检索结果-内蒙古大学图书馆

Research on Lightweight Acoustic Scene Perception Method Based on Drunkard Methodology

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2024年第1期E107D卷 83-92页

作者： Liu, Wenkai Zhang, Lin Wu, Menglong Cai, Xichang Dong, Hongxia North China Univ Technol Beijing Peoples R China

The goal of Acoustic Scene Classification (ASC) is to simulate human analysis of the surrounding environment and make accurate decisions promptly. Extracting useful information from audio signals in real-world scenarios is challenging and can lead to suboptimal performance in acoustic scene classification, especially in environments with relatively homogeneous backgrounds. To address this problem, we model the sobering-up process of "drunkards" in real-life and the guiding behavior of normal people, and construct a high-precision lightweight model implementation methodology called the "drunkard methodology". The core idea includes three parts: (1) designing a special feature transformation module based on the different mechanisms of information perception between drunkards and ordinary people, to simulate the process of gradually sobering up and the changes in feature perception ability;(2) studying a lightweight "drunken" model that matches the normal model's perception processing process. The model uses a multi-scale class residual block structure and can obtain finer feature representations by fusing information extracted at different scales;(3) introducing a guiding and fusion module of the conventional model to the "drunken" model to speed up the sobering up process and achieve iterative optimization and accuracy improvement. Evaluation results on the official dataset of DCASE2022 Task1 demonstrate that our baseline system achieves 40.4% accuracy and 2.284 loss under the condition of 442.67K parameters and 19.40M MAC (multiply-accumulate operations). After adopting the "drunkard" mechanism, the accuracy is improved to 45.2%, and the loss is reduced by 0.634 under the condition of 551.89K parameters and 23.6M MAC.

关键词： acoustic scene classification model compression multi-scale module knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

A two-branch hand gesture recognition approach combining atrous convolution and attention mechanism

引用

VISUAL COMPUTER 2023年第10期39卷 4487-4500页

作者： Wang, Shi Zhang, Shihui Zhang, Xiaowei Geng, Qingjia Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066004 Hebei Peoples R China Key Lab Comp Virtual Technol & Syst Integrat Hebe Qinhuangdao 066004 Hebei Peoples R China Hebei Normal Univ Sci & Technol Qinhuangdao 066004 Hebei Peoples R China

Hand gesture recognition is an important research field in computer vision. To effectively solve the problem of low hand gesture recognition accuracy, we propose two modules by using atrous convolution in this paper. One is multi-scale Fusion (MSF) module. The other is Light-Weight multi-scale (LWMS) module. The MSF module can be used for extracting multi-scale features at different receptive fields. The LWMS module can be considered as a kind of enhanced and expanded convolutional operation. Based on the two modules, a Hand Gesture Recognition Approach called HGRA is designed. HGRA is a hand gesture recognition approach which is based on an end-to-end CNN-based framework with two branches. One branch uses the U-Net combined with multi-scale Attention module to perform hand gesture segmentation in order to separate hand gestures from complex backgrounds. Then the segmentation result is used for extracting shape features. The other branch extracts visual features, such as appearance and color. The shape and the visual features obtained by the two branches are integrated to perform hand gesture recognition. Experimental results on the OUHANDS and HGR1 gesture datasets show that the proposed method has competitive performance both in hand gesture segmentation and recognition.

关键词： Hand gesture recognition Hand gesture segmentation multi-scale module multi-scale attention mechanism Atrous convolution

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Graph Network for Video Crowd Counting

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第1期33卷 228-241页

作者： Wu, Zhe Zhang, Xinfeng Tian, Geng Wang, Yaowei Huang, Qingming Peng Cheng Lab Shenzhen 518055 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China

In recent years, researchers have developed many deep-learning-based methods to count crowd numbers in static images. However, much fewer works focus on video-based crowd counting, in which the critical challenge of temporal correlation has not been well explored. This paper proposes a Spatial-Temporal Graph Network (STGN) to achieve efficient and accurate crowd counting in videos via learning pixel-wise and patch-wise relations in local spatial-temporal domains. Specifically, we design a pyramid graph module to leverage multi-scale features. In each scale, we sequentially construct three graphs: spatial-temporal pixel graph, temporal patch graph, and spatial pixel graph, in which we apply the self-attention mechanism to capture pixel-wise relation, learn structure-aware relation, and aggregate local features, respectively. Furthermore, we propose spatial-aware channel-wise attention to effectively fuse multi-scale features. To demonstrate the effectiveness of the proposed method, we conduct experiments on five crowd counting datasets, including a large-scale video crowd dataset (FDST). Moreover, the proposed model is also applied in the vehicle counting dataset (TRANCOS). The results show that the proposed model outperforms existing spatial-temporal crowd counting models and achieves state-of-the-art.

关键词： Computational modeling Predictive models Analytical models Long short term memory Optical flow Integrated circuit modeling Head Video-based crowd counting spatiotemporal graph attention multi-scale module

来源：评论

学校读者我要写书评

暂无评论

Sika Deer Behavior Recognition Based on Machine Vision

引用

Computers, Materials & Continua 2022年第12期73卷 4953-4969页

作者： He Gong Mingwang Deng Shijun Li Tianli Hu Yu Sun Ye Mu Zilian Wang Chang Zhang Thobela Louis Tyasi Jilin Agricultural University Changchun130118China Wuzhou University Wuzhou543000China Jilin Province Agricultural Internet of Things Technology Collaborative Innovation Center Changchun130118China Jilin Province Intelligent Environmental Engineering Research Center Changchun130118China Department of Agricultural Economics and Animal Production University of LimpopoSovenga0727PolokwaneSouth Africa Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou543000China

With the increasing intensive and large-scale development of the sika deer breeding industry,it is crucial to assess the health status of the sika deer by monitoring their behaviours.A machine vision-based method for the behaviour recognition of sika deer is proposed in this *** Inception Net(GoogLeNet)is used to optimise the model in this ***,the number of layers and size of the model were ***,the 5×5 convolution was changed to two 3×3 convolutions,which reduced the parameters and increased the nonlinearity of the model.A 5×5 convolution kernel was used to replace the original convolution for extracting coarse-grained features and improving the model’s extraction ability.A multi-scale module was added to the model to enhance the multi-faceted feature extraction capability of the ***,the Squeeze-and-Excitation Networks(SE-Net)module was included to increase the channel’s attention and improve the model’s *** dataset’s images were rotated to reduce *** image rotation,the angle wasmultiplied by 30°to obtain the dataset enhanced by rotation operations of 30°,60°,90°,120°and 150°.The experimental results showed that the recognition rate of this model in the behaviour of sika deer was 98.92%.Therefore,the model presented in this paper can be applied to the behaviour recognition of sika *** results will play an essential role in promoting animal behaviour recognition technology and animal health monitoring management.

关键词： Behaviour recognition SE-Net module multi-scale module improved Inception module

来源：评论

学校读者我要写书评

暂无评论

FREQUENCY AND multi-scale SELECTIVE KERNEL ATTENTION FOR SPEAKER VERIFICATION

FREQUENCY AND MULTI-SCALE SELECTIVE KERNEL ATTENTION FOR SPE...

引用

IEEE Spoken Language Technology Workshop (SLT)

作者： Mun, Sung Hwan Jung, Jee-Weon Han, Min Hyun Kim, Nam Soo Seoul Natl Univ Dept ECE & INMC Seoul South Korea Naver Corp Seongnam Si South Korea

ISBN: (纸本)9798350396904

The majority of recent state-of-the-art speaker verification architectures adopt multi-scale processing and frequency-channel attention mechanisms. Convolutional layers of these models typically have a fixed kernel size, e.g., 3 or 5. In this study, we further contribute to this line of research utilising a selective kernel attention (SKA) mechanism. The SKA mechanism allows each convolutional layer to adaptively select the kernel size in a data-driven fashion. It is based on an attention mechanism which exploits both frequency and channel domain. We first apply existing SKA module to our baseline. Then we propose two SKA variants where the first variant is applied in front of the ECAPA-TDNN model and the other is combined with the Res2net backbone block. Through extensive experiments, we demonstrate that our two proposed SKA variants consistently improves the performance and are complementary when tested on three different evaluation protocols.

关键词： speaker verification selective kernel attention multi-scale module

来源：评论

学校读者我要写书评

暂无评论

Dual-path multi-scale attention residual network for fault diagnosis of rolling bearings under complex operating conditions

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第8期35卷 086106-086106页

作者： Deng, Linfeng Zhang, Yuanwen Zhao, Cheng Wang, Guojun Lanzhou Univ Technol Sch Mech & Elect Engn Lanzhou Peoples R China

Rolling bearing faults inevitably occur during the long-term continuous operation of rotating machinery. Therefore, fault diagnosis is greatly important for ensuring the normal and safe operation of rolling bearings. However, the complexity and diversity of working conditions of rolling bearings present a significant challenge in extracting fault characteristics accurately, which further affects the ultimate fault diagnosis results. In this article, we propose a new model, called dual-path multi-scale attention residual network (DPMARN), for diagnosing bearing faults under complex operating conditions. DPMARN can effectively capture the feature-feature correlation information at different scales, which is more beneficial for fusing fault features at different scales to improve the model's performance. The main contributions of this work are summarized as follows: (1) the designed dual-path network model which incorporates parallel multi-scale branches of convolutional kernels and serially connects skip-layer multi-scale branches can integrate both low-frequency and high-frequency information and enhance the multi-scale feature extraction and complex data representation abilities. (2) The squeeze-and-excitation attention mechanism is embedded into the residual blocks to improve the ability of learning feature correlations and utilizing feature information effectively, which is helpful for extracting important fault characteristics. Extensive experiments conducted on two public bearing datasets demonstrate the superior performance of the DPMARN model for addressing the complex fault diagnosis problem. These results indicate that our proposed approach provides an effective solution for fault diagnosis of rolling bearings under complex operating conditions.

关键词： rolling bearing complex operating condition multi-scale module attention residual network fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Occlusion facial expression recognition based on feature fusion residual attention network

引用

FRONTIERS IN NEUROROBOTICS 2023年 17卷 1250706页

作者： Chen, Yuekun Liu, Shuaishi Zhao, Dongxu Ji, Wenkai Changchun Univ Technol Sch Elect & Elect Engn Changchun Peoples R China

Recognizing occluded facial expressions in the wild poses a significant challenge. However, most previous approaches rely solely on either global or local feature-based methods, leading to the loss of relevant expression features. To address these issues, a feature fusion residual attention network (FFRA-Net) is proposed. FFRA-Net consists of a multi-scale module, a local attention module, and a feature fusion module. The multi-scale module divides the intermediate feature map into several sub-feature maps in an equal manner along the channel dimension. Then, a convolution operation is applied to each of these feature maps to obtain diverse global features. The local attention module divides the intermediate feature map into several sub-feature maps along the spatial dimension. Subsequently, a convolution operation is applied to each of these feature maps, resulting in the extraction of local key features through the attention mechanism. The feature fusion module plays a crucial role in integrating global and local expression features while also establishing residual links between inputs and outputs to compensate for the loss of fine-grained features. Last, two occlusion expression datasets (FM_RAF-DB and SG_RAF-DB) were constructed based on the RAF-DB dataset. Extensive experiments demonstrate that the proposed FFRA-Net achieves excellent results on four datasets: FM_RAF-DB, SG_RAF-DB, RAF-DB, and FERPLUS, with accuracies of 77.87%, 79.50%, 88.66%, and 88.97%, respectively. Thus, the approach presented in this paper demonstrates strong applicability in the context of occluded facial expression recognition (FER).

关键词： occluded facial expression recognition feature fusion network multi-scale module local attention module attention mechanism

来源：评论

学校读者我要写书评

暂无评论

基于偏振成像和YOLOv8的雾天道路目标检测

引用

计量学报 2024年第11期45卷 1626-1633页

作者：谈爱玲李晓航赵勇高美静苏海杰刘闯郭天安燕山大学信息科学与工程学院河北省特种光纤与光纤传感重点实验室河北秦皇岛066004 燕山大学电气工程学院河北省测试计量技术及仪器重点实验室河北秦皇岛066004 北京理工大学集成电路与电子学院北京100081

雾天天气下,车辆和行人目标的准确检测对汽车自动驾驶非常重要。首先通过偏振成像装置采集了0°、45°、90°和135°角度的偏振图像,并通过3种不同的融合方式构建了I04590、stokes和pauli图像数据集。提出一种改进YOLOv... 详细信息

雾天天气下,车辆和行人目标的准确检测对汽车自动驾驶非常重要。首先通过偏振成像装置采集了0°、45°、90°和135°角度的偏振图像,并通过3种不同的融合方式构建了I04590、stokes和pauli图像数据集。提出一种改进YOLOv8的目标检测算法以提高雾天偏振图像中汽车和行人两类目标的检测准确率。提出一种基于混合池化的MixSPPF结构,改善了原有SPPF结构对全局信息的提取能力;然后基于不同大小的卷积设计了multiscale module模块并结合Coordinate Attention注意力机制增强了对空间信息和通道信息的提取。实验结果表明,提出的改进YOLOv8算法获得的全类平均准确率P_(A)@0.5和P_(A)@0.5:0.95分别达到了83.4%和39.3%,比初始YOLOv8算法分别提升了1.6%和0.9%。

关键词：目标检测偏振图像融合雾天天气 YOLOv8 MixSPPF multi-scale module

来源：评论

学校读者我要写书评

暂无评论

Knee Cartilages Segmentation Based on multi-scale Cascaded Neural Networks 1

引用

12th International Workshop on Machine Learning in Medical Imaging (MLMI 2021)

作者： Liu, Junrui Hua, Cong Zhang, Liang Li, Ping Lu, Xiaoyuan Xidian Univ Sch Comp Sci & Technol Xian Peoples R China Shanghai BNC Shanghai Peoples R China

ISBN: (数字)9783030875893

ISBN: (纸本)9783030875886;9783030875893

Knee arthritis is one of the most common chronic degenerative joint diseases in the world, affecting the quality of life of a considerable part of the Modern population. Therefore, the early detection of knee arthritis is of great significance for diagnosis and treatment. Magnetic resonance imaging (MRI) is one of the most commonly used methods for evaluating joint degeneration in osteoarthritis research. In order to obtain information on knee cartilage degradation from MRI, it is necessary to segment the articular cartilage interface and cartilage surface boundary on the entire joint surface. In this work, we propose a novel cascaded network structure with an effective inception-like multi-scale module for knee joint magnetic resonance images segmentation. Compared with the baseline, a maximum of 1.6% dice score mean promotion is obtained. The code is publicly available at https://***/ETVP

关键词： Knee cartilage segmentation Cascaded neural network Medical image multi-scale module

来源：评论

学校读者我要写书评

暂无评论

Intelligent judgment of rotating machinery based on multi-scale parallel network and attention mechanism

Intelligent judgment of rotating machinery based on multi-sc...

引用

第二十一届分布式计算及其应用国际学术研讨会

作者： Zhixiang Fan Pengjiang Qian Jiangnan University School of Artificial Intelligence and Computer Science

The primary problem solved in rotating machinery fault diagnosis is how to effectively extract fault features from the vibration signals with *** extract fault features accurately,this study proposes a multi-scale parallel convolutional neural network fault recognition algorithm,which can carry out feature *** above method combines empirical feature extraction(e.g.,fast Fourier transform) to enrich feature information,which can effectively implement deep *** effectiveness and reliability of the method are verified through example studies on JNU,SEU and PU rolling bearing experimental data *** algorithm has the higher classification capability and diagnostic accuracy compared with four common deep learning algorithms.

关键词： component Mechanical intelligent diagnosis Deep neural network multi-scale module Attention mechanism

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：