce a lightweight convolutional module and design a lightweight layer aggrega-tion module called Reparameterization convolution and Partial convolution Efficient Layer Aggregation Networks(RPELAN).This module effectively reduces the impact of redundant information generated by traditional convolutional stacking on the network size and detection speed while enhancing the capability to process feature *** experimentally verified that our generalized one-stage detection network lightweight method based on Grouped Spatial Convolution(GSconv)enhances the detection speed while maintaining accuracy across various state-of-the-art(SOTA)*** experiments conducted on the publicly available Cityscapes dataset demonstrated that YOLO-LF maintained the same accuracy as yolov8n(mAP@0.537.9%),the model volume decreased by 14.3%from 3.259 to=2.804 M,and the Frames Per Second(FPS)increased by 14.48%from 57.47 to 65.79 compared with YOLOv8n,thereby demonstrating its potential for real-time instance segmentation on edge devices.

关键词： Automatic driving convolution deep learning real-time instance segmentation

来源：评论

学校读者我要写书评

暂无评论

MST-Adapter: Multi-Scaled Spatio-Temporal Adapter for Parameter-Efficient Image-to-Video Transfer Learning

引用

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences 2025年第5期E108.A卷 736-745页

作者： Chang, Chenrui Lu, Tongwei Yao, Feng Hubei Key Laboratory of Intelligent Robot School of Computer Science and Engineering Wuhan Institute of Technology Wuhan430205 China

Large-scale image pre-training models have recently demonstrated strong representation capabilities in spatial information contexts. Prior works apply these models to video action recognition through fully fine-tuning, which is expensive and resource-intensive. To reduce computational costs, some studies have shifted their focus to efficient parameter fine-tuning methods. However, existing efficient fine-tuning methods lack exploration of multi-scale information in videos. In this work, the Multi-scale spatio-temporal Adapter (MST-Adapter) is proposed for parameter-efficient Image-to-Video transfer learning. By freezing the pretrained models and adding the lightweight adapters, we only need to update few parameters, which is highly efficient. In addition, extensive experiments on two video action recognition benchmarks show that our method can learn high-quality video spatio-temporal representations and achieve competitive or even better performance than prior works. Copyright © 2025 The Institute of Electronics, Information and Communication Engineers.

关键词： multi-scale spatio-temporal adapter parameter-efficient image-to-video transfer learning video action recognition video spatiotemporal representations

来源：评论

学校读者我要写书评

暂无评论

DSSNet: a transformer-based network for dense scene text detection and recognition in complex environments 5

DSSNet: a transformer-based network for dense scene text det...

引用

5th International Conference on Signal Processing and Computer Science, SPCS 2024

作者： Li, Jing Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

This paper presents a novel approach for dense scene text detection called DSSNet (Dense Script Spotter Network). The network leverages ResNet and FPN for feature extraction, employing multi-scale feature fusion and Transformer-based feature processing to enhance text recognition across varying sizes. The method generates text instance shapes using Bézier central curves and performs text recognition by integrating positional query information. Experimental results on the DSTD1500 and ICDAR2015 datasets demonstrate that DSSNet outperforms existing methods in terms of text localization accuracy, recognition accuracy, and annotation flexibility. © 2025 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Accelerated inference for thyroid nodule recognition in ultrasound imaging using FPGA

引用

Physical and Engineering Sciences in Medicine 2025年 1-9页

作者： Ma, Wei Wu, Xiaoxiao Zhang, Qing Li, Xiang Wu, Xinglong Wang, Jun School of Computer Science and Engineering Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan China

Thyroid cancer is the most prevalent malignant tumour in the endocrine system, with its incidence steadily rising in recent years. Current central processing units (CPUs) and graphics processing units (GPUs) face significant challenges in terms of processing speed, energy consumption, cost, and scalability in the identification of thyroid nodules, making them inadequate for the demands of future green, efficient, and accessible healthcare. To overcome these limitations, this study proposes an efficient quantized inference method using a field-programmable gate array (FPGA). We employ the YOLOv4-tiny neural network model, enhancing software performance with the K-means + + optimization algorithm and improving hardware performance through techniques such as 8-bit weight quantization, batch normalization, and convolutional layer fusion. The study is based on the ZYNQ7020 FPGA platform. Experimental results demonstrate an average accuracy of 81.44% on the Tn3k dataset and 81.20% on the internal test set from a Chinese tertiary hospital. The power consumption of the FPGA platform, CPU (Intel Core i5-10200 H), and GPU (NVIDIA RTX 4090) were 3.119 watts, 45 watts, and 68 watts, respectively, with energy efficiency ratios of 5.45, 0.31, and 5.56. This indicates that the FPGA’s energy efficiency is 17.6 times that of the CPU and 0.98 times that of the GPU. These results show that the FPGA not only significantly outperforms the CPU in speed but also consumes far less power than the GPU. Moreover, using mid-to-low-end FPGAs yields performance comparable to that of commercial-grade GPUs. This technology presents a novel solution for medical imaging diagnostics, with the potential to significantly enhance the speed, accuracy, and environmental sustainability of ultrasound image analysis, thereby supporting the future development of medical care. © Australasian College of Physical Scientists and Engineers in Medicine 2025.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Elastic wave propagation and attenuation characteristics of roof fracture source

引用

Geomechanics and Engineering 2025年第4期40卷 295-305页

作者： Zhang, Peng-Fei Zhao, Tong-Bin Gong, Xu-Fei Tan, Yan Guo, Chuan-Qing College of Energy and Mining Engineering Shandong University of Science and Technology Qingdao266590 China State Key Laboratory of Mining Disaster Prevention and Control Co-founded by Shandong Province and the Ministry of Science and Technology Shandong University of Science and Technology Qingdao266590 China Shandong Key Laboratory of Intelligent Prevention and Control of Dynamic Disaster in Deep Mines Shandong University of Science and Technology Qingdao266590 China Energy Group Co. Ltd. Jining No.2 Coal Mine Jining272012 China

Abstract. The propagation attenuation law of elastic waves generated by rock mass fractures in strata is of great significance in explaining engineering problems, such as rock bursts. In this study, a wave velocity model was established based on the actual stratum conditions of the Jining No.2 coal mine in China. The propagation process of different types of elastic waves is simulated using the elastic wave equation and finite difference method. The attenuation coefficients of various elastic wave parameters propagating at different positions were calculated. Based on the calculated results, an attenuation equation for the elastic wave energy is proposed. The results show that the propagation of S-waves and P-waves in strata is similar to each other, and wave pattern transformation occurs at the interface of the strata. The magmatic rocks played a role in channeling and reflecting elastic wave propagation, leading to the occurrence of low-energy aftershocks in the coal seams. The peak displacement, peak stress, and energy density of the elastic wave that propagated to the coal seam after the siltstone layer fracture of the roof of the 3down coal seam decreased to 28%, 25%, and 9% of the source, respectively. The attenuation of elastic wave energy is highly correlated with the propagation distance, and the attenuation equation can be represented as an exponential function. These results are of great significance for revealing the propagation attenuation process of elastic waves in the stratum. © 2025 Techno-Press, Ltd.

关键词： Exponential functions

来源：评论

学校读者我要写书评

暂无评论

Exploration and Prospects of Large Language Models with ReAct Integration in Maritime Risk Identification

Exploration and Prospects of Large Language Models with ReAc...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Chen, Chen Shu, Zhong-Cheng Guo, Lei Chen, Yu-Han School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9789819639601

Maritime risk identification technology is more and more important for ships sailing on the sea, and can ensure the safety of ships sailing on the sea. However, traditional risk identification methods rely on historical data and qualitative experience, which is difficult to deal with complex and changeable environment. Recently, advancements in artificial intelligence, particularly large language models, have introduced new solutions to these challenges. While these models excel in data processing and pattern recognition, their effective application within the maritime domain remains problematic. This paper presents the ReAct (Reasoning and Acting) model, which enhances the adaptability of large language models by simulating human reasoning and actions. This paper first reviews the traditional methods and existing problems of maritime risk identification, and then discusses the basic principle of ReAct model and its potential in risk identification. Finally, the study proposes the integration of ReAct with large language models, highlighting the advantages and future prospects of this approach. This research aims to provide new theoretical and technological support for maritime risk identification, ultimately contributing to improved risk management and accident prevention. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Narrowband directional chiral emission enabled by hyperbolic material α-MoO3

引用

Optics Express 2025年第8期33卷 16965-16975页

作者： Wu, Biyuan Huang, Xiqiao Liu, Haotuo Wu, Xiaohu School of Power and Energy Northwestern Polytechnical University Shaanxi Xi’an710072 China Thermal Science Research Center Shandong Institute of Advanced Technology Shandong Jinan250100 China Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology Harbin150080 China

Chiral emission plays a pivotal role in the design of advanced sensors and thermal detectors. However, the ability to control the chiral emission of far-field thermal radiation over a fixed narrow angular range is an important yet currently limited capability. In this paper, we investigate a lithography-free chiral thermal emitter based on the hyperbolic material α-phase molybdenum trioxide (α-MoO3). Numerical studies demonstrate that the proposed chiral emitter is highly sensitive to the incident angle, showing narrowband chiral emission exclusively in the range of incidence angles from 75° to 89° at a wavelength of 10 µm. The directional chiral emission arises from the extrinsic chirality resulting from the mutual orientation of the α-MoO3 film with in-plane anisotropy and the incident light. Furthermore, we elucidate the mechanism through polarization conversion and analyze the degree of polarization (DoP) of the thermal radiation. Our findings indicate that the DoP can reach 0.95, signifying efficient conversion of left-handed to right-handed circularly polarized light while maintaining perfect polarization at the resonant wavelength. Electric field distributions further validate the origin of directional chiral emission. This study not only advances the understanding of circularly polarized light manipulation but also promises significant applications in chiral sensing and thermal detection. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Heat radiation

来源：评论

学校读者我要写书评

暂无评论

Power Allocation Based on Federated Multiagent Deep Reinforcement Learning for NOMA Maritime Networks

引用

IEEE Internet of Things Journal 2025年第9期12卷 12869-12884页

作者： He, Jiayi Liu, Zhiyong Zhang, Yakai Jin, Zihao Zhang, Qinyu School of Information Science and Engineering Shandong Weihai264209 China Shandong Provincial Key Laboratory of Marine Electronic Information and Intelligent Unmanned Systems Key Laboratory of Cross-Domain Synergy and Comprehensive Support for Unmanned Marine Systems of the Ministry of Industry and Information Technology Shandong Weihai264209 China Communication Engineering Research Center Guangdong Shenzhen518055 China Peng Cheng Laboratory Shenzhen518055 China

The absence of established communication infrastructures at sea presents a significant hurdle for the development of the Internet of Things (IoT) in maritime environments. In this article, we propose a novel solution: a nonorthogonal multiple access (NOMA) maritime network employing power allocation facilitated by federated multiagent deep reinforcement learning (DRL). Conventional single-agent DRL algorithms encounter challenges, such as dimensionality explosion in real-world scenarios. We address this issue by extending these algorithms to incorporate multiple agents. Furthermore, to mitigate risks associated with centralized training, such as data leakage and network attacks, we adopt a federated learning (FL) framework for distributed training across multiple agents. By uploading only select parameters during training and keeping data locally, FL not only enhances algorithm convergence speed but also bolsters data privacy. Specifically, we introduce the federated multiagent deep Q-network (FLMADQN) algorithm tailored for power allocation in NOMA maritime networks. Our algorithm aims to maximize system throughput, optimize data transfer rates, and expedite convergence. Through extensive computer simulations, we validate the efficacy of our proposed approach. Results demonstrate that the FLMADQN algorithm significantly outperforms the traditional DRL algorithm, DQN, in NOMA maritime environments, improving average system throughput by 20.12%, peak system throughput by 45.10%, and system spectral efficiency by 48.33%. Moreover, FLMADQN exhibits a twofold increase in convergence speed compared to MADQN without FL and is 2.5 times faster than DQN. Our findings underscore the potential of federated multiagent DRL in advancing communication systems for maritime IoT applications. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robust interface and excellent as-built mechanical properties of Ti–6Al–4V fabricated through laser-aided additive manufacturing with powder and wire

引用

International Journal of Minerals,Metallurgy and Materials 2025年第1期32卷 154-168页

作者： Fei Weng Guijun Bi Youxiang Chew Shang Sui Chaolin Tan Zhenglin Du Jinlong Su Fern Lan Ng Key Laboratory for Liquid-Solid Structural Evolution and Processing of Materials Ministry of EducationShandong Engineering&Technology Research Center for Superhard MaterialSchool of Materials Science and EngineeringShandong UniversityJinan 250061China Institute of Intelligent Manufacturing Guangdong Academy of SciencesGuangzhou 510095China Singapore Institute of Manufacturing Technology 5 Cleantech Loop636732Singapore

The feasibility of manufacturing Ti-6Al-4V samples through a combination of laser-aided additive manufacturing with powder(LAAM_(p))and wire(LAAM_(w))was explored.A process study was first conducted to successfully circumvent defects in Ti-6Al-4V deposits for LAAM_(p) and LAAM_(w),*** the optimized process parameters,robust interfaces were achieved between powder/wire deposits and the forged substrate,as well as between powder and wire *** characterization results revealed the epitaxial prior β grains in the deposited Ti-6Al-4V,wherein the powder deposit was dominated by a finerα′microstructure and the wire deposit was characterized by lamellar α *** mechanisms of microstructure formation and correlation with mechanical behavior were analyzed and *** mechanical properties of the interfacial samples can meet the requirements of the relevant Aerospace Material Specifications(AMS 6932)even without post heat *** fracture occurred within the interfacial area,further suggesting the robust *** findings of this study highlighted the feasibility of combining LAAM_(p) and LAAM_(w) in the direct manufacturing of Ti-6Al-4V parts in accordance with the required dimensional resolution and deposition rate,together with sound strength and ductility balance in the as-built condition.

关键词： laser-aided additive manufacturing powder deposition wire deposition interfacial characteristic mechanical behavior

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：