检索结果-内蒙古大学图书馆

SPIE 12th International Symposium on Multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Zou, Lamei Xie, Jia Wang, Hao Lu, Luhan Wu, Chengqing Guo, Yichun Zhang, Tianbao National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781510674967

ISBN: (纸本)9781510674950

We present a robust facial landmark detection network based on multiscale attention residual blocks (MARBNet) for effectively predicting facial landmark. MARBNet consists of three modules. Firstly, the coarse feature extraction module obtains coarse features through convolution, batch normalization, ReLU activation, and maximum pooling. The fine feature extraction module is composed of 33 multiscale attention residual blocks (MARB). MARB is composed of 1x1 convolution layer, 3x3 convolution layer, 1x1 convolution layer, two multiscale convolution module(MulRes) and channel attention module(CAM). MulRes is used to extract complementary features of different scales, obtain more feature information under different Receptive field, and avoid excessive loss of key information in the input image. CAM enables the network to pay more attention to high-frequency information on the channel, effectively prevents the loss of information, so as to improve the effect of facial landmark detection. The output module consists of two 1x1 convolution layers, one of which outputs landmark heatmap score and landmark coordinate offset, and the other outputs the nearest neighbor landmark offset. The experiment results on WFLW and 300W datasets show that our method is superior to the existing algorithms in terms of normalized mean square error indicators. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Human pose estimation constrained by human structure information 12

Human pose estimation constrained by human structure informa...

引用

SPIE 12th International Symposium on Multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Zou, Lamei Wang, Hao Xie, Jia Wu, Chengqing Lu, Luhan Guo, Yichun National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781510674967

ISBN: (纸本)9781510674950

We present a two-dimensional human pose estimation network constrained by the human structure information (HSINet). HSINet effectively fuses features of different scales and explicitly integrates human structure information to enhance the precision of key point localization. The architecture of HSINet comprises three pivotal modules: The feature extraction module, the encoding module, and the decoding module. The feature extraction module within HSINet employs the architecture of High-Resolution Net (HRNet). In contrast to HRNet, we remove redundant layers, and enhance the ability to combine global features and local features using the Gated Attention Unit (GAU). The second module encodes the feature maps derived from the feature extraction module. Each feature map corresponds to a joint point and is characterized by two feature vectors representing the x and y axes. Utilizing graph convolution for encoding introduces constraints based on human structure information. Subsequently, these encoded feature maps are decoded into precise coordinates of key points. The experiment results on COCO datasets show that our proposed method can improve the precision of key point detection while effectively reducing the number of parameters. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

One-bit splitting deceptive jamming against SAR

引用

Defence technology（防务技术） 2022年第10期18卷 1760-1777页

作者： Bo Zhao Lei Huang Bing Li Shi-qi Liu Wei-min Bao Guangdong Key Laboratory of Intelligent Information Processing College of Information EngineeringShenzhen UniversityShenzhen518060China China Aerospace Science and Technology Corporation Beijing100048China

One-bit quantization is a promising technique due to its performance retention and complexity reduction in a deceptive jammer against synthetic aperture radar(SAR).In this paper,the 1-bit quantization technology is utilized to agilely generate split false targets in the SAR imagery once the radar signal is intercepted,which reduces the complexity of the jammer significantly with guaranteed focusing quality.A single-frequency threshold is used to decompose harmonics incurred by the 1-bit quantization,and its parameters are adjusted through different pulse repetition intervals to provide steerable *** this way,the SAR signal is split into coupled false scatterers during the 1-bit *** further deploying amplitude,time-delay,and Doppler frequency modulations on the 1-bit intercepted signal,the split false targets are *** proposed approach is compared with different deceptive jamming methods to show its validity in effectiveness and cost,and numerical experiments are also presented for verification.

关键词： Synthetic aperture radar(SAR) 1-Bit quantization Multi-false-target Single-frequency threshold

来源：评论

学校读者我要写书评

暂无评论

MAGPNet: Multi-Domain Attention-Guided Pyramid Network for Infrared Small Object Detection

引用

Journal of Shanghai Jiaotong University (Science) 2024年 1-18页

作者： Ding, Leqi Wang, Biyun Yao, Lixiu Cai, Yunze Department of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China National Key Laboratory of Air-based Information Perception and Fusion Henan Luoyang471009 China Shanghai Institute of Aerospace Control Technology Infrared Detection Technology R&D Center of China Aerospace Science and Technology Corporation Shanghai201109 China

To overcome the obstacles of poor feature extraction and little prior information on the appearance of infrared dim small targets, we propose a multi-domain attention-guided pyramid network (MAGPNet). Specifically, we design three modules to ensure that salient features of small targets can be acquired and retained in the multi-scale feature maps. To improve the adaptability of the network for targets of different sizes, we design a kernel aggregation attention block with a receptive field attention branch and weight the feature maps under different perceptual fields with attention mechanism. Based on the research on human vision system, we further propose an adaptive local contrast measure module to enhance the local features of infrared small targets. With this parameterized component, we can implement the information aggregation of multi-scale contrast saliency maps. Finally, to fully utilize the information within spatial and channel domains in feature maps of different scales, we propose the mixed spatial-channel attention-guided fusion module to achieve high-quality fusion effects while ensuring that the small target features can be preserved at deep layers. Experiments on public datasets demonstrate that our MAGPNet can achieve a better performance over other state-of-the-art methods in terms of the intersection of union, Precision, Recall, and F-measure. In addition, we conduct detailed ablation studies to verify the effectiveness of each component in our network. © 2024, Shanghai Jiao Tong University.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

EPI-Mamba: State Space Model for Semantic Segmentation from Light Fields

EPI-Mamba: State Space Model for Semantic Segmentation from ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Li, Yan Chen, Jianan Wang, Qiong Xu, Jinshan College of Computer Science & Technology Zhejiang University of Technology Hangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China

ISBN: (纸本)9798350368741

Global contextual dependency is of significance for semantic segmentation from light fields. However, previous works mostly exploit attention mechanisms to model spatial context dependency and angular context dependency separately, since a light field capture is very data-intensive. Considering that self-attention is resource-consuming, existing methods only use it to capture spatial contextual dependency for the central view of light fields, and employ resource-efficient attention mechanisms to model angular view dependencies instead. Inspired by the recent success of State Space Sequence model (SSM), we present a novel SSM-based encoder for light field semantic segmentation, which models spatio-angular contextual dependency together. The proposed method is evaluated on the existing light field semantic segmentation datasets, and experimental results show that the proposed method significantly outperforms previous state-of-the-art methods. The code and models used in this work are available in https://***/YanWQ/EPI-Mamba. © 2025 IEEE.

关键词： Light field semantic segmentation Mamba State space model

来源：评论

学校读者我要写书评

暂无评论

Leveraging Slot-Aware Enhancements for Improved Zero-Shot Dialogue State Tracking 6

Leveraging Slot-Aware Enhancements for Improved Zero-Shot Di...

引用

6th International Conference on Frontier Technologies of information and Computer, ICFTIC 2024

作者： Song, Tianhang Hu, Haolei Chen, Xinxin Zi, Kangli Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Institute of Computing Technology Key Laboratory of Intelligent Information Processing Beijing China

ISBN: (纸本)9798331541750

Task-oriented dialogue systems (TOD) aim to help users complete specific tasks through multiple rounds of dialogue, in which Dialogue State Tracking (DST) is a key component. The training of DST models typically necessitates the availability of a substantial corpus of dialogue data with turn-level annotations. However, the collection of such data is both costly and inefficient. Despite the impressive performance of systems based on advanced large language models (LLMs), their closed-source nature restricts the potential for local deployment. To address this challenge, this paper proposes a new zero-shot slot-aware enhanced model (SAE), which introduces a novel coded prompting framework to enhance the DST capability of small parameter models in new domains and task scenarios. In particular, we have devised a prompting framework that employs code to refine task instructions. Furthermore, we have proposed a slot-aware question generation mechanism that generates slot-aware questions based on contextual details in accordance with the dialogue context, thereby enhancing the model's perception and matching capabilities for slots. In order to verify the effectiveness of the model, we conducted experiments on the MultiWOZ dataset. The results show that the SAE model has achieved significant performance improvements in zero-shot DST tasks. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

An Improved High Precision 3D Semantic Mapping of Indoor Scenes from RGB-D Images

引用

Computer Modeling in Engineering & Sciences 2023年第12期137卷 2621-2640页

作者： Jing Xin Kenan Du Jiale Feng Mao Shan Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of TechnologyXi’an710048China Australian Centre for Field Robotics The University of SydneySydney2006Australia

This paper proposes an improved high-precision 3D semantic mapping method for indoor scenes using RGB-D *** current semantic mapping algorithms suffer from low semantic annotation accuracy and insufficient real-time *** address these issues,we first adopt the Elastic Fusion algorithm to select key frames from indoor environment image sequences captured by the Kinect sensor and construct the indoor environment space ***,an indoor RGB-D image semantic segmentation network is proposed,which uses multi-scale feature fusion to quickly and accurately obtain object labeling information at the pixel level of the spatial point cloud ***,Bayesian updating is used to conduct incremental semantic label fusion on the established spatial point cloud *** also employ dense conditional random fields(CRF)to optimize the 3D semantic map model,resulting in a high-precision spatial semantic map of indoor *** results show that the proposed semantic mapping system can process image sequences collected by RGB-D sensors in real-time and output accurate semantic segmentation results of indoor scene images and the current local spatial semantic ***,it constructs a globally consistent high-precision indoor scenes 3D semantic map.

关键词： 3D semantic map online reconstruction RGB-D images semantic segmentation indoor mobile robot

来源：评论

学校读者我要写书评

暂无评论

FSA-Net:A Cost-efficient Face Swapping Attention Network with Occlusion-Aware Normalization

引用

intelligent Automation & Soft Computing 2023年第7期37卷 971-983页

作者： Zhipeng Bin Huihuang Zhao Xiaoman Liang Wenli Chen College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002China

The main challenges in face swapping are the preservation and adaptive superimposition of attributes of two *** this study,the Face Swapping Attention Network(FSA-Net)is proposed to generate photoreal-istic face *** existing face-swapping methods ignore the blending attributes or mismatch the facial keypoint(cheek,mouth,eye,nose,etc.),which causes artifacts and makes the generated face silhouette *** address this problem,a novel reinforced multi-aware attention module,referred to as RMAA,is proposed for handling facial fusion and expression occlusion *** framework includes two *** the first stage,a novel attribute encoder is proposed to extract multiple levels of target face attributes and integrate identities and attributes when synthesizing swapped *** the second stage,a novel Stochastic Error Refinement(SRE)module is designed to solve the problem of facial occlusion,which is used to repair occlusion regions in a semi-supervised way without any *** proposed method is then compared with the current state-of-the-art *** obtained results demonstrate the qualitative and quantitative outperformance of the proposed *** details are provided at the footnote link and at https://***/view/fsa-net-official.

关键词： Attention face-swapping neural network face manipulation identity swap image translation

来源：评论

学校读者我要写书评

暂无评论

Permittivity inversion of GPR images based on DeepLab 3

Permittivity inversion of GPR images based on DeepLab

引用

3rd International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2022

作者： Liu, Hongwei Wang, Jinpeng Talukdar, Masud Yuan, Da Key Laboratory of Intelligent Information Processing Shandong Technology and Business University Yantai Shandong264005 China

ISBN: (纸本)9781510663473

Ground Penetrating Radar (GPR) is usually used to detect unknown underground structure information, but it is very difficult to extract the underground target structure information from original GPR signal. This paper aims to solve the inversion problem by deep learning method. The two-dimensional ground penetrating radar B-scan signal is converted into intuitive underground structure information by neural network. In this paper, the DeepLab network proposed by Google is improved to solve the problem of permittivity inversion of GPR signal images. We verify the network using simulated data, which is generated by Finite Difference Time Domain (FDTD) algorithm. Finally we quantitatively evaluate the performance of our network by comparing it with some existing deep learning inversion networks. © 2023 SPIE.

关键词： Permittivity

来源：评论

学校读者我要写书评

暂无评论

Chinese Event Extraction Algorithm of Multi-information Semantic Enhancements 12

Chinese Event Extraction Algorithm of Multi-Information Sema...

引用

12th International Conference on Computing and Pattern Recognition, ICCPR 2023

作者： Qiang, Baohua Tang, Feng Zhou, Xiangyu Wang, Yuanchun Yang, Xianyi Li, Kai Guilin University of Electronic Technology Guilin China The 54th Research Institute of Cetc Shijiazhuang China Hebei Key Laboratory of Intelligent Information Perception and Processing Shijiazhuang China

ISBN: (纸本)9798400707988

To address the problems of inaccurate event element extraction, inability to directly handle long texts and errors in the fine-tuning stage of the task due to insufficient semantic information and incomplete semantic feature samples in the current Chinese domain event extraction model, this paper proposes the Chinese Event Extraction Algorithm of Multi-information Semantic Enhancements (MiSE). In the embedding stage, the algorithm is designed a coding structure that fusing multiple information: Using the Roformer model based on rotational encoding for word embedding and text embedding, and augment the Roformer word embedding matrix by mapping the word embedding matrixs of event trigger, argument information and their location information to it , forming an vector matrix that incorporates multiple information;the matrix is then placed into the BiLSTM for forward and backward chain calculation to enhance the model's ability to extract semantic information from Chinese text. In the decoding stage, using the decoding structure to obtain the set of tags with the highest probability. Comparing this algorithm with several Chinese event extraction algorithms on the Baidu DuEE dataset and its extraction results outperformed other event extraction algorithms in all evaluation metrics. © 2023 ACM.

关键词： Embeddings

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：