检索结果-内蒙古大学图书馆

A position-enhanced attention framework for video deblurring

DIGITAL SIGNAL PROCESSING 2025年 161卷

作者： Lia, Zhi Zhou, Yangfan Tao, Fazhan Li, Jiadong Henan Univ Sci & Technol Coll Informat Engn Luoyang Peoples R China Chinese Acad Sci Suzhou Inst Nanotech & Nanob Suzhou Peoples R China Guangdong Inst Semicond Micronano Mfg Technol Foshan Peoples R China Henan Key Lab Sensing Technol & Syst Internet Thin Luoyang Peoples R China

Video deblurring holds significant importance for the field of motion photography such as hand-held photography, UAV aerial photography, and vehicle video. However, the non-uniform dynamic blur brings great challenges to the existing methods to realize video deblurring in high dynamic scenes. To address this challenge, we innovatively proposes a video deblurring method that precisely captures and compensates for complex spatial- temporal blur variations caused by intense motion and dynamic scene changes. The proposed method presents a Position-Enhanced Channel Attention Block (PEAB), which integrates channel information and significant positional information. Moreover, this block is embedded within an encoder-decoder network, enabling robust multi-scale feature modeling and enhancing deblurring performance across various motion-induced blurs. Additionally, the PEAB within the spatial-temporal shift module improves multi-frame information aggregation, reduces computational overhead, and enhances overall restoration quality. To further refine the process, we introduce an image optimization module based on the transformer architecture, which simplifies feature processing while maintaining high deblurring accuracy. Experimental results show that, compared to existing methods, the proposed approach achieves excellent performance while maintaining a remarkable balance between precision and efficiency on the GOPRO and DVD datasets. It also demonstrates strong generalization ability on the RBVD dataset.

关键词： Video restoration Non-uniform dynamic blurring Attention mechanism encoder-decoder framework Transformer

来源：评论

学校读者我要写书评

暂无评论

Micro-KTNet: Microstructure knowledge transfer learning for fiber masterbatch agglomeration recognition

引用

JOURNAL OF INDUSTRIAL TEXTILES 2025年 55卷

作者： Zhang, Xianqi Wei, Bing Hao, Kuangrong Gao, Lei Xie, Ruimin Wang, Huaping Donghua Univ Coll Informat Sci & Technol Minist Educ Engn Res Ctr Digitized Text & Apparel Technol Shanghai Peoples R China Australias Commonwealth Sci & Ind Res Org CSIRO Waite Campus Urrbrae SA Australia Donghua Univ Coll Mat Sci & Engn State Key Lab Modificat Chem Fibers & Polymer Mat Shanghai Peoples R China

Fiber masterbatch production suffers from inherent agglomeration effect of high-concentration color masterbatches, negatively impacting color uniformity, particle dispersion, and thermal stability in fiber masterbatch, and ultimately the quality of fiber products. However, accurately recognizing and classifying the agglomeration in scanning electron microscopy (SEM) images remain a challenge due to the complexity of agglomeration status, difficulty in distinguishing micro-size agglomeration, and limited data availability. To address this challenge, this paper proposes a novel microstructure recognition architecture, named Micro-KTNet, which is designed for segmenting SEM images of fiber masterbatch aggregation. First, Micro-KTNet leverages transferable microstructural features to initialize the proposed network, mitigating the impact of limited data. Then, to handle multi-scale features in the microstructure, an encoding-decoding structure is constructed and skip connections are used to transfer the output features of the encoding layer. Finally, the decoder incorporates a novel attention module to effectively process both global and local features. To evaluate Micro-KTNet, a unique fiber masterbatch SEM database is built as the benchmark for micro-size agglomeration recognition. Experimental results indicate that Micro-KTNet surpasses existing state-of-the-art methods and improves the recognition precision from 75. 37% to 87. 04%.

关键词： Fiber masterbatch agglomeration effects encoder-decoder framework transfer learning microstructure segmentation attention module

来源：评论

学校读者我要写书评

暂无评论

Triple confidence-aware encoder-decoder model for commonsense knowledge graph completion

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2025年第3期16卷 2073-2091页

作者： Chen, Hongzhi Zhang, Fu Li, Qinghui Li, Xiang Ding, Yifan Zhang, Daqing Cheng, Jingwei Wang, Xing Northeastern Univ Sch Comp Sci & Engn Shenyang 110169 Peoples R China Linyi Univ Sch Informat Sci & Engn Linyi 276005 Peoples R China

Commonsense knowledge is essential for performing inference and retrieval in many artificial intelligence applications, including those in natural language processing and expert system. However, a large amount of valuable commonsense knowledge exists implicitly or is missing in commonsense knowledge graphs (KGs). In this case, commonsense knowledge graph completion (CKGC) is proposed to solve this incomplete problem by inferring missing parts of commonsense triples, e.g., (?, HasPrerequisite, turn computer on) or (get onto web, HasPrerequisite, ?). Some existing methods attempt to learn as much entity semantic information as possible by exploiting the structural and semantic context of entities for improving the performance of CKGC. However, we found that the existing models only pay attention to entities and relations of the commonsense triples and ignore the important confidence (weight) information related to the commonsense triples. In this paper we innovatively introduce commonsense triple confidence into CKGC and propose a confidence-aware encoder-decoder CKGC model. In the encoding stage, we propose a method to incorporate the commonsense triple confidence into RGCN (relational graph convolutional network), so that the encoder can learn a more accurate semantic representation of a triple by considering the triple confidence constraints. Moreover, the commonsense KGs are usually sparse, because there are a large number of entities with an in-degree of 1 in the commonsense triples. Therefore, we propose to add a new relation (called similar edge) between two similar entities for compensating the sparsity of commonsense KGs. In the decoding stage, considering that entities in the commonsense triples are sentence-level entities (e.g., the tail entity turn computer on mentioned above), we propose a joint decoding model by fusing effectively the existing InteractE and ConvTransE models. Experiments show that our new model achieves better performance compared to the

关键词： Commonsense knowledge graph Commonsense knowledge graph completion (CKGC) Triple confidence encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

A chest imaging diagnosis report generation method based on dual-channel transmodal memory network

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 100卷

作者： Dong, Zilong Lian, Jing Zhang, Xiangzi Zhang, Bingtao Liu, Jizhao Zhang, Jiajun Zhang, Huaikun Lanzhou Jiaotong Univ Sch Elect & Informat Engn Lanzhou 730070 Gansu Peoples R China Lanzhou Univ Sch Informat Sci & Engn Lanzhou 730000 Gansu Peoples R China Northwest Normal Univ Sch Psychol Lanzhou 730070 Gansu Peoples R China

Medical imaging is critical for clinical diagnosis. In the past few years, medical imaging data has been steadily growing at an annual rate of 30%, while the annual growth rate in the number of radiologists is only 4. 1%. The traditional manual methods of chest imaging reports result in high information load and workload with low relevance of images and texts. Here we propose a chest CT imaging diagnosis report generation network to effectively integrate image and text feature information, improve the relevance of the cross-modal networks and automatically generate imaging diagnosis reports. The network includes three major modules: a novel ResNetII for information extraction, an image-text dual-channel transmodal memory network (DCTMN), and a dual-channel decoder module combined with LSTM gate. We validate the effectiveness of the proposed network on the IU X-ray and the MIMIC-CXR datasets. Our analysis indicates that the proposed method can strengthen the relationship between chest imaging and text information, ultimately achieving the automatic generation of chest imaging diagnosis reports.

关键词： Automatic report generation Cross-modal network encoder-decoder framework LSTM gate IU X-ray and MIMIC-CXR

来源：评论

学校读者我要写书评

暂无评论

An efficient encoder-decoder network for the capacitated vehicle routing problem

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 278卷

作者： Luo, Jia Li, Chaofeng Ningbo Univ Technol Sch Econ & Management Ningbo 315211 Zhejiang Peoples R China Shanghai Maritime Univ Inst Logist Sci & Engn Shanghai 200135 Peoples R China

The capacitated vehicle routing problem (CVRP) is of great importance to intelligent transportation systems. In recent, deep reinforcement learning (DRL) approaches have shown great potential in solving the CVRP efficiently. Specifically, encoder-decoder frameworks are trained via reinforcement learning with different schemes to construct solutions incrementally. As the total customer demands and remaining vehicle capacity are dynamic with time steps, it is still a challenge for this kind of methods to obtain optimal solutions. In this work, we develop an efficient encoder-decoder framework, termed the residual graph convolutional encoder and multiple attention-based decoders (RGCMA), which is trained by a reinforcement learning method with an elite baseline. The encoder produces powerful node representations while being dedicated to aggregating neighborhood features by a fitted dense residual edge and node features updating block. Compared to the popular single decoder strategy, our multiple decoders mechanism incrementally constructs a variety of solutions for any CVRP instance, which diversifies solution space, and eventually improves the solution quality. Extensive experiments demonstrate that RGCMA performs competitively with existing methods on variety CVRP datasets. RGCMA narrows the gap to LKH solver on four benchmark tasks, and its run time is less than 1 s. It also exhibits good generalization ability on large-scale tasks, well-known CVRPLIB dataset and real-world Jingdong Logistics distribution task.

关键词： Capacitated vehicle routing problem Deep reinforcement learning encoder-decoder framework Graph convolutional neural network Attention-based mechanism

来源：评论

学校读者我要写书评

暂无评论

DiffMamba: semantic diffusion guided feature modeling network for semantic segmentation of remote sensing images

引用

GISCIENCE & REMOTE SENSING 2025年第1期62卷

作者： Wang, Zhen Xu, Nan You, Zhuhong Zhang, Shanwen Xijing Univ Sch Elect Informat Xian Shaanxi Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian Shaanxi Peoples R China Hohai Univ Sch Earth Sci & Engn Nanjing Jiangsu Peoples R China

With the rapid development of remote sensing technology, the application scope of high-resolution remote sensing images (HR-RSIs) has been continuously expanding. The emergence of convolutional neural networks and Transformer models has significantly enhanced the accuracy of semantic segmentation. However, these methods primarily focus on local feature extraction and long-range dependency modeling of global information, neglecting the spatial correlation of local features, which leads to poor segmentation of small-scale regions. To address this issue, based on Diffusion Model and State Space Model (SSM), we propose a semantic diffusion guided feature modeling network (DiffMamba) for HR-RSI semantic segmentation. DiffMamba uses a hybrid CNNs-Transformer as the encoder structure, and is equipped with the efficient phase sensing module (EPSM), the multi-view transformer module (MVTrans), the semantic diffusion alignment module (SDAM), and the coordinate state space model (CAMamba). EPSM focuses on enhancing local feature representation in the channel dimension, using the phase information of object region features to improve local information interaction and filter out clutter noise interference. MVTrans can observe the spatial location information of the object region from various perspectives to obtain refined global context details. SDAM utilizes the diffusion propagation process to fuse local and global information, alleviating the feature redundancy caused by semantic information differences. CAMamba employs state space transformation to construct the correlation of enhanced local features, and guides the model to achieve feature decoding to obtain refined semantic segmentation results. Extensive experiments on the widely used ISPRS 2-D Semantic Labeling dataset and the 15-Class Gaofen Image dataset confirm the superior efficiency of DiffMamba over several state-of-the-art methods.

关键词： Diffusion model state space model (SSM) encoder-decoder framework remote sensing images semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Visuals to Text:A Comprehensive Review on Automatic Image Captioning

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1339-1365页

作者： Yue Ming Nannan Hu Chunxiao Fan Fan Feng Jiangwan Zhou Hui Yu Beijing University of Posts and Telecommunications Beijing 100876China School of Creative Technologies University of PortsmouthPortsmouth PO12DJUK

Image captioning refers to automatic generation of descriptive texts according to the visual content of *** is a technique integrating multiple disciplines including the computer vision(CV),natural language processing(NLP)and artificial *** recent years,substantial research efforts have been devoted to generate image caption with impressive *** summarize the recent advances in image captioning,we present a comprehensive review on image captioning,covering both traditional methods and recent deep learning-based ***,we first briefly review the early traditional works based on the retrieval and *** deep learning-based image captioning researches are focused,which is categorized into the encoder-decoder framework,attention mechanism and training strategies on the basis of model structures and training manners for a detailed *** that,we summarize the publicly available datasets,evaluation metrics and those proposed for specific requirements,and then compare the state of the art methods on the MS COCO ***,we provide some discussions on open challenges and future research directions.

关键词： Artificial intelligence attention mechanism encoder-decoder framework image captioning multi-modal understanding training strategies

来源：评论

学校读者我要写书评

暂无评论

High-Order Interaction Learning for Image Captioning

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第7期32卷 4417-4430页

作者： Wang, Yanhui Xu, Ning Liu, An-An Li, Wenhui Zhang, Yongdong Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230052 Peoples R China

Image captioning aims at understanding various semantic concepts (e.g., objects and relationships) from an image and integrating them in a sentence-level description. Hence, it is necessary to learn the interaction among these concepts. If we define the context of the interaction to be involved in the subject-predicate-object triplet, most current methods only focus on the single triplet for the first-order interaction to generate sentences. Intuitively, we humans are able to perceive the high-order interaction among concepts from two or more triplets to describe an image. For example, when we see the triplets man-cutting-sandwich and man-with-knife, it is natural to integrate and predict the sentence man cutting sandwich with knife. This depends on the high-order interaction between cutting and knife in different triplets. Therefore, exploiting high-order interaction is expected to benefit image captioning and focus on reasoning. In this paper, we introduce the novel high-order interaction learning method over detected objects and relationships for image captioning under the umbrella of the encoder-decoder framework. We first extract a set of object and relationship features in an image. During the encoding stage, the interactive refining network is proposed to learn high-order representations by modeling intra- and inter-object feature interaction in the self-attention fashion. During the decoding stage, the interactive fusion network is proposed to integrate object and relationship information by strengthening their high-order interaction based on language context for sentence generation. In this way, we learn the object-relationship dependencies in different stages, which can provide abundant cues for both visual understanding and caption generation. Extensive experiments show that the proposed method can achieve competitive performances against the state-of-the-art methods on MSCOCO dataset. Additional ablation studies further validate its effectiveness.

关键词： Visualization Semantics Feature extraction Decoding Task analysis Ions Encoding Image captioning high-order interaction encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Keyphrase Generation Based on Self-Attention Mechanism

引用

Computers, Materials & Continua 2019年第8期61卷 569-581页

作者： Kehua Yang Yaodong Wang Wei Zhang Jiqing Yao Yuquan Le College of Computer Science and Electronic Engineering and Key Laboratory for Embedded and Network Computing of Hunan Province Hunan UniversityChangsha410082China Oath Verizon Company ManhattanNew York10007USA

Keyphrase greatly provides summarized and valuable *** information can help us not only understand text semantics,but also organize and retrieve text content *** task of automatically generating it has received considerable attention in recent *** the previous studies,we can see many workable solutions for obtaining *** method is to divide the content to be summarized into multiple blocks of text,then we rank and select the most important *** disadvantage of this method is that it cannot identify keyphrase that does not include in the text,let alone get the real semantic meaning hidden in the *** approach uses recurrent neural networks to generate keyphrases from the semantic aspects of the text,but the inherently sequential nature precludes parallelization within training examples,and distances have limitations on context *** works have demonstrated the benefits of the self-attention mechanism,which can learn global text dependency features and can be *** by the above observation,we propose a keyphrase generation model,which is based entirely on the self-attention *** is an encoder-decoder model that can make up the above disadvantage *** addition,we also consider the semantic similarity between keyphrases,and add semantic similarity processing module into the *** proposed model,which is demonstrated by empirical analysis on five datasets,can achieve competitive performance compared to baseline methods.

关键词： Keyphrase generation self-attention mechanism encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Video captioning: a review of theory, techniques and practices

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第25期81卷 35619-35653页

作者： Jain, Vanita Al-Turjman, Fadi Chaudhary, Gopal Nayar, Devang Gupta, Varun Kumar, Aayush Bharati Vidyapeeths Coll Engn New Delhi India Near East Univ Nicosia Cyprus

In today's world, video captioning is extensively used in various applications for specially-abled and, more specifically, visually abled persons. With advancements in technology for object detection and natural processing, there has been an instant surge infusing the above mainstream tasks. One such example of this fusion resulted in the generation of Image captions when an input image is fed to the system, and it gives a short description of what is present in the image. This fusion pertained to images and was further moved to be implemented on the Videos, with some tweaking in the current methods. This paper presents the survey of the state of art techniques of various video captioning methods. There have been many inputs provided by people worldwide in this domain;thus, there was a need to compile, study and analyze all the results and present that in a comprehensive study, which we have done in this paper. The comparison of various video captioning methods on the distinct dataset was evaluated on different parameters, which were most common and mainly used for image and video analysis. This review was done for methods used from the year 2015-2019 (year by year). The most commonly used dataset and evaluation method are also pictorially represented in a bar graph and scatter plot for each year for the respective evaluation parameter. Though a lot of analysis and research has been done on video captioning, our survey shows many problems.

关键词： Video captioning Natural language processing CNN RNN encoder-decoder framework

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：