检索结果-内蒙古大学图书馆

International Conference on intelligent Control and Information processing (ICICIP)

作者： Yanke Lu Fang Li Xiaonan Luo Guangxi Key Laboratory of Image and and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Center for Applied Mathematics of Guangxi (GUET) Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

Image restoration is a classic foundational visual task, aimed at recovering damaged images, such as those affected by compression, blurring, or noise, to high-definition clarity. Although current image enhancement techniques largely rely on convolutional neural networks, the efficient capabilities of Transformers demonstrated in complex visual tasks have not yet been extensively applied in the field of image restoration. This paper presents an optimized image restoration strategy based on the SwinlR model, which is applied to the task of underwater image restoration. In the shallow feature extraction phase, deep separable convolution technology is employed; while in the deep feature extraction phase, a Spatial Gated Feedforward Network (SGFN) is utilized. The experimental data suggests that the novel approach surpasses conventional techniques in effectiveness and has effectively minimized both the model's parameter quantity and computational demands.

关键词： Visualization Convolution Computational modeling Noise Information processing Logic gates Feature extraction Transformers Image restoration intelligent control

来源：评论

学校读者我要写书评

暂无评论

Liver Tumor Image Segmentation Method Based on U-Net Network

Liver Tumor Image Segmentation Method Based on U-Net Network

引用

Data Intelligence and Innovative Application (DIIA), IEEE International Conference on

作者： Dinghong Lu Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

Liver tumors are the most common and fatal ones globally, bringing great harm to human life. In order to ascertain the precise location, size, and volume of tumors, the conventional method of manual segmentation necessitates that physicians delineate the tumor boundaries within the patients’ abdominal CT scans, a process that demands considerable expenditure of time and effort on the part of the medical staff. A method harnessing the U-Net neural network, predicated on deep learning, has been introduced in this study to augment the accuracy and efficiency of liver tumor segmentation in imaging. The U-Net network has been enhanced with the incorporation of Adam optimization and callback mechanisms to bolster the training efficacy and preserve the most effective model. Furthermore, the implementation of the binary crossentropy loss function has been pivotal for optimizing the neural network's convergence and predictive accuracy, which in turn has led to enhanced segmentation results. The experimental findings suggest that the proposed method is capable of automating the segmentation of liver tumor images, including the precise delineation of tumors and those with indistinct margins, achieving a segmentation accuracy of 99.64%.

关键词： Training Image segmentation Accuracy Computed tomography Neural networks Liver Medical services Manuals Optimization Tumors

来源：评论

学校读者我要写书评

暂无评论

Advanced Scale-aware Attention for Enhanced Tiny Object Detection in Remote Sensing

Advanced Scale-aware Attention for Enhanced Tiny Object Dete...

引用

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Tingting Qiao He Chen Bingqian Chai Wenchao Liu Guijie Qi Yizhuang Xie National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Recent advancements in remote sensing object detection have progressed, but distinguishing objects from complex backgrounds remains difficult, especially for tiny objects. To address this, we introduce the Advanced Scale-Aware Attention (ASA) module, which retains key channel information while minimizing computational cost. This module reorganizes channels into the batch dimension and splits them into multiple sub-features. The ASA module contains three branches: the first encodes weights based on scale and channel relationships. The second and third branches use different convolution kernel sizes to capture features across various receptive fields. These branches collaborate to enhance pixel-level relationships, improving foreground-background contrast. On the AI-TOD dataset, our method improved AP50 by 8.6% over state-of-the-art approaches.

关键词： Image resolution Convolution Object detection Feature extraction Data processing Sensors Object recognition Kernel Remote sensing Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Wearable:Multicolored Photochromic Fiber Opens New Frontiers in Human–Machine Interaction

引用

Advanced Fiber Materials 2024年第3期6卷 619-621页

作者： Jing Zhang Zhigang Xia Perry Ping Shum School of Mechanical Engineering and Electronic Information China University of Geosciences(Wuhan)Wuhan 430074China State Key Laboratory of New Textile Materials and Advanced Processing Technologies School of Textile Science and EngineeringTextile Industry Key Laboratory of Yarn and Its FunctionalizationWuhan Textile UniversityWuhan 430200China Department of Electronic and Electrical Engineering Southern University of Science and TechnologyShenzhen 518055China

Substantial challenges remain in developing fiber devices to achieve uniform and customizable photochromic lighting effects using lightweight hardware.A recent publication in Light Science&Application,spearheaded by ***-Qing Lu and *** Tao presents a methodical approach to surmount the limitations in photochromic *** integrated controllable photochromic fibers into various wearable devices,providing a promising path for future exploration and advancement in the field of human–machine interaction.

关键词： Multicolored photochromic fiber Wearable device Fiber thermal drawing process Human–machine interaction

来源：评论

学校读者我要写书评

暂无评论

Pseudo-Centroid Representation Learning for Cross-domain Few-shot Classification from Remote Sensing Imagery

Pseudo-Centroid Representation Learning for Cross-domain Few...

引用

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Can Li Jianlin Xie He Chen Yin Zhuang Jiahao Li Liang Chen National Key Laboratory of Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Cross-domain few-shot classification is gaining significant attention due to its potential to address challenges in remote sensing applications, such as large domain gaps and limited labeled data. Recent approaches have explored leveraging unlabeled target domain data for semi-supervised learning, in addition to source labeled data, to improve cross-domain training. However, these techniques often struggle with getting discriminative representation for distinguishing categories in novel target domains, particularly when facing new categories and limited training examples. To overcome these issues, we propose a novel cross-domain pseudo-centroid representation (CDPCR) framework, designed to generate more discriminative and adaptable class representations for improved cross-domain learning. The framework consists of a semi-supervised cross-domain structure that integrates both source labeled data and a portion of target unlabeled data to establish the relationship between domains. A consistency regularization branch is introduced to stabilize model outputs by aligning predictions on the target unlabeled data under input perturbations. Additionally, a pseudo-centroid contrastive representation learning module is incorporated to enhance intra-category feature consistency while improving the separability of inter-category representations, aiding the model in adapting to classification tasks across diverse domains. The effectiveness of the proposed CDPCR framework is validated through comprehensive experiments conducted across 8 cross-domain scenarios using remote sensing scene classification datasets.

关键词： Training Representation learning Adaptation models Scene classification Perturbation methods Semisupervised learning Predictive models Data processing Data models Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Beyond MLE: Convex Learning for Text Generation 37

Beyond MLE: Convex Learning for Text Generation

引用

37th Conference on Neural Information processing Systems, NeurIPS 2023

作者： Shao, Chenze Ma, Zhengrui Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Future Science and Engineering Soochow University China

ISBN: (纸本)9781713899921

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at https://***/ictnlp/Convex-Learning. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

SC-DVNet: A Dual-Branch Recognition Network for Synthetic Aperture Radar Images Based on Scattering Features

SC-DVNet: A Dual-Branch Recognition Network for Synthetic Ap...

引用

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Fan Chen Hao Shi Jingfei He Yifei Yin Fanyu Meng Liang Chen National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Ship classification using Synthetic Aperture Radar (SAR) images is a crucial component in marine monitoring. With the rise of deep neural networks (DNN), the abstract feature maps obtained by CNN-based methods have significantly improved classification performance. However, most current DNN-based methods are predominantly inherited from optical imagery, designed only for SAR intensity images, which may present challenges for further improving recognition performance. Therefore, this paper proposes using the point Scattering Center (SC) model for scattering feature extraction combined with graph convolutional networks for ship classification tasks. Comprehensive ablation experiments were carried out to demonstrate the efficacy of the proposed approach. Finally, experimental results on OpenSARShip1.0 dataset verify that the performance of the suggested approach notably outperforms DNN-driven techniques.

关键词： Integrated optics Image recognition Scattering Artificial neural networks Feature extraction Optical imaging Adaptive optics Optical scattering Marine vehicles Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Wearable and interactive multicolored photochromic fiber display

引用

Light(Science & Applications) 2024年第3期13卷 454-465页

作者： Pan Li Yuwei Wang Xiaoxian He Yuyang Cui Jingyu Ouyang Ju Ouyang Zicheng He Jiayu Hu Xiaojuan Liu Hang Wei Yu Wang Xiaoling Lu Qian Ji Xinyuan Cai Li Liu Chong Hou Ning Zhou Shaowu Pan Xiangru Wang Huamin Zhou Cheng-Wei Qiu Yan-Qing Lu Guangming Tao State Key Laboratory of Material Processing and Die&Mould Technology School of Materials Science and Engineering and Wuhan National Laboratory for OptoelectronicsHuazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Vascular Aging(HUST) Ministry of EducationWuhan 430030China School of Optoelectronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore National Laboratory of Solid State Microstructures Key Laboratory of Intelligent Optical Sensing and ManipulationCollege of Engineering and Applied Sciencesand Collaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210023China School of Performing Arts Wuhan Conservatory of MusicWuhan 430060China School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China School of Architecture and Urban Planning Huazhong University of Science and TechnologyWuhan 430074China School of Fashion Beijing Institute of Fashion TechnologyBeijing 100029China School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Tongji Medical College Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Materials Science and EngineeringDonghua UniversityShanghai 201620China

Endowing flexible and adaptable fiber devices with light-emitting capabilities has the potential to revolutionize the current design philosophy of intelligent,wearable interactive ***,significant challenges remain in developing fiber devices when it comes to achieving uniform and customizable light effects while utilizing lightweight ***,we introduce a mass-produced,wearable,and interactive photochromic fiber that provides uniform multicolored light *** designed independent waveguides inside the fiber to maintain total internal reflection of light as it traverses the *** impact of excessive light leakage on the overall illuminance can be reduced by utilizing the saturable absorption effect of fluorescent materials to ensure light emission uniformity along the transmission *** addition,we coupled various fluorescent composite materials inside the fiber to achieve artificially controllable spectral radiation of multiple color systems in a single *** prepared fibers on mass-produced kilometer-long using the thermal drawing *** fibers can be directly integrated into daily wearable devices or clothing in various patterns and combined with other signal input components to control and display patterns as *** work provides a new perspective and inspiration to the existing field of fiber display interaction,paving the way for future human–machine integration.

关键词： fiber interactive colored

来源：评论

学校读者我要写书评

暂无评论

keypoints and Action Units Jointly Drive Talking Head Generation for Video Conferencing

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Shi, Wuzhen Xue, Zibang Wen, Yang Shenzhen University Shenzhen Key Laboratory of Digital Creative Technology Guangdong Province Engineering Laboratory for Digital Creative Technology Guangdong Provincial Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen518060 China

This paper introduces a high-quality talking head generation method that is jointly driven by keypoints and action units, aiming to strike a balance between low-bandwidth transmission and high-quality generation in video conference scenarios. Existing methods for talking head generation often face limitations: they either require an excessive amount of driving information or struggle with accuracy and quality when adapted to low-bandwidth conditions. To address this, we decompose the talking head generation task into two components: a driving task, focused on information-limited control, and an enhancement task, aimed at achieving high-quality, high-definition output. Our proposed method innovatively incorporates the joint driving of keypoints and action units, improving the accuracy of pose and expression generation while remaining suitable for low-bandwidth environments. Furthermore, we implement a multistep video quality enhancement process, targeting both the entire frame and key regions, while incorporating temporal consistency constraints. By leveraging attention mechanisms, we enhance the realism of the challenging-to-generate mouth regions and mitigate background jitter through background fusion. Finally, a prior-driven super-resolution network is employed to achieve high-quality display. Extensive experiments demonstrate that our method effectively supports low-resolution recording, low-bandwidth transmission, and high-definition display. © 1991-2012 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection Based on the Transformer and High-Resolution Network

引用

Computers, Materials & Continua 2023年第2期74卷 3439-3454页

作者： Dengyong Zhang Huaijian Pu Feng Li Xiangling Ding Victor S.Sheng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411004China Department of Computer Science Texas Tech UniversityLubbock79409TXUSA

Now object detection based on deep learning tries different *** uses fewer data training networks to achieve the effect of large dataset ***,the existing methods usually do not achieve the balance between network parameters and training *** makes the information provided by a small amount of picture data insufficient to optimize model parameters,resulting in unsatisfactory detection *** improve the accuracy of few shot object detection,this paper proposes a network based on the transformer and high-resolution feature extraction(THR).High-resolution feature extractionmaintains the resolution representation of the *** and spatial attention are used to make the network focus on features that are more useful to the *** addition,the recently popular transformer is used to fuse the features of the existing *** compensates for the previous network failure by making full use of existing object *** on the Pascal VOC and MS-COCO datasets prove that the THR network has achieved better results than previous mainstream few shot object detection.

关键词： Object detection few shot object detection transformer high-resolution

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：