检索结果-内蒙古大学图书馆

A Global Visual Information Intervention Model for Medical Visual Question Answering

computers in Biology and Medicine 2025年第PT A期192卷 110195-110195页

作者： Peng, Peixi Fan, Wanshu Shen, Yue Yang, Xin Zhou, Dongsheng National and Local Joint Engineering Laboratory of Computer-Aided Design School of Software Engineering Dalian University Dalian116622 China School of Computer Science and Technology Dalian University of Technology Dalian116024 China

Medical Visual Question Answering (Med-VQA) aims to furnish precise responses to clinical queries related to medical imagery. While its transformative potential in healthcare is undeniable, current solutions remain nascent and are yet to see widespread clinical adoption. Med-VQA presents heightened complexities compared to standard visual question answering (VQA) tasks due to the myriad of clinical scenarios and the scarcity of labeled medical imagery. This often culminates in language biases and overfitting vulnerabilities. In light of these challenges, this study introduces Global Visual Information Intervention (GVII), an innovative Med-VQA model designed to mitigate language biases and improve model generalizability. GVII is centered on two key branches: the Global Visual Information Branch (GVIB), which extracts and filters holistic visual data to amplify the image's contribution and reduce question dominance, and the Forward Compensation Branch (FCB), which refines multimodal features to counterbalance disruptions introduced by GVIB. These branches work in tandem to enhance predictive accuracy and robustness. Furthermore, a multi-branch fusion mechanism ensures cohesive integration of features and losses across the model. Experimental results demonstrate that the proposed model outperforms existing state-of-the-art models, achieving a 2.6% improvement in accuracy on the PathVQA dataset. In conclusion, the GVII-based Med-VQA model not only successfully mitigates prevalent language biases and overfitting issues but also significantly improves diagnostic precision, offering a considerable stride toward robust, clinically applicable VQA systems. © 2025

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

CNsum:Automatic Summarization for Chinese News Text

arXiv

引用

arXiv 2025年

作者： Zhao, Yu Huang, Songping Zhou, Dongsheng Ding, Zhaoyun Wang, Fei Nian, Aixin Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha410000 China National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian116000 China

Obtaining valuable information from massive data efficiently has become our research goal in the era of Big Data. Text summarization technology has been continuously developed to meet this demand. Recent work has also shown that transformer-based pre-trained language models have achieved great success on various tasks in Natural Language Processing (NLP). Aiming at the problem of Chinese news text summary generation and the application of Transformer structure on Chinese, this paper proposes a Chinese news text summarization model (CNsum) based on Transformer structure, and tests it on Chinese datasets such as THUCNews. The results of the conducted experiments show that CNsum achieves better ROUGE score than the baseline models, which verifies the outperformance of the model. © 2025, CC BY.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Iterative Optimal Attention and local Model for Single Image Rain Streak Removal

arXiv

引用

arXiv 2025年

作者： Li, Xiangyu Fan, Wanshu Shen, Yue Wang, Cong Wang, Wei Yang, Xin Zhang, Qiang Zhou, Dongsheng National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian China Department of Computing The Hong Kong Polytechnic University Hong Kong School of Cyber Science and Technology Sun Yat-Sen University Shenzhen China School of Computer Science and Technology Dalian University of Technology Dalian China National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University School of Computer Science and Technology Dalian University of Technology Dalian China

High-fidelity imaging is crucial for the successful safety supervision and intelligent deployment of vision-based measurement systems (VBMS). It ensures high-quality imaging in VBMS, which is fundamental for reliable visual measurement and analysis. However, imaging quality can be significantly impaired by adverse weather conditions, particularly rain, leading to blurred images and reduced contrast. Such impairments increase the risk of inaccurate evaluations and misinterpretations in VBMS. To address these limitations, we propose an Expectation Maximization Reconstruction Transformer (EMResformer) for single image rain streak removal. The EMResformer retains the key self-attention values for feature aggregation, enhancing local features to produce superior image reconstruction. Specifically, we propose an Expectation Maximization Block seamlessly integrated into the single image rain streak removal network, enhancing its ability to eliminate superfluous information and restore a cleaner background image. Additionally, to further enhance local information for improved detail rendition, we introduce a local Model Residual Block, which integrates two local model blocks along with a sequence of convolutions and activation functions. This integration synergistically facilitates the extraction of more pertinent features for enhanced single image rain streak removal. Extensive experiments validate that our proposed EMResformer surpasses current state-of-the-art single image rain streak removal methods on both synthetic and real-world datasets, achieving an improved balance between model complexity and single image deraining performance. Furthermore, we evaluate the effectiveness of our method in VBMS scenarios, demonstrating that high-quality imaging significantly improves the accuracy and reliability of VBMS tasks. Codes are at https://***/ghfkahfk/EMResformer. Copyright © 2025, The Authors. All rights reserved.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Semantic-Guided Global-local Collaborative Networks for Lightweight Image Super-Resolution

arXiv

引用

arXiv 2025年

作者： Fan, Wanshu Wang, Yue Wang, Cong Zhang, Yunzhe Wang, Wei Zhou, Dongsheng The National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian China Hong Kong School of Cyber Science and Technology Sun Yat-Sen University Shen Zhen China

Single-Image Super-Resolution (SISR) plays a pivotal role in enhancing the accuracy and reliability of measurement systems, which are integral to various vision-based instrumentation and measurement applications. These systems often require clear and detailed images for precise object detection and recognition. However, images captured by visual measurement tools frequently suffer from degradation, including blurring and loss of detail, which can impede measurement accuracy. As a potential remedy, we in this paper propose a Semantic-Guided Global-local Collaborative Network (SGGLC-Net) for lightweight SISR. Our SGGLC-Net leverages semantic priors extracted from a pre-trained model to guide the super-resolution process, enhancing image detail quality effectively. Specifically, we propose a Semantic Guidance Module that seamlessly integrates the semantic priors into the super-resolution network, enabling the network to more adeptly capture and utilize semantic priors, thereby enhancing image details. To further explore both local and non-local interactions for improved detail rendition, we propose a Global-local Collaborative Module, which features three Global and local Detail Enhancement Modules, as well as a Hybrid Attention Mechanism to work together to efficiently learn more useful features. Our extensive experiments show that SGGLC-Net achieves competitive PSNR and SSIM values across multiple benchmark datasets, demonstrating higher performance with the multi-adds reduction of 12.81G compared to state-of-the-art lightweight super-resolution approaches. These improvements underscore the potential of our approach to enhance the precision and effectiveness of visual measurement systems. Codes are at https://***/fanamber831/SGGLC-Net. © 2025, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

3D Human Pose Estimation Using Two-Stream Architecture with joint Training

引用

computer Modeling in engineering & Sciences 2023年第10期137卷 607-629页

作者： Jian Kang Wanshu Fan Yijing Li Rui Liu Dongsheng Zhou National and Local Joint Engineering Laboratory of Computer Aided Design School of Software EngineeringDalian UniversityDalian116622China Dalian Maritime University Dalian116023China

With the advancement of image sensing technology, estimating 3Dhuman pose frommonocular video has becomea hot research topic in computer vision. 3D human pose estimation is an essential prerequisite for subsequentaction analysis and understanding. It empowers a wide spectrum of potential applications in various areas, suchas intelligent transportation, human-computer interaction, and medical rehabilitation. Currently, some methodsfor 3D human pose estimation in monocular video employ temporal convolutional network (TCN) to extractinter-frame feature relationships, but the majority of them suffer from insufficient inter-frame feature relationshipextractions. In this paper, we decompose the 3D joint location regression into the bone direction and length, wepropose the TCG, a temporal convolutional network incorporating Gaussian error linear units (GELU), to solvebone direction. It enablesmore inter-frame features to be captured andmakes the utmost of the feature relationshipsbetween data. Furthermore, we adopt kinematic structural information to solve bone length enhancing the use ofintra-frame joint features. Finally, we design a loss function for joint training of the bone direction estimationnetwork with the bone length estimation network. The proposed method has extensively experimented on thepublic benchmark dataset Human3.6M. Both quantitative and qualitative experimental results showed that theproposed method can achieve more accurate 3D human pose estimations.

关键词： 3D human pose improved TCN GELU kinematic structure

来源：评论

学校读者我要写书评

暂无评论

FDC: Feature Dropout Consistency for unsupervised domain adaptation semantic segmentation

引用

Neural Networks 2025年 189卷 107527页

作者： Rao, Chaoyu Fan, Wanshu Wang, Cong Yang, Xin Wei, Xiaopeng Zhou, Dongsheng National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University China Department of Computing The Hong Kong Polytechnic University Hong Kong School of Computer Science and Technology Dalian University of Technology China

In Unsupervised Domain Adaptation Semantic Segmentation (UDASS), while self-training techniques have become one of the most effective methods to date, the absence of target labels makes models susceptible to overfitting. To address this problem, consistency techniques regularize the model by perturbing the target domain and enforcing consistent pixel predictions before and after the perturbation. Consistency techniques are based on the idea that a well-performing model should yield consistent predictions for the target data stream before and after perturbations. In this paper, we introduce the Feature Dropout Consistency (FDC) module, a novel approach that instigates perturbations at the feature level. This is achieved by implementing random feature dropout between the encoder and decoder of the student network. Subsequently, a feature dropout consistency loss is applied to minimize discrepancies in predictions between the perturbed student network and its teacher counterpart. Notably, FDC seamlessly integrates with existing self-training methodologies and, when paired with input perturbation, delves into an even broader perturbation spectrum. Through rigorous experimentation in standard UDA settings — training with synthetic labeled and real unlabeled data — FDC consistently outperforms baseline models, establishing new benchmarks on GTAV → Cityscapes and SYNTHIA → Cityscapes. © 2025

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

ER-Net:Efficient Recalibration Network for Multi-ViewMulti-Person 3D Pose Estimation

引用

computer Modeling in engineering & Sciences 2023年第8期136卷 2093-2109页

作者： Mi Zhou Rui Liu Pengfei Yi Dongsheng Zhou National and Local Joint Engineering Laboratory of Computer Aided Design School of Software EngineeringDalian UniversityDalian116622China School of Computer Science and Technology Dalian University of TechnologyDalian116024China

Multi-view multi-person 3D human pose estimation is a hot topic in the field of human pose estimation due to its wide range of application *** the introduction of end-to-end direct regression methods,the field has entered a new stage of ***,the regression results of joints that are more heavily influenced by external factors are not accurate enough even for the optimal *** this paper,we propose an effective feature recalibration module based on the channel attention mechanism and a relative optimal calibration strategy,which is applied to themulti-viewmulti-person 3D human pose estimation task to achieve improved detection accuracy for joints that are more severely affected by external ***,it achieves relative optimal weight adjustment of joint feature information through the recalibration module and strategy,which enables the model to learn the dependencies between joints and the dependencies between people and their corresponding *** call this method as the Efficient Recalibration Network(ER-Net).Finally,experiments were conducted on two benchmark datasets for this task,Campus and Shelf,in which the PCP reached 97.3% and 98.3%,respectively.

关键词： Multi-view multi-person pose estimation attention mechanism computer vision

来源：评论

学校读者我要写书评

暂无评论

DETG: Dual encoding document level relation extraction based on tree graph 7

DETG: Dual encoding document level relation extraction based...

引用

7th International Conference on computer Information Science and Application Technology, CISAT 2024

作者： Li, Jiaxing Zhong, Zhaoqian Dalian University National and Local Joint Engineering Laboratory of Computer Aided Design Dalian China

ISBN: (纸本)9798350375107

In recent years, graph-based and sequence-based document-level relation extraction models have attracted much attention. However, when performing document-level relation extraction tasks, traditional graph-based models struggle to address the overfitting issue of graph convolutional networks when analyzing document information, and sequence-based models may not effectively capture all document features. To address the above problems, we propose a document level relation extraction model based on dendrogram with dual encoders. The model uses dual encoders to extract document features of various granularities to construct a dendrogram structure. Experimental results on the public dataset DocRED show that the performance of the proposed model is significantly improved compared to other models that solely rely on graph structure or sequence structure. © 2024 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

3D Human Pose Estimation via Graph Extended Spatio-Temporal Convolutional Network 9

3D Human Pose Estimation via Graph Extended Spatio-Temporal ...

引用

9th International Conference on Virtual Reality, ICVR 2023

作者： Jia, Yanhui Fan, Wanshu Zhou, Dongsheng Zhang, Qiang Dalian University National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian China

ISBN: (纸本)9798350345810

3D human pose estimation is an important premise for human behavior analysis and understanding, which has a wide range of applications in intelligent transportation, human-computer interaction, and animation production. Most existing works focus on extracting the feature relationship between frames by combining spatio-temporal information to reduce the error of attitude reconstruction. However, the majority of them often suffer from insufficient joint correlation characteristics. To address this problem, we propose a Graph Expand Spatiotemporal Convolutional Network, named GESC-Net, to improve the limitation of extracting human spatial structure features. To better enrich the feature of extracting local information, we develop a learnable symmetric connection (LSC) block in the spatial structure. Moreover, a CbAttantion block is also designed to obtain a larger view of the acquisition of global structure and get more effective features. We evaluate our approach on two standard benchmark datasets: Human3.6M and HumanEva-I. The quantitative and qualitative evaluation results demonstrate that the GESC-Net can achieve better 3D human posture estimation than existing state-of-the-art methods. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Dual modality prompt learning for visual question-grounded answering in robotic surgery

引用

Visual Computing for Industry,Biomedicine,and Art 2024年第1期7卷 316-328页

作者： Yue Zhang Wanshu Fan Peixi Peng Xin Yang Dongsheng Zhou Xiaopeng Wei National and Local Joint Engineering Laboratory of Computer Aided Design School of Software EngineeringDalian UniversityDalian 116622LiaoningChina School of Computer Science and Technology Dalian University of TechnologyDalian 116081LiaoningChina

With recent advancements in robotic surgery,notable strides have been made in visual question answering(VQA).Existing VQA systems typically generate textual answers to questions but fail to indicate the location of the relevant content within the *** limitation restricts the interpretative capacity of the VQA models and their abil-ity to explore specific image *** address this issue,this study proposes a grounded VQA model for robotic surgery,capable of localizing a specific region during answer *** inspiration from prompt learning in language models,a dual-modality prompt model was developed to enhance precise multimodal information ***,two complementary prompters were introduced to effectively integrate visual and textual prompts into the encoding process of the model.A visual complementary prompter merges visual prompt knowl-edge with visual information features to guide accurate *** textual complementary prompter aligns vis-ual information with textual prompt knowledge and textual information,guiding textual information towards a more accurate inference of the ***,a multiple iterative fusion strategy was adopted for comprehensive answer reasoning,to ensure high-quality generation of textual and grounded *** experimental results vali-date the effectiveness of the model,demonstrating its superiority over existing methods on the EndoVis-18 and End-oVis-17 datasets.

关键词： Prompt learning Visual prompt Textual prompt Grounding-answering Visual question answering

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：