检索结果-内蒙古大学图书馆

Micro-Expression Recognition Based on Spatio-Temporal Feature Extraction of key Regions

computers, Materials & Continua 2023年第10期77卷 1373-1392页

作者： Wenqiu Zhu Yongsheng Li Qiang Liu Zhigao Zeng College of Computer Science Hunan University of TechnologyZhuzhou412007China Intelligent Information Perception and Processing Technology Hunan Province Key LaboratoryZhuzhou412007China

Aiming at the problems of short duration,low intensity,and difficult detection of micro-expressions(MEs),the global and local features of ME video frames are extracted by combining spatial feature extraction and temporal feature *** on traditional convolution neural network(CNN)and long short-term memory(LSTM),a recognition method combining global identification attention network(GIA),block identification attention network(BIA)and bi-directional long short-term memory(Bi-LSTM)is *** the BIA,the ME video frame will be cropped,and the training will be carried out by cropping into 24 identification blocks(IBs),10 IBs and uncropped *** alleviate the overfitting problem in training,we first extract the basic features of the preprocessed sequence through the transfer learning layer,and then extract the global and local spatial features of the output data through the GIA layer and the BIA layer,*** the BIA layer,the input data will be cropped into local feature vectors with attention weights to extract the local features of the ME frames;in the GIA layer,the global features of the ME frames will be ***,after fusing the global and local feature vectors,the ME time-series information is extracted by *** experimental results show that using IBs can significantly improve the model’s ability to extract subtle facial features,and the model works best when 10 IBs are used.

关键词： Micro-expression recognition attention mechanism long and short-term memory network transfer learning identification block

来源：评论

学校读者我要写书评

暂无评论

CBNet: Cooperation-Based Weakly Supervised Polyp Detection 24

CBNet: Cooperation-Based Weakly Supervised Polyp Detection

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Du, Xiuquan Chen, Jiajia Zhang, Xuejun Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Anhui Hefei China School of Computer Science and Technology Anhui University Anhui Hefei China

ISBN: (纸本)9798400706868

Missed polyps are the major risk factor for colorectal cancer. To minimize misdiagnosis, many methods have been developed. However, they either rely on laborious instance-level annotations, require labeling of prompt points, or lack the ability to filter noise proposals and detect polyps integrally, resulting in severe challenges in this area. In this paper, we propose a novel Cooperation-Based network (CBNet), a two-stage polyp detection framework supervised by image labels that removes wrong proposals through classification in collaboration with segmentation and obtains a more accurate detector by aggregating adaptive multi-level regional features. Specifically, we conduct a Cooperation-Based Region Proposal Network (CBRPN) to reduce the negative impact of noises by deleting proposals without polyps, enabling our network to capture polyp features. Moreover, to enhance location integrity and classification precision of polyps, we aggregate multi-level region of interest (ROI) features under the guidance of the backbone classification layer, namely Adaptive ROI Fusion Module (ARFM). Extensive experiments on the public and private datasets show that our method achieves state-of-the-art performance for weakly supervised methods and even outperforms full supervision in some terms. All code is available at https://***/dxqllp/CBNet. © 2024 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement via Associated Perturbation Removal and Texture Reconstruction Learning

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2253-2269页

作者： Kui Jiang Ruoxi Wang Yi Xiao Junjun Jiang Xin Xu Tao Lu IEEE the School of Computer Science and Technology Harbin Institute of Technology Zhengzhou Research Institute Harbin Institute of Technology the School of Artificial Intelligence Jianghan University the School of Geodesy and Geomatics Wuhan University the Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology the School of Computer Science and Engineering and also with the Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology

Degradation under challenging conditions such as rain, haze, and low light not only diminishes content visibility, but also results in additional degradation side effects, including detail occlusion and color distortion. However, current technologies have barely explored the correlation between perturbation removal and background restoration, consequently struggling to generate high-naturalness content in challenging scenarios. In this paper, we rethink the image enhancement task from the perspective of joint optimization: Perturbation removal and texture reconstruction. To this end, we advise an efficient yet effective image enhancement model, termed the perturbation-guided texture reconstruction network(PerTeRNet). It contains two subnetworks designed for the perturbation elimination and texture reconstruction tasks, respectively. To facilitate texture recovery,we develop a novel perturbation-guided texture enhancement module(PerTEM) to connect these two tasks, where informative background features are extracted from the input with the guidance of predicted perturbation priors. To alleviate the learning burden and computational cost, we suggest performing perturbation removal in a sub-space and exploiting super-resolution to infer high-frequency background details. Our PerTeRNet has demonstrated significant superiority over typical methods in both quantitative and qualitative measures, as evidenced by extensive experimental results on popular image enhancement and joint detection tasks. The source code is available at https://***/kuijiang94/PerTeRNet.

关键词： Association learning attention mechanism image enhancement perturbation modeling

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive Load Monitoring Based Data-Free Incremental Electrical Appliance Identification 8th

Non-intrusive Load Monitoring Based Data-Free Incremental El...

引用

8th International Conference on Energy and Environmental Science, ICEES 2024

作者： Zhou, Rui Fang, Xiaohan The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China

ISBN: (纸本)9783031639005

In the realm of modern energy management systems, Non-Intrusive Load Monitoring (NILM) technology provides an innovative solution for power suppliers. It allows for remote monitoring and analysis of users’ electricity consumption patterns without requiring direct access to each device. This technology works by collecting comprehensive energy data at the user’s meter entry point and using algorithms to differentiate and identify the energy consumption characteristics of each device. However, with the increasing number of smart devices used by residential and commercial users, traditional NILM methods face the challenge of dealing with more complex and diverse electricity usage patterns. To address these challenges, we propose a novel incremental NILM framework. This framework has the ability to independently learn new load categories without load data, which is crucial for adapting in real-time to the changing variety of load devices, while also effectively addressing user privacy concerns. We introduce a VI-SCRM for extracting V-I trajectory features, incorporating a reconstruction convolution module. This method reduces the redundancy of V-I trajectory features and eliminates insignificant features, thereby improving algorithm efficiency. Additionally, this approach streamlines the model training process and prevents the model from ‘forgetting’ previously acquired knowledge. By implementing this framework in NILM, the system can continually adjust to new types of devices. Our experimental results confirm the effectiveness of this approach and highlight its potential advantages in practical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv8n Model for Detecting Helmets and License Plates on Electric Bicycles

引用

computers, Materials & Continua 2024年第7期80卷 449-466页

作者： Qunyue Mu Qiancheng Yu Chengchen Zhou Lei Liu Xulong Yu The College of Computer Science and Engineering North Minzu UniversityYinchuan750021China The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu UniversityYinchuan750021China

Wearing helmetswhile riding electric bicycles can significantly reduce head injuries resulting fromtraffic *** effectively monitor compliance,the utilization of target detection algorithms through traffic cameras plays a vital role in identifying helmet usage by electric bicycle riders and recognizing license plates on electric ***,manual enforcement by traffic police is time-consuming and *** methods face challenges in accurately identifying small targets such as helmets and license plates using deep learning *** paper proposes an enhanced model for detecting helmets and license plates on electric bicycles,addressing these *** proposedmodel improves uponYOLOv8n by deepening the network structure,incorporating weighted connections,and introducing lightweight convolutional *** modifications aim to enhance the precision of small target recognition while reducing the model’s parameters,making it suitable for deployment on low-performance devices in real traffic *** results demonstrate that the model achieves an mAP@0.5 of 91.8%,showing an 11.5%improvement over the baselinemodel,with a 16.2%reduction in ***,themodel achieves a frames per second(FPS)rate of 58,meeting the accuracy and speed requirements for detection in actual traffic scenarios.

关键词： YOLOv8 object detection electric bicycle helmet detection electric bicycle license plate detection

来源：评论

学校读者我要写书评

暂无评论

Joint Secure Transmit Beamforming Designs for Physical Layer Security in MIMO-ISAC System 2

Joint Secure Transmit Beamforming Designs for Physical Layer...

引用

2nd IEEE International Conference on signal, Information and Data processing, ICSIDP 2024

作者： Guo, Sitong Zheng, Hao Zhang, Yinghui Yan, Junkun Inner Mongolia University College of Electronic Information Engineering Hohhot China Inner Mongolia University Inner Mongolia Key Laboratory of Intelligent Communication and Sensing and Signal Processing Hohhot China Xidian University National Key Laboratory of Radar Signal Processing Xian China

ISBN: (纸本)9798331515669

This article concentrates on the physical layer security (PLS) towards an integrated sensing and communication (ISAC) system, which communicates with legitimate communication users (CUs) and detects the single sensing target, which is considered to be eavesdropper because it might intercept the transmitting message from the base station to CUs. The joint transmitting beamforming for secure communication and sensing is designed to maximize the sum secrecy rate (SR) of system under the constraints of quality-of-service of CUs, the signal-to-Noise Ratio (SNR) of sensing and the power budget of the system. The optimal solution is obtained by the semidefinite relaxation and successive convex approximation algorithms. The availability of the beamforming design in ensuring the SR of the ISAC system is showed by Simulation results. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

A Multi-strategy Improved Snake Optimizer Assisted with Population Crowding Analysis for Engineering Design Problems

引用

Journal of Bionic Engineering 2024年第3期21卷 1567-1591页

作者： Lei Peng Zhuoming Yuan Guangming Dai Maocai Wang Jian Li Zhiming Song Xiaoyu Chen School of Computer Science China University of GeosciencesWuhan430074China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of GeosciencesWuhan430074China China Astronautics Standards Institute Beijing100071China

Snake Optimizer(SO)is a novel Meta-heuristic Algorithm(MA)inspired by the mating behaviour of snakes,which has achieved success in global numerical optimization problems and practical engineering ***,it also has certain drawbacks for the exploration stage and the egg hatch process,resulting in slow convergence speed and inferior solution *** address the above issues,a novel multi-strategy improved SO(MISO)with the assistance of population crowding analysis is proposed in this *** the algorithm,a novel multi-strategy operator is designed for the exploration stage,which not only focuses on using the information of better performing individuals to improve the quality of solution,but also focuses on maintaining population *** boost the efficiency of the egg hatch process,the multi-strategy egg hatch process is proposed to regenerate individuals according to the results of the population crowding *** addition,a local search method is employed to further enhance the convergence speed and the local search *** is first compared with three sets of algorithms in the CEC2020 benchmark functions,including SO with its two recently discussed variants,ten advanced MAs,and six powerful CEC competition *** performance of MISO is then verified on five practical engineering design *** experimental results show that MISO provides a promising performance for the above optimization cases in terms of convergence speed and solution quality.

关键词： Snake optimizer Multi-strategy Population crowding analysis Engineering design problem

来源：评论

学校读者我要写书评

暂无评论

Research on Improved MobileViT Image Tamper Localization Model

引用

computers, Materials & Continua 2024年第8期80卷 3173-3192页

作者： Jingtao Sun Fengling Zhang Huanqi Liu Wenyan Hou School of Computer Science and Technology Xi’an University of Posts and TelecommunicationsXi’an710121China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and TelecommunicationsXi’an710121China

As image manipulation technology advances rapidly,the malicious use of image tampering has alarmingly escalated,posing a significant threat to social *** the realm of image tampering localization,accurately localizing limited samples,multiple types,and various sizes of regions remains a multitude of *** issues impede the model’s universality and generalization capability and detrimentally affect its *** tackle these issues,we propose FL-MobileViT-an improved MobileViT model devised for image tampering *** proposed model utilizes a dual-stream architecture that independently processes the RGB and noise domain,and captures richer traces of tampering through dual-stream ***,the model incorporating the Focused Linear Attention mechanism within the lightweight network(MobileViT).This substitution significantly diminishes computational complexity and resolves homogeneity problems associated with traditional Transformer attention mechanisms,enhancing feature extraction diversity and improving the model’s localization *** comprehensively fuse the generated results from both feature extractors,we introduce the ASPP architecture for multi-scale feature *** facilitates a more precise localization of tampered regions of various ***,to bolster the model’s generalization ability,we adopt a contrastive learning method and devise a joint optimization training strategy that leverages fused features and captures the disparities in feature distribution in tampered *** strategy enables the learning of contrastive loss at various stages of the feature extractor and employs it as an additional constraint condition in conjunction with cross-entropy *** a result,overfitting issues are effectively alleviated,and the differentiation between tampered and untampered regions is *** evaluations on five benchmark datasets(IMD-20,CASIA,NIST-16,Columbia and Coverage)validat

关键词： Image tampering localization focused linear attention mechanism MobileViT contrastive loss

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning of non-additive joint steganographic embedding costs with attention mechanism

引用

Science China(Information Sciences) 2023年第3期66卷 273-286页

作者： Weixuan TANG Bin LI Weixiang LI Yuangen WANG Jiwu HUANG Institute of Artificial Intelligence and Blockchain Guangzhou University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Computer Science and Cyber Engineering Guangzhou University

Image steganography is the art and science of secure communication by concealing information within digital images. In recent years, the techniques of steganographic cost learning have developed rapidly. Although the existing methods can learn satisfactory additive costs, the interplay of different pixels' embedding impacts has not been considered, so the potential of learning may not be fully exploited. To overcome this limitation, in this paper, a reinforcement learning paradigm called Jo Po L(joint policy learning) is proposed to extend the idea of additive cost learning to a non-additive situation. Jo Po L aims to capture the interactions within pixel blocks by defining embedding policies and evaluating contributions of embedding impacts on a block level rather than a pixel level. Then, a policy network is utilized to learn optimal joint embedding policies for pixel blocks through interactions with the environment. Afterwards,these policies can be converted into joint embedding costs for practical message embedding. The structure of the policy network is designed with an effective attention mechanism and incorporated with the domain knowledge derived from traditional non-additive steganographic methods. The environment is responsible for assigning rewards according to the impacts of the sampled joint embedding actions, which are evaluated by the gradient information of a neural network-based steganalyzer. Experimental results show that the proposed non-additive method Jo Po L significantly outperforms the existing additive methods against both feature-based and CNN-based steganalzyers over different payloads.

关键词： information hiding non-additive steganography steganalysis cost learning image processing

来源：评论

学校读者我要写书评

暂无评论

Accuracy verification of sulfur dioxide data based on ultraviolet hyperspectral solar radiometer observations 3

Accuracy verification of sulfur dioxide data based on ultrav...

引用

3rd International Conference on Environmental Remote Sensing and Geographic Information Technology, ERSGIT 2024

作者： Zeng, Hao Wang, Shun Xun, Lina The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei China

ISBN: (纸本)9781510690219

One of the primary air pollutants that has a detrimental effect on both the environment and human health is sulfur dioxide. The ecosystem and climate greatly depend on the high-precision monitoring of sulfur dioxide. In this study, SO2 ground-based data in Xi'an and Hangzhou were calculated using the UV continuous spectral inversion method, and the accuracy was confirmed using OMI satellite data that had undergone bilinear spatial interpolation. Although there are still some discrepancies in the comparative analysis results, the results indicate a good correlation between the ground-based measurement results of the UV hyperspectral solar radiometer and OMI data products;the correlation numbers are 0.938 and 0.941, respectively, and the relative errors are roughly 10%. The ultraviolet hyperspectral solar radiometer can complement this study's findings with accuracy and is a valuable tool for environmental monitoring. © 2025 SPIE.

关键词： Air quality

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：