检索结果-内蒙古大学图书馆

Recurrent fusion transformer for image captioning

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第1期19卷 1-9页

作者： Mou, Zhenping Yuan, Qiao Song, Tianqi Chongqing Normal Univ Sch Comp & Informat Sci Chongqing 401331 Peoples R China Chongqing Univ Sci & Technol Coll Intelligent Technol & Engn Chongqing 401331 Peoples R China

Image captioning describes the visual content of a given image by using natural language sentences. However, in the existing image captioning model, the encoder only describes the image content from a specific pattern, and cannot fully understand the semantic sequence information of the input image. In this paper, we propose a multimodal recurrent fusion block (RF-Block), which uses a new recurrent attention and combines gated recurrent networks to capture feature correlation information. Also, a stack multiple feature fusion blocks is used can better enhance the relationship between higher-level features. Finally, the feature fusion block is inserted into the Transformer to form a recurrent fusion transformer (RCT), which can improve the performance of the image captioning model. Experimental results show that the proposed model is better than the traditional encoder-decoder image captioning model and provides comparable performance to the most advanced models.

关键词： Image captioning Recurrent fusion block Transformer encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

CFPNet: Complementary Feature Perception Network for Underwater Image Enhancement

引用

IEEE JOURNAL OF OCEANIC ENGINEERING 2025年第1期50卷 150-163页

作者： Fu, Xianping Qin, Wenqiang Li, Fengqi Xu, Fengqiang Yan, Xiaohong Dalian Maritime Univ Sch Informat Sci & Technol Dalian 116026 Peoples R China Dalian Jiaotong Univ Sch Software Dalian 116600 Peoples R China Dalian Key Lab Blockchain Technol & Applicat Dalian 116028 Peoples R China

Images shot underwater are usually characterized by global nonuniform information loss due to selective light absorption and scattering, resulting in various degradation problems, such as color distortion and low visibility. Recently, deep learning has drawn much attention in the field of underwater image enhancement (UIE) for its powerful performance. However, most deep learning-based UIE models rely on either pure convolutional neural network (CNN) or pure transformer, which makes it challenging to enhance images while maintaining local representations and global features simultaneously. In this article, we propose a novel complementary feature perception network (CFPNet), which embeds the transformer into the classical CNN-based UNet3+. The core idea is to fuse the advantages of CNN and transformer to obtain satisfactory high-quality underwater images that can naturally perceive local and global features. CFPNet employs a novel dual encoder structure of the CNN and transformer in parallel, while the decoder is composed of one trunk decoder and two auxiliary decoders. First, we propose the regionalized two-stage vision transformer that can progressively eliminate the variable levels of degradation in a coarse-to-fine manner. Second, we design the full-scale feature fusion module to explore sufficient information by merging the multiscale features. In addition, we propose an auxiliary feature guided learning strategy that utilizes reflectance and shading maps to guide the generation of the final results. The advantage of this strategy is to avoid repetitive and ineffective learning of the model, and to accomplish color correction and deblurring tasks more efficiently. Experiments demonstrate that our CFPNet can obtain high-quality underwater images and show superior performance compared to the state-of-the-art UIE methods qualitatively and quantitatively.

关键词： Deep learning encoder-decoder image enhancement transformer underwater image

来源：评论

学校读者我要写书评

暂无评论

Deep Feature Blend Attention: A New Frontier in Super Resolution Image Generation

引用

NEUROCOMPUTING 2025年 618卷

作者： Dhanusha, P. B. Muthukumar, A. Lakshmi, A. Kalasalingam Acad Res & Educ Dept Elect & Commun Engn Virudunagar Tamil Nadu India Ramco Inst Technol Dept Elect & Commun Engn Rajapalayam Tamil Nadu India

Super Resolution (SR) images contain more useful information than Low Resolution (LR) images. Generally, SR images are highly preferred over LR images in the medical field due to their high quality. Generally, SR images are affected by many factors, like blur, noise, and decimation. Therefore, the present study proposes Deep Feature Blend Attention Mechanism for generating SR images with optimal outcomes. In this study, a Deep Learning (DL) based encoder-decoder is used to extract the detailed information from the LR image, assist in noise removal, and improve image quality. Using Gaussian blur, an LR image is produced, which is given as input to the encoder-decoder. The Attention mechanism with feature blending is performed to produce the reconstructed SR image. The low and high frequency component issues from feature map are improved using the attention mechanism. Also, feature blend attention mechanism is implied to reconstruct SR images from LR images. The present study utilizes the feature blend technique, which helps select the optimal features and blending to attain the optimal feature set. The study is performed with and without the feature blend technique in attention mechanism to expose the impact of the feature blend technique, and it is used to avoid overfitting issues and produce optimal results. The performance of the proposed system is assessed by using PSNR and SSIM to show the system's efficiency. The proposed system is compared with other state-of-the-art studies to expose the efficacy of the present system.

关键词： Super resolution image generation encoder-decoder Feature blend Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A deep learning model based on multi-attention mechanism and gated recurrent unit network for photovoltaic power forecasting

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 123卷

作者： Yang, Kuo Cai, Yanjie Cheng, Jinrun Shanghai Dianji Univ Sch Mech Engn Shanghai 200444 Peoples R China

Solar energy plays a crucial role in the power grid due to its clean, stable, and cost-effective nature, as well as its significant storage potential. Accurate short-term photovoltaic (PV) power forecasting is essential for effective grid management and dispatching decisions. This study introduces a hybrid deep learning model integrating multiple attention mechanisms and gated recurrent unit networks to forecast PV output power one day in advance. To address the impact of random weather variations and historical PV power data on forecasting accuracy, the model incorporates an input attention mechanism to process input features. Additionally, temporal and spatial attention mechanisms are embedded within the encoder-decoder framework to enhance prediction performance. These mechanisms effectively capture the relationships between historical PV power output and meteorological variables while identifying crucial time-dependent hidden states. The proposed model is validated on a real-world PV dataset, achieving a mean absolute error of 0.0903 under favorable weather conditions, demonstrating a 22.5 % improvement over traditional forecasting methods across various weather classifications. Comparative analyses with other state-of-the-art models confirm that the proposed approach offers superior predictive accuracy.

关键词： Multi-attention mechanism Gated recurrent unit encoder-decoder Photovoltaic power prediction

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Multi-Target Object Detection and Tracking Framework for Robust Spatio-Temporal Memory in Dynamic Environments

引用

IEEE ACCESS 2025年 13卷 47146-47164页

作者： Alzubi, Tareq Mahmod Mukhtar, Umar Raza Al Balqa Appl Univ Prince Abdullah Bin Ghazi Fac Informat & Commun Te Dept Comp Sci As Salt 19385 Jordan Univ Management & Technol Dept Comp Sci Lahore 54770 Pakistan

Multiple object tracking (MOT) is a critical task in computer vision, applied in areas such as autonomous driving, sports analytics, and human activity recognition. Traditional online MOT approaches, which rely on separate detection and re-identification (re-ID) stages, often suffer from high computational costs and suboptimal accuracy. To address these challenges, we propose MOTTNet, a unified framework that integrates detection and tracklet mapping using transformer-based architectures. MOTTNet leverages a spatiotemporal memory network to store past observations of tracked objects, allowing for more robust identity preservation and trajectory prediction over time. The Target Proposal Module generates object candidates using a transformer encoder-decoder structure, and the memory decoder integrates both proposal and track vectors to predict object locations and identities in real-time, minimizing post-processing. The framework incorporates a multi-scale attention pyramid to handle variations in object scale and utilizes a deformable transformer for generating accurate object proposals. A memory encoding-decoding aggregates object features and associates them across frames, allowing robust detection and identity preservation over time. MOTTNet achieves IDF1 scores of 79.8 and 80.4, MOTA scores of 79.3 and 80.1, and HOTA scores of 73.2 and 72.7, respectively, on on the MOT17 and MOT20 datasets. Additionally, MOTTNet exhibits lower identity switch rates, significantly outperforming existing transformer-based and traditional tracking models.

关键词： Feature extraction Transformers Target tracking Vectors Accuracy Trajectory Object detection Visualization Sports Real-time systems Multi-object tracking memory network transformer multi-scale pyramid encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

FS-Net: Full scale network and adaptive threshold for improving extraction of micro-retinal vessel structures

引用

PATTERN RECOGNITION LETTERS 2025年 189卷 188-194页

作者： Getahun, Melaku N. Rogov, Oleg Y. Dylov, Dmitry V. Somov, Andrey Bouridane, Ahmed Hamoudi, Rifat Skolkovo Inst Sci & Technol Skoltech Moscow Russia Univ Sharjah Ctr Data Analyt & Cybersecur Sharjah U Arab Emirates Univ Sharjah Res Inst Med & Hlth Sci Coll Med Sharjah U Arab Emirates UCL Fac Med Sci Div Surg & Intervent Sci London England Univ Sharjah Biomed Informed Artificial Intelligence Lab BIMAI Lab Sharjah U Arab Emirates Bian Que AI Hong Kong Peoples R China

Retinal vascular segmentation, a widely researched topic in biomedical image processing, aims to reduce the workload of ophthalmologists in treating and detecting retinal disorders. Segmenting retinal vessels presents unique challenges;previous techniques often failed to effectively segment branches and microvascular structures. Recent neural network approaches struggle to balance local and global properties and frequently miss tiny end vessels, hindering the achievement of desired results. To address these issues in retinal vessel segmentation, we propose a comprehensive micro-vessel extraction mechanism based on an encoder- decoder neural network architecture. This network includes residual, encoder booster, bottleneck enhancement, squeeze, and excitation building blocks. These components synergistically enhance feature extraction and improve the prediction accuracy of the segmentation map. Our solution has been evaluated using the DRIVE, CHASE-DB1, and STARE datasets, yielding competitive results compared to previous studies. The AUC and accuracy on the DRIVE dataset are 0.9884 and 0.9702, respectively. For the CHASE-DB1 dataset, these scores are 0.9903 and 0.9755, respectively, and for the STARE dataset, they are 0.9916 and 0.9750. Given its accurate and robust performance, the proposed approach is a solid candidate for being implemented in real-life diagnostic centers and aiding ophthalmologists.

关键词： Retinal vascular segmentation Microvascular structures encoder booster Bottleneck enhancement encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Abstractive text summarization using deep learning models: a survey

引用

INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS 2025年 1-29页

作者： Abdul Salam, Mustafa Gamal, Mostafa Hamed, Hesham F. A. Sweidan, Sara Prince Sattam Bin Abdulaziz Univ Coll Engn Dept Comp Engn & Informat Al Kharj 16273 Saudi Arabia Benha Univ Fac Comp & Artificial Intelligence Dept Artificial Intelligence Banha 13518 Egypt Minia Univ Fac Engn Elect Engn Dept El Minia Egypt Egyptian Russian Univ Badr City Fac Artificial Intelligence Dept Artificial Intelligence Cairo 11829 Egypt New Mansoura Univ Fac Comp Sci & Engn Gamasa 35712 Egypt

In the face of escalating volumes of textual data, the demand for advanced systems to efficiently manage this deluge is evident. Automatic summarization is a pivotal solution, continually evolving to meet the burgeoning data needs and user expectations. This paper delves into abstract text summarization, particularly focusing on utilizing neural networks-a recent breakthrough in the field. Through a comprehensive analysis of various models, we meticulously dissect critical components such as encoder-decoder design, mechanisms, training methodologies, dataset considerations, and evaluation metrics. Our primary objective is to illuminate current model landscapes, pinpoint existing challenges, and propose potential remedies. Notably, transformer-based encoder-decoder architectures emerge as state-of-the-art solutions. We suggest combining neural networks with pre-trained language models to improve abstractive summarization, making advanced techniques more accessible and effective. This approach aims to bolster the efficiency and efficacy of summarization systems, thereby facilitating superior information extraction and comprehension for users grappling with extensive textual datasets.

关键词： NLP Abstract text summarization encoder-decoder Mechanism attention Transformers

来源：评论

学校读者我要写书评

暂无评论

ARAFNet: An attribute refinement attention fusion network for advanced visual captioning

引用

DIGITAL SIGNAL PROCESSING 2025年 162卷

作者： Hossen, Md. Bipul Ye, Zhongfu Hossain, Md. Shamim Hossain, Md. Imran Begum Rokeya Univ Fac Sci Dept Stat Rangpur 5404 Bangladesh Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230027 Anhui Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230027 Anhui Peoples R China Pabna Univ Sci & Technol Dept ICE Rajshahi 6600 Bangladesh

Visual captioning, at the nexus of computer vision and natural language processing, is one of the pivotal aspects of multimedia content understanding, demands precise and contextually fitting image descriptions. Attribute-based approaches with attention mechanisms are effective in this realm. However, many of these approaches struggle to capture semantic details due to the prediction of irrelevant attributes and reduced performance. In response to these challenges, we propose an innovative solution: the Attribute Refinement Attention Fusion Network (ARAFNet), which aims to produce significant captions by distinctly identifying major objects and background information. The model features a comprehensive Attribute Refinement Attention (ARA) module, equipped with an attribute attention mechanism, which interactively extracts the most important attributes according to the linguistic context. Diverse attributes are employed at different time steps, enhancing the model's capability to utilize semantic features effectively while also filtering out irrelevant attribute words, thereby enhancing the precision of semantic guidance. An integrated fusion mechanism is then introduced to narrow the semantic gap between visual and attribute features. Finally, this fusion mechanism combined with the language LSTM to generate precise and contextually relevant captions. Extensive experimentation demonstrates our model's superiority over advanced counterparts, achieving an average CIDEr-D score of 11.88% on the Flickr30K dataset and 11.25% on the MS-COCO dataset through cross-entropy optimization. The ARAFNet model consistently outperforms the baseline model across a diverse range of evaluation metrics and makes a significant contribution to the field of image captioning precision. The implementing code and associated materials will be published at https://***/mdbipu/ARAFNet.

关键词： Visual captioning Attribute refinement attention Integrated fusion mechanism encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

MRI super-resolution reconstruction based on 3D dense connected convolutional autoencoders

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 107卷

作者： Kang, Li Song, Xinxin Huang, Jianjun Liu, Guojuan Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Peoples R China Guangdong Prov Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China

High-Resolution MR (HR-MR) images provide rich structural detail to assist physicians in clinical diagnosis and detection of lesions. However, it is arduous to acquire HR-MRI due to equipment limitations, scanning time or patient comfort. Computer-aided image post-processing approaches allow indirect acquisition of HR-MRI without the requirements described above. In this paper, we propose a MRI super-resolution reconstruction method based on an image post-processing technique. Specifically, 3D densely connected convolutional neural networks are introduced to address the problem of underutilizing the spatial information in the reconstruction of 2D slices by convolutional neural networks, which can simultaneously achieve the super- resolution reconstruction of three anatomical planes: axial, coronal and sagittal. To obtain features from different sensory fields, differently sized convolution kernels are used in the shallow feature extraction module, which promotes the robustness and reliability in the deep mapping process. Furthermore, an improved densely connected high frequency module (DBHE) is built to extract high-frequency features recovered from the deep mapping to avoid the loss of detailed information, while a hybrid attention module is utilized to boost the weights of important features. Several experiments are designed to evaluate the proposed framework, and the results suggest that it could achieve favorable reconstruction performance compared with state-of-the-art methods. In addition, the experimental results on other datasets also show the proposed framework's promising generalization performance.

关键词： CNN MRI encoder-decoder Attention

来源：评论

学校读者我要写书评

暂无评论

MSPFusion: A feature transformer for multidimensional spectral-polarization image fusion

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 275卷

作者： Tong, Geng Yao, Xinling Li, Ben Fu, Jiaye Wang, Yan Hao, Jia Karim, Shahid Yu, Yiting Northwestern Polytech Univ Ningbo Inst Coll Mech Engn Xian 710072 Peoples R China Northwestern Polytech Univ Key Lab Micro Nano Syst Aerosp Minist Educ Shaanxi Prov Key Lab Micro & Nano Electromech Syst Xian 710072 Peoples R China Northwestern Polytech Univ Shenzhen Res & Dev Inst Shenzhen 518057 Peoples R China Xian Polytech Univ Coll Comp Sci & Engn Xian 710021 Peoples R China

Spectral images capture reflection characteristics, texture, and spatial details, while polarimetric images provide insights into surface roughness, morphology, and material structure. Fusing these complementary sensing modalities overcomes the limitations of individual perception techniques, offering a richer understanding of the scene. However, traditional fusion methods are typically designed for dual-modal inputs and lack robustness when handling multimodal data. To address this, we propose MSPFusion, a novel feature transformer network for multidimensional spectral-polarization image fusion. Our approach leverages a Feature Multi-head Self- attention (F-MSA) mechanism in the encoder to enhance feature extraction and introduces an entropy-based fusion layer to adaptively integrate spectral and polarization information by maximizing information content. The F-MSA decoder further refines the fused features to produce high-quality integration and visualization of spectral-polarization data. We constructed a hyperspectral-polarization dataset, NWPU-SP, to validate our method. Experimental results show that MSPFusion achieves state-of-the-art performance, ranking first in the following metrics, i.e., entropy (EN), information (MI), standard deviation (SD), quality of saliency (QS), and quality of gradient (QG). All these metrics show a better preservation of information, along with improved clarity and contrast in the fusion results of our proposed method. Additionally, MSPFusion demonstrates strong robustness in infrared-visible image fusion tasks, proving its adaptability across various scenarios. The source code and NWPU-SP dataset are available at https://***/tgg-77/MSPFusion.

关键词： Image fusion encoder-decoder Transformer Spectral-polarization image

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：