检索结果-内蒙古大学图书馆

10th IEEE Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2022

作者： Yu, Xiao Li, Qishen Huang, Hua Li, Qiufeng School of Information Engineering Nanchang Hangkong University Jiangxi Nanchang China School of Software Nanchang Hangkong University Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang China Jiangxi China

ISBN: (数字)9781665422079

ISBN: (纸本)9781665422079

Zero-shot learning (ZSL) utilizes semantic information that is auxiliary information to transfer knowledge from seen classes to unseen classes, thereby realizing the recognition of unseen classes. The generative methods train the model to generate pseudo image features for the unseen classes, thus transforming ZSL into a supervised learning problem. However, the classification performances of these methods still suffer from weak generalization. To address this issue, the paper proposes a novel Generative Adversarial Network based on Generative Feature Constraint (GFCGAN). First, based on the LsrGAN [1], a semantic constraint module is added to restrict the generated image features by keeping the semantic information consistent. Then, in the case of keeping the semantic relationships between classes consistent, the generated image features of unseen classes are farther away from the feature prototypes of their most similar classes in both semantic and feature space so as to train the generative model and generate high-quality pseudo image features. Finally, the trained classifier is used to classify images of unseen classes. Experiments on standard datasets verify the effectiveness of our model and achieve good results. © 2022 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Millimeter-wave radar image analysis for the traffic sensing 2

Millimeter-wave radar image analysis for the traffic sensing

引用

2nd Spring International Conference on Defence Technology, ICDT 2020

作者： Wu, H.M. Qi, F. Wang, J.K. Wang, Y. School of Communication Science and Engineering Northeastern University Liaoning Province Shenyang110819 China Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences China Key Lab of Image Understanding and Computer Vision Liaoning Province Shenyang110016 China

Millimeter-wave(MMW) radar sensing is one of the most promising technologies to provide safe navigation for autonomous vehicles due to its expected high-resolution imaging capability However, driverless cars have higher request for different environment and light conditions. Therefore, millimetre-wave imaging is of paramount importance for complex load scenario. In this paper, we have built models of pavement pits and bulges and analysed their with differences ways of antennas. A comparison of the imaging performance of experimental systems operating at a MMW radar and a Lidar is presented with the analysis of features for initial image interpretation Experimental images of the complex road surface are made by a 94GHz frequency-modulated continuous-wave (FMCW) radar technique with 3mm wavelength. © Published under licence by IOP Publishing Ltd.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Object Detector based on Enhanced Multi-scale Feature Fusion Pyramid Network

Object Detector based on Enhanced Multi-scale Feature Fusion...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Luan Zhao Xiaofeng Zhang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Constructing the pyramidal architecture for the feature is currently a very effective way to obtain feature information of objects at different scales. Although the feature pyramid can realize the recognition and detection of multi-scale objects in the object detection task well, it still has some limitations. Since the feature information of different levels is often not from the same layer of the network, it is difficult to obtain the feature of different objects information at a certain scale from a certain level feature map of the pyramid network. To solve this problem, we present a novel object detection architecture, named Enhanced Multi-scale Feature Fusion Pyramid Network (EMFFPNet). Our network consists of Enhanced Multi-scale Feature Fusion Module (EMFFM) and Predictor Optimization Module (POM). In EMFFM, Features at different levels can be fused into the Enhanced features as outputs, which are more representative and deterministic. In order to enable the enhanced features to play their respective roles in the pyramid network, we assign different weights to fusion features of different levels in POM. We perform the experiments on the COCO detection benchmark. The experimental results indicate that the performance of our model is much better than the state-of-the-art model.

关键词： Object detection Predictive models Feature extraction Task analysis Information technology Optimization Standards

来源：评论

学校读者我要写书评

暂无评论

Element-Wise Layer Normalization for Continuous Signal Representation 23

Element-Wise Layer Normalization for Continuous Signal Repre...

引用

15th International Conference on Digital image processing, ICDIP 2023

作者： Chen, Weifeng Ding, Hui He, Zhifen Li, Bo Liu, Bin Wang, Kang School of Mathematics and Information Science Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China Jiangxi Science and Technology Infrastructure Center Jiangxi Computing Center Jiangxi Computing Center Nanchang China

ISBN: (纸本)9798400708237

Implicit neural representation (INR), sometimes also referred to coordinate-based representation or fitting, has gained the state-of-the-art performance in numerous research fields including computer vision and computer graphics due to the powerful continuous representation ability. Recent researches indicate that Fourier embedding is critical for INR to fit realistic images with high-frequency details. However, is Fourier embedding all we need for high-frequency coordinate (image) fitting? In this paper, we revisit the problem of coordinate fitting from a novel perspective of distribution mapping. Fourier embedding, as a preprocessing step of coordinate fitting, essentially performs the operation of mapping the uniform coordinate distribution to a normal distribution, and makes the learning of mapping function between two similar smooth distribution become easier. However, the number of discrete Fourier basis function affects the fitting performance dramatically and cannot be determined automatically. Based on the above analysis, a simple yet efficient INR coordinate fitting method is proposed in this paper, which demonstrates that the Fourier embedding is not the only way to improve INR. The proposed method only adds an element-wise layer normalization (ELN) module to the vanilla multi-layer perception (MLP) with ReLU activation. Experimental results on public database demonstrate that the proposed method outperforms the state-of-the-art methods using Fourier embedding. © 2023 ACM.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Asymmetric stereoscopic video encoding algorithm based on subjective visual characteristic

Asymmetric stereoscopic video encoding algorithm based on su...

引用

International Conference on Wireless communications and Signal processing (WCSP)

作者： Shu Liu Feng Liu Jingjing Fan Hongfei Xia Image Processing and Image Communication Jiangsu Key Laboratory Nanjing University of Posts and Telecommunications Nanjing China ZTE Telecom Company Limited Nanjing China

In traditional asymmetric stereo video encoding scheme, one eye is represented with high quality sequence, the other eye is represented with lower quality one. However, if the low quality view is the observer's dominant eye, the masking effect will not work. Based on this human visual characteristic, this paper proposed a GOP-based resolution cross-switching asymmetric encoding scheme. By allocating degradation to both of views in a balanced way over time, our experimental results show better compression efficiency than JMVM reference software and better subjective visual quality than the traditional asymmetric stereo video encoding scheme. Our stereo video coding scheme can be a trade-off between compression performance and subjective visual quality.

关键词： Encoding image coding Video compression Degradation Video coding image quality Psychology Layout image processing image communication

来源：评论

学校读者我要写书评

暂无评论

Autofocusing for Cleavage-stage Embryos in Brightfield Microscopy: Towards Automated Preimplantation Genetic Testing 16th

Autofocusing for Cleavage-stage Embryos in Brightfield Micro...

引用

16th International Conference on Intelligent Robotics and Applications, ICIRA 2023

作者： Yao, Sheng Wu, Kairui Qi, Li Yang, Feng Feng, Qianjin School of Biomedical Engineering Southern Medical University Guangzhou China Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou China Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology Southern Medical University Guangzhou China

ISBN: (纸本)9789819964888

Autofocusing is essential and serves as a prerequisite for the automation of embryo biopsy in preimplantation genetic testing (PGT) using robotics. Despite the existence of numerous autofocus algorithms, achieving accurate autofocusing for cleavage-stage embryos in brightfield microscopy remains challenging due to their non-unimodal nature. Thus, an adaptive and robust autofocusing method is required. This paper presents an autofocusing method based on an adaptive focus measure. The proposed method employs an adaptive focus measure selection approach and incorporates a coarse-to-fine strategy for autofocusing cleavage-stage embryos in brightfield microscopy. Experimental results demonstrate that the proposed autofocusing method achieves superior performance compared to other regular autofocus algorithms in brightfield microscopy for cleavage-stage embryos. This advancement marks a significant step forward in the automation development of PGT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

Enabling Multi-scale Features and Double-Attention for Single-image 3D Urban Reconstruction

Enabling Multi-scale Features and Double-Attention for Singl...

引用

2021 China Automation Congress, CAC 2021

作者： Miao, Jun Shen, Ji Jiang, Ruixiang Chu, Jun Guo, Luanzheng The School of Aeronautical Manufacturing Engineering Nanchang Hangkong University Nanchang330063 China The Department of Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang330063 China The Pacific Northwest National Laboratory WA99354 United States

ISBN: (纸本)9781665426473

3D reconstruction from a single RGB image for urban scenes has been a foundation for safety-critical applications such as autonomous driving and city planning. It is essential to develop 3D reconstruction models that are accurate for these applications. The most recent single-image 3D reconstruction models leverage representative neural networks to address the problem and have achieved promising results. However, these approaches cannot correctly calculate the segmentation map and reconstruct depth for ambiguous scene regions and when scene information gets lost going through down-sampling layers. To solve this problem, we propose EMERALD, an end-to-end single-image 3D reconstruction framework, in which we empower the fully convolutional networks (FCN) with multi-scale contextual features and a novel double-attention mechanism to advance its discrimination capability on ambiguous scene regions and loss of scene details. The evaluation results on two leading urban- scene data sets, Cityscapes (Segmentation Covering (SC)1 of 61.2%) and SYNTHIA (SC of 81.9%), demonstrate the optimized network architecture's effectiveness. © 2021 IEEE

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Immune microenvironment-reshaping Au@Bi_(2)Te_(3) nanoparticles for spectral computed tomography/photoacoustic imaging-guided synergetic photo/radio/immunotherapy

引用

Nano Research 2023年第1期16卷 771-781页

作者： Kai Zhu Zede Wu Qiuyu Li Meirong Hou Honglei Hu Shuting Zheng Li Qi Yikai Xu Chenggong Yan Bingxia Zhao Department of Medical Imaging Center Nanfang HospitalSouthern Medical UniversityGuangzhou 510515China Guangzhou Key Laboratory of Tumor Immunology Research Cancer Research InstituteSchool of Basic Medical SciencesSouthern Medical UniversityGuangzhou 510515China Guangdong Provincial Key Laboratory of Medical Image Processing Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic TechnologySchool of Biomedical EngineeringSouthern Medical UniversityGuangzhou 510515China Guangdong Provincial Key Laboratory of Shock and Microcirculation Guangzhou 510515China Experimental Education/Administration Center School of Basic Medical ScienceSouthern Medical UniversityGuangzhou 510515China

Radiotherapy(RT)mediated tumor immunogenicity offers an opportunity for simultaneous RT and immunotherapy via immunogenic cell death(ICD),which releases damaged-associated molecular patterns and generates“eat me”signals for the innate immune system to modulate the ***,tumor hypoxia significantly reduces the therapeutic efficacy of RT and hampers its mediation of ICD ***,Au@Bi_(2)Te_(3)-polyethylene glycol(PEG)was rationally constructed as theranostic nanozymes for mild photothermal therapy,tumor hypoxia modulation,and RT adjuvant cancer *** tumor-specific production of oxygen could not only augment the effects of RT by enhanced reactive oxygen species(ROS)generation,but also reduce hypoxia-related cytokines and downregulate programmed cell death-ligand 1(PD-L1)to unleash immune-enhancing T ***,Au@Bi_(2)Te_(3)-PEG could act as an immune-blocking inhibitor by efficient ICD induction with the combination of mild-photothermal therapy+RT to inhibit the tumor immune escape and improve antitumor immune *** amounts of CD^(4+) and CD^(8+) Tcells and elevated levels of cytokines could be observed that eventually led to effective post-medication inhibition of primary and abscopal *** computed tomography/photoacoustic imaging allowed noninvasive and real-time tracking of nanoparticle(NP)accumulation and oxygenation status at tumor ***,Au@Bi_(2)Te_(3)-PEG NPs could serve as effective theranostic nanoregulators with remarkable synergistic mildphotothermal/RT/immunotherapy effects that helped reshape the immune microenvironment and had remarkable molecular imaging properties.

关键词： radioresistance immunotherapy immunogenic cell death hypoxia programmed cell death-ligand 1(PD-L1) spectral computed tomography(CT)

来源：评论

学校读者我要写书评

暂无评论

A skew angle detection algorithm based on maximum gradient difference

A skew angle detection algorithm based on maximum gradient d...

引用

2011 International Conference on Transportation, Mechanical, and Electrical Engineering, TMEE 2011

作者： Wang, Dan Wang, Xichang Liu, Jiang Institute of Information Science and Engineering Shandong Normal University Shandong Province Key Laboratory for Distributed Computer Software Novel Technology Shandong China Shandong Oumasoft Co. Ltd Research Institute of Digital Image Processing Shandong China

ISBN: (纸本)9781457717017

In order to resolve the problem of skew phenomenon in the handwritten document image during the scanning process, a new skew angle detection algorithm based on maximum gradient difference as well as Hough transform was proposed in the paper. Firstly, text lines are labeled by using maximum gradient difference, and then we use the method of non-text filtering to get rid of shorter text lines and dots. Finally, margin information is extracted after refining on text lines, and two-stage Hough transform is made to the margin extracted information with the strategy varying from "coarse" to "fine" strategy, calculating the skew angle of document image which is fixed by the average of several longest lines. Experiment results shows that the algorithm detects skew angles of document image more rapidly and accurately than Hough transform alone. © 2011 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Multi-focus image Fusion Algorithm Based on Regional Firing Characteristic of Pulse Coupled Neural Networks

Multi-focus Image Fusion Algorithm Based on Regional Firing ...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Xiaobo Qu Jingwen Yan Department of Communication Engineering Xiamen University Xiamen China Key Laboratory of Digital Signal and Image Processing of Guangdong Province Shantou University Shantou China

Multi-focus image fusion aims at overcoming imaging cameras' finite depth of field by combining information from multiple images with the same scene. In this paper, a regional firing intensity (RFI) is defined, which is based on the statistical characteristic in local window of neuron firing times when pulse coupled neural networks (PCNN) is utilized in the image fusion. A novel image fusion algorithm based on regional firing characteristic PCNN (RFC-PCNN) is proposed and RFI is considered as a determination to select the coefficients of source images. First, a multiscale decomposition on each source image is performed by discrete wavelet transform. Second, PCNN is employed to extract features of source images in wavelet domain. Thirdly, RFI is computed and used to combine the coefficients of source images. Finally, the fused coefficients are used to reconstruct the fused image by an inverse discrete wavelet transform. Experimental results show that the proposed algorithm outperforms the wavelet-based and wavelet-PCNN-based fusion algorithms.

关键词： image fusion Neural networks Discrete wavelet transforms Radiofrequency interference Cameras Layout Neurons Feature extraction Wavelet domain image reconstruction

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：