检索结果-内蒙古大学图书馆

Low-light few-shot object detection via curve contrast enhancement and flow-encoder-based variational autoencoder

Neural Computing and Applications 2025年第10期37卷 7261-7278页

作者： Jiang, Zetao Jin, Xin Kang, Junjie The Key Laboratory of image and graphic intelligent processing Guilin University of Electronic Technology Guangxi Guilin541004 China Wuhan Service Department Sinopec Shared Services.LTD.Nanjing Branch Jiangsu Nanjing210018 China Co. LTD Geely Group Zhejiang Ningbo315336 China

Aiming at the problem of insufficient samples in low-light object detection in some environments, a low-light few-shot object detection method based on curve contrast enhancement and flow-encoder-based variational autoencoder (CCEFVAE) is proposed. Our approach involves designing a CCE module to enhance the detailed features and contrast of low-light images by deriving a relationship expression between the enhanced image and the low-light image through the recursive relationship of high-order curves. The lumination estimation module in the CCE module estimates the parameters of the expression to calculate the pixel values of the enhanced image. Moreover, we propose an FVAE module to improve the decoupling of support features by combining the flow model encoder with the variational autoencoder, facilitating subsequent feature aggregation and classification. To ensure the consistency of the loss function of the flow model with the few-shot object detection loss, we design a negative Jacobian determinant transformation function. This enables direct addition of the two losses, allowing for unified optimization. Experimental results demonstrate that our proposed algorithm outperforms mainstream few-shot object detection models by an average of 13.1–23% in average after training on the low-light dataset (ExDark), and shows an average improvement of 5.8% compared to the state-of-the-art (SOTA) few-shot object detection model VFA. When trained on the normal lighting dataset (PASCAL VOC), the proposed algorithm exhibits a 1.7% improvement in average compared to VFA. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Curve contrast enhancement Few-shot object detection Flow-encoder-based variational autoencoder Low-light environment

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive load monitoring based on a combination of Transformer and CNN 4

Non-intrusive load monitoring based on a combination of Tran...

引用

4th International Conference on Energy, Power and Electrical Engineering, EPEE 2024

作者： Cheng, Yiqi Zhong, Yanru Guilin University of Electronic Technology College of Computer and Information Security Guangxi Guilin China Guilin University of Electronic Technology Guangxi Key Laboratory of Image And Graphic Intelligent Processing Guangxi Guilin China

ISBN: (纸本)9798331518066

Non-intrusive load monitoring (NILM) estimates the energy usage of individual devices by analyzing the total power meter data from a household. To address the issue of decreased monitoring accuracy with an increasing number of electricity meters, this paper proposes a solution for single appliance load monitoring (Tra-CNN). The solution uses the UK-DALE dataset, which contains high and low frequencies electricity consumption data of multiple households in the UK and the electricity consumption data of each household appliance, and uses the active power of the appliance as the input of the algorithm. The first part of the model consists of a convolutional layer, a normalization layer, and a dropout layer, with the primary task of capturing local dependencies in the data. The second part consists of a Transformer, whose self-attention mechanism associates features at different positions in the sequence to achieve modeling of long-term dependencies. The third part introduces a convolutional neural network, which uses a sliding window for convolution operations to extract local features from different positions and further extract features from sequence data. The final decoder consists of a transposed convolutional layer and a normalization layer, designed to revert the learned features to their original dimensions. Through experimental verification, the effectiveness and superiority of Tra-CNN are shown, which provides important ideas and methods for the further development of NILM technology. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Smart Power Safety Hazard Inspection System Based on YOLOv7 1st

Smart Power Safety Hazard Inspection System Based on YOLOv7

引用

1st International Conference on Applied Intelligence, ICAI 2023

作者： Liang, Yiheng Li, Xiaoming Deng, Zhenrong School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9789819708260

Power safety is closely related to people’s well-being. Electric power sectors regularly inspect and maintain power lines to guarantee people’s safe and stable use of electricity, and the current mainstream inspection method is to use UAVs for power inspection. Traditional inspection and detection methods have many shortcomings, such as high labor costs, slow inspection speed, low detection efficiency, and single detection targets. In this paper, a set of smart power inspection systems based on YOLOv7 was designed to check the common potential security risks of power lines such as bird nests, insulators, garbage, and hardware. After the detection, the detection report could be generated. The system adopted the YOLOv7 target detection algorithm. The accuracy rate of all detection targets was up to 93.9%, and the mAP @.5% reached 95.9%. Therefore, the algorithm could greatly improve the detection efficiency and greatly facilitate the electric power sectors to check power lines, so it has a high use value. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking 48

Learning to Reconnect Interrupted Trajectories for Weakly Su...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Yu-Lei Lu, Yang Li, Jie Wang, Hanzi Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics China Xidian University Video and Image Processing System Laboratory School of Electronic Engineering China

ISBN: (纸本)9781728163277

Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may contain many false or missing identities, which adversely affect the optimization of tracking networks, resulting in interrupted trajectories of occluded targets. To effectively reconnect the interrupted trajectories caused by noisy pseudo labels, we propose a novel weakly supervised MOT method based on a Trajectory-Reconnecting Transformer (TRTMOT). TRT-MOT performs feature decoupling to extract discriminative embedding features for reconnecting trajectories of occluded targets. Experimental results show that TRTMOT outperforms previous weakly supervised MOT methods by at least +3.6 and +5.6 on MOTA for the MOT17 and MOT20 datasets, respectively. © 2023 IEEE.

关键词： Feature Decoupling Pseudo Identity Labels Trajectory-Reconnecting Transformer Weakly Supervised Multi-Object Tracking

来源：评论

学校读者我要写书评

暂无评论

Research summary of "Camellia oleifera fruit picking robot" technical analysis

Research summary of "Camellia oleifera fruit picking robot" ...

引用

2021 International Conference on Signal processing and communication Technology, SPCT 2021

作者： Wang, Liang Hou, Yifeng Wang, Kuikui Wei, Chunming Guangxi Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Wuzhou Guangxi543003 China

ISBN: (数字)9781510653344

ISBN: (纸本)9781510653337

Aiming at the problems of my country's current camellia fruit picking mainly relying on manual picking, large labor and low efficiency, the development and promotion of camellia fruit picking equipment and technology are discussed, and technical analysis is carried out for the design of camellia fruit picking robots. This article analyzes the characteristics and existing problems of camellia fruit picking, and analyzes the four major components of the picking robot: "end effector", "manipulator motion control system", "visual recognition positioning system"and "driving walking device". In summary, summarize the problems that have been solved, the results achieved, and the difficulties that still exist, so as to provide enlightenment for the subsequent exploration of the subject research of "camellia fruit picking robot". © 2022 SPIE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

GFENet: Enabling Attention and Adaptive Feature Fusion in Real-time Object Detection 2

GFENet: Enabling Attention and Adaptive Feature Fusion in Re...

引用

2nd International Symposium on Electrical, Electronics and Information Engineering, ISEEIE 2022

作者： Pan, Chaolin Zhu, Xiaoyang Chu, Jun Nanchang Hangkong University Department of Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang China

ISBN: (数字)9781665468749

ISBN: (纸本)9781665468749

Real-time object detection has been a critical component of onboard instrumentation for next-generation autonomous driving. To enable safety and reliability in autonomous driving systems, we must continue advancing its real-time object detection accuracy for future autonomous driving systems in complex environments. Existing works in real-time object detection cannot accurately detect objects with similar appearances and in complex environments. In particular, existing approaches missed many essential features because of the loss of multi-scale contextual features. Therefore, they cannot differentiate objects that have a similar appearance, a low-resolution, and a small size. To solve these issues, and to advance real-time object detection accuracy, we develop GFENet (Global Feature Enhancement Network), an end-to-end real-time object detection framework. First, we introduce a convolutional attention module that integrates spatial and channel-wise features and eliminates ineffective features to enable a strong feature representation of the network, followed by a lightweight residual module that further advances the feature representation by highlighting salient changes in features. Second, we build an adaptive feature fusion module to adaptively learn weights of multi-scale contextual features across layers, aiming to strengthen weights for small-size objects. We comprehensively evaluate GFENet on two leading object detection datasets-PASCAL VOC and MS COCO. The evaluation results (mAP of 82.9 and FPS of 31 on PASCAL VOC;mAP of 39.0 and FPS of 23 on MS COCO) show the outperformance of GFENet compared to competing baseline methods. © 2022 IEEE.

关键词： Instruments Object detection Detectors Feature extraction Real-time systems Safety Reliability

来源：评论

学校读者我要写书评

暂无评论

AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment

arXiv

引用

arXiv 2025年

作者： Cao, Yuqin Min, Xiongkuo Gao, Yixuan Sun, Wei Zhai, Guangtao Institute of Image Communication and Network Engineering Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiao Tong University Shanghai China

Many video-to-audio (VTA) methods have been proposed for dubbing silent AI-generated videos. An efficient quality assessment method for AI-generated audio-visual content (AGAV) is crucial for ensuring audio-visual quality. Existing audio-visual quality assessment methods struggle with unique distortions in AGAVs, such as unrealistic and inconsistent elements. To address this, we introduce AGAVQA, the first large-scale AGAV quality assessment dataset, comprising 3, 382 AGAVs from 16 VTA methods. AGAVQA includes two subsets: AGAVQA-MOS, which provides multi-dimensional scores for audio quality, content consistency, and overall quality, and AGAVQA-Pair, designed for optimal AGAV pair selection. We further propose AGAV-Rater, a LMM-based model that can score AGAVs, as well as audio and music generated from text, across multiple dimensions, and selects the best AGAV generated by VTA methods to present to the user. AGAV-Rater achieves state-of-the-art performance on AGAVQA, Text-to-Audio, and Text-to-Music datasets. Subjective tests also confirm that AGAV-Rater enhances VTA performance and user experience. The project page is available at https://***. Copyright © 2025, The Authors. All rights reserved.

关键词： Subjective testing

来源：评论

学校读者我要写书评

暂无评论

First-Principles Study on Switching Performance and Spin Filtering Efficiency of Dimethyldihydropyrene/Cyclophanediene Single-Molecule Devices with Zigzag Graphene Nanoribbon Electrodes

引用

Chinese Journal of Chemical Physics 2024年第5期37卷 644-652,I0066-I0072,I0100页

作者： Chang-Feng Zheng Yan-Qi Mu Zong-Liang Li Guang-Ping Zhang Shandong Key Laboratory of Medical Physics and Image Processing&Shandong Provincial Engineering and Technical Center of Light Manipulations School of Physics and ElectronicsShandong Normal UniversityJinan 250358China

Moleculardeviceswith highswitchingperformance and/or the perfect spin filtering effect have always been the pursuit with the development of molecular ***,yusingthe 2001.0V ***'s function method in combination with the density functionaltheory,the switching performance and spin filtering properties of dimethyldihydropyrene(DHP)/cyclophanediene(CPD)photoswitchable molecule connected by carbon atomic chains(CACs)to two zigzag graphene nanoribbon electrodes have been theoretically *** results show that DHP is more conductive than CPD and therefore an evident switching effect is demonstrated,and the switching ratio(RON/OFF)can reach 4.5×*** is further revealed that the RoON/OF of DHP/CPD closely depends on the length of *** specifically,the RoN/OFF values of DHP/CPD with odd-numbered CACs are larger than those with even-numbered *** interestingly,a high or even perfect spin filtering effect can be obtained in these investigated DHP/CPD single-molecule *** study is helpful for future design of single-molecule switches and spin filters and provides a way to optimize their performance by means of varying the length of bridging CACs.

关键词： Single-molecule switch Spin filtering effect Odd-even effect Nonequilibrium Green's function method Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Real-time arbitrarily-shaped scene text spotting with weakly supervised points

Real-time arbitrarily-shaped scene text spotting with weakly...

引用

2023 International Conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2023

作者： Zhao, Longyang Zhang, Shuhao Xu, Zhi School of Computer Science and Information Security Guilin University of Electronics Technology No.1 Jinji road Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9781510677685

Recently, there has been widespread interest in arbitrary-shaped scene text spotting, showing notable progress in both speed and accuracy. However, common issues such as model complexity, slow inference speed, and challenges in deployment persist. For this reason, this paper proposes Weakly Supervised Point-collection Network (WSPNet) for arbitrarily shaped scene text, which adopts deformable convolutional single-shot network architecture to realize multi-branch parallel reading of text, and combines weakly supervised text line point sampling to realize sampling recognition and transcription of arbitrarily shaped text instances. To enhance the robustness of multi-scale fusion, we utilize the Text Feature Fusion (TFF) module to dynamically acquire key features at different scales during the fusion process. This approach aims to reduce discrepancies in scale fusion. Extensive experiments on arbitrarily shaped benchmarks show that WSPNet achieves competitive accuracy and speed. For example, the proposed method achieves an end-to-end text recognition F-measure of 63.4 on the Total-Text dataset at 35.5 FPS, which is competitive with the best results in terms of speed and accuracy balance. © 2024 SPIE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

SpliceCannon: A novel framework for the prediction of canonical and non-canonical splice sites based on deep learning

SpliceCannon: A novel framework for the prediction of canoni...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhang, Yanju Qi, Wangjing Lin, Ruohan Fan, Jinli Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Huaqiao University College of Computer Science and Technology Xiamen China

ISBN: (纸本)9798350337488

Accurately predicting splice sites in DNA sequences is not only of utmost importance in the study of gene expression and protein synthesis, but also crucial to precisely understanding the pathogenesis of various diseases related to splicing. In the past few decades, several tools for identifying splice sites have been developed, however, many of them ignore the contextual influence in DNA sequences in the process of encoding, consequently leading to considerable false positives in prediction. Additionally, most methods solely investigate canonical splicing whereas pay little attention to non-canonical ones. To address the issues mentioned above, we propose a comprehensive method, SpliceCannon, for accurately predicting both canonical and non-canonical splice sites based on neural networks. This method uses the combination of k-nucleotide frequencies and Doc2vec to encode the sequence, then employs a series of comprehensive neural networks such as bidirectional long short-term memory networks and residual networks to effectively extract features from the original sequence while avoiding the problems such as gradient vanishing. The results demonstrate that our method consistently achieves high accuracy when tested on multiple species. Compared to other recent methods, our model exhibits superior performance, stronger generalization ability, and wider applicability. In particular, The recognition accuracy is also remarkably high on the non-canonical dataset. We envision that this proposed method will serve as a promising tool for splice sites prediction to facilitate genomic research. © 2023 IEEE.

关键词： Bidirectional long short-term memory networks Canonical and non-canonical splice sites Deep learning Skip connection

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：