检索结果-内蒙古大学图书馆

BENet: bi-directional enhanced network for image captioning

MULTIMEDIA SYSTEMS 2024年第1期30卷 48-48页

作者： Yan, Peixin Li, Zuoyong Hu, Rong Cao, Xinrong Fujian Univ Technol Sch Comp Sci & Math Fujian Prov Key Lab Big Data Min & Applicat Fuzhou 350118 Peoples R China Minjiang Univ Coll Comp & Control Engn Fujian Prov Key Lab Informat Proc & Intelligent Co Fuzhou 350121 Peoples R China

Transformer-based models have been used in image captioning to generate a natural language text for describing a given image accurately. In this paper, we propose a bi-directional enhanced network, which strengthens the correlation between image features and text features by the memory bank to improve the performance of the transformer-based encoder-decoder framework for image captioning. In addition, we fine-tune the connection method in the encoder to obtain rich image features. Specifically, during training, the memory bank is first used to store the correspondences between images and annotated texts in the dataset as additional information of image features. After processing through the encoder, we feed the visual features composed of image features and the additional information in the memory bank into the decoder to generate better caption. Subsequently, we utilize a decoder-like architecture to reconstruct visual features from the generated caption. Finally, we calculate the similarity loss between the reconstructed features and the visual features to optimize the encoder. Extensive experiments on the MSCOCO benchmark demonstrate that the proposed method has shown promising results on both the Karpathy test split and the online test server, providing evidence of its effectiveness.

关键词： Image captioning Transformer Bi-directional enhanced network Memory bank Reconstruct

来源：评论

学校读者我要写书评

暂无评论

Splitting the backbone: A novel hierarchical method for assessing light field image quality

引用

OPTICS AND LASERS IN ENGINEERING 2024年 178卷

作者： Guo, Wenzhong Wang, Hanling Ke, Xiao Fuzhou Univ Coll Comp & Data Sci Fujian Prov Key Lab Networking Comp & Intelligent Fuzhou 350116 Fujian Peoples R China Fuzhou Univ Engn Res Ctr Big Data Intelligence Minist Educ Fuzhou 350116 Peoples R China

The rising popularity of light field imaging underscores the pivotal role of image quality in user experience. However, evaluating the quality of light field images presents significant challenges owing to their highdimensional nature. Current quality assessment methods for light field images predominantly rely on machine learning or statistical analysis, often overlooking the interdependence among pixels. To overcome this limitation, we propose an innovative approach that employs a universal backbone network and introduces a dual-task framework for feature extraction. Specifically, we integrate a staged "primary-secondary" hierarchical evaluation mode into the universal backbone networks, enabling accurate quality score inference while preserving the intrinsic information of the original image. Our proposed approach reduces inference time by over 75% compared to existing methods, simultaneously achieving state-of-the-art results in terms of evaluation metrics. By harnessing the efficiency of neural networks, our framework offers an effective solution for the quality assessment of light field images, providing superior accuracy and speed compared to current methodologies.

关键词： Light field images Image quality assessment Deep learning Multitasking mode

来源：评论

学校读者我要写书评

暂无评论

PRNet: Parallel Reinforcement Network for two-view correspondence learning

引用

KNOWLEDGE-BASED SYSTEMS 2025年 310卷

作者： Kang, Zheng Lai, Taotao Li, Zuoyong Wei, Lifang Chen, Riqing Minjiang Univ Sch Comp & Big Data Fujian Prov Key Lab Informat Proc & Intelligent Co Fuzhou 350121 Peoples R China Fujian Agr & Forestry Univ Coll Comp & Informat Sci Fuzhou 350002 Peoples R China

Two-view correspondence learning is a fundamental task in computer vision for locating the same object across two different images, and its essence lies in capturing the context from the images. Recent studies employ the standard Convolutional Neural Network (CNN) as the core architecture to capture the context. However, the inherent nature of the CNN's local receptive field and pooling operations can result in the loss of certain semantic context. This can result in the CNN-based correspondence learning methods having an insufficient understanding of the global context, especially on image pairs including challenges like significant viewpoint changes, repetitive structures and weak textures. To address this issue and these challenges, we propose a novel correspondence learning method called Parallel Reinforcement Network (PRNet). Firstly, we design a reinforcement injection block, not only to dynamically refine feature weights by using channel attention mechanism, but also to preserve important details for alleviating over-smoothing issue by strengthening the network's capacity. Secondly, to alleviate the potential issue of overlooking the weak local context by CNN, we propose a parallel fusion block to integrate both shallow and deep features, preserving local details and enhancing global context. We evaluate the performance of the proposed PRNet on an outlier rejection task and a relative pose estimation task. The experimental results demonstrate the proposed PRNet exceeds several existing state-of-the-art methods in various challenging scenarios.

关键词： Two-view correspondence Channel attention mechanism Parallel fusion Pose estimation Outlier rejection

来源：评论

学校读者我要写书评

暂无评论

IceBerg: Deep Generative Modeling for Constraint Discovery and Anomaly Detection 20

IceBerg: Deep Generative Modeling for Constraint Discovery a...

引用

20th IEEE Int Symposium on Parallel and Distributed Processing with Applicat / 15th IEEE Int Conf on Social comp and Networking / 12th IEEE Int Conf on big data and Cloud comp / 12th IEEE Int Conf on Sustainable comp and Commun

作者： Hu, Wentao Jiang, Dawei Wu, Sai Chen, Ke Chen, Gang Zhejiang Univ Key Lab Big Data Intelligent Comp Zhejiang Prov Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781665464970

Automatic constraint discovery from a relational database is beneficial for domain experts in fraud detection and intelligent auditing. Its objective is to discover a set of inherent constraints underlying the database such that tuples violating them are considered anomalous. In this paper, we propose IceBerg as the first system to simultaneously detect anomalous tuples and discover the associated human-readable constraints. The backbone of IceBerg is a novel generative network, namely KD-VAE, that integrates Kernel Density estimation with Variational AutoEncoder. KD-VAE is expected to learn the distributions of normal tuples. We can perform anomalous data detection by calculating the likelihood that the tuple fits the distributions of normal tuples and abnormality interpretation by comparing the detected anomalous tuples with their generated normal *** empirically compare the proposed method with several state-of-the-art outlier detection methods on 13 real-world datasets. The results show that IceBerg outperforms its competitors in most cases, especially for complex datasets with high-dimensional features.

关键词： Deep Generative Modeling Constraint Discovery intelligent Auditing Anomaly Detection databases

来源：评论

学校读者我要写书评

暂无评论

Experimental and numerical investigation on heat transfer analysis of square slotted pin-fin heat sinks

引用

APPLIED THERMAL ENGINEERING 2024年 245卷

作者： Zhu, Chenlin Wang, Chen Qian, Lijuan Jiang, Zhitao Hu, Xiao China Jiliang Univ Key Lab Intelligent Mfg Qual Big Data Tracing & An Hangzhou 310018 Zhejiang Peoples R China Zhejiang Santian Filter Co Ltd Doctoral Innovat Stn Lishui 323700 Zhejiang Peoples R China Zhejiang Sci Tech Univ Key Lab Fluid Transmiss Technol Zhejiang Prov Hangzhou 310018 Zhejiang Peoples R China

This paper introduces two novel designs of pin -fin heat sink (PHFS), namely the inline slotted pin -fin (ISP) and the V-shaped slotted pin -fin (VSP), to address rapid heat dissipation for one central/graphics processing unit (CPU/GPU) in a single-phase liquid cooling system. Experimental and numerical investigations are conducted to observe the effect of heat transfer for non -slotted and slotted pin -fin heat sinks under different Reynolds numbers (225-720) and heating powers (90-120 W). Parameters such as average wall temperature, Nusselt number, thermal resistance, pressure drop, and hydrothermal performance factor are evaluated. comparative analyses show that the slotted pin -fin heat sinks exhibit higher Nusselt numbers ( Nu ) and lower thermal resistance ( R th ) levels than that in the non -slotted pin -fin heat sinks, particularly at lower Reynolds numbers. At the Reynolds number 225 and power of 120 W, the inline and V-shaped slotted pin -fin heat sinks experience a 13.98% and 19.69% increase in Nu and a 12.65% and 15.41% reduction in R th compared to the non -slotted one, respectively. The V-shaped slotted pin -fin heat sink achieves more than 5 degrees C reduction in the maximum wall temperature than the non -slotted one. The slotted structure reduces pressure drop losses by minimizing dead flow areas on one hand. On the other hand, the inclined slots generate vortices behind the fins, increase shear -induced mixing and thus improve the force convection cooling performance.

关键词： Slotted pin-fin heat sinks V-shaped slots Heat transfer enhancement Immersion cooling Forced convection

来源：评论

学校读者我要写书评

暂无评论

Phased Noise Enhanced Multiple Feature Discrimination Network for fabric defect detection

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 149卷

作者： Ma, Haoran Li, Zuoyong Fan, Haoyi Zheng, Xiangpan Yan, Jiaquan Hu, Rong Fujian Univ Technol Sch Comp Sci & Math Fujian Prov Key Lab Big Data Min & Applicat Fuzhou 350118 Peoples R China Minjiang Univ Sch Comp & Big Data Fujian Prov Key Lab Informat Proc & Intelligent Co Fuzhou 350121 Peoples R China Zhengzhou Univ Sch Comp & Artificial Intelligence Zhengzhou 450001 Peoples R China Minjiang Univ Coll Phys & Elect Informat Engn Fuzhou 350121 Peoples R China Wuyi Univ Key Lab Cognit Comp & Intelligent Informat Proc Fujian Educ Inst Wuyishan 354300 Peoples R China

Fabric defect detection is crucial for evaluating the quality of textile products. However, the subtlety and scarcity of fabric defects pose challenges to the task of detecting. Therefore, we propose a Phased Noise Enhanced Multiple Feature Discrimination Network, which is based on phased noise enhancement strategy and multiple feature discrimination module to improve the model's ability to identify complex and subtle flaws. Specifically, we propose the phased noise enhancement strategy in the feature space to simulate feature-level anomalies that are closer to reality. This strategy can improve the input quality of the feature reconstructor, so that helps its perception and reconstruction ability. Then, we propose the multiple feature discrimination module, which has dual feature branches to improve its ability to distinguish more complex detailed texture features. In addition, we propose a subsampling module to reduce feature redundancy and ensure efficient inference speed. Finally, we conduct extensive experiments and ablation studies on two publicly available fabric datasets, AITEX and Kaggle Fabric. The experimental results show that the proposed method achieved 92% and 100% image level metrics and 97.5% and 67.1% pixel level metrics on two datasets, respectively, which is superior to the current state-of-the-art methods. In addition, our method also demonstrated significant performance in generalization experiments.

关键词： Fabric defect detection Generative adversarial network Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

An adaptive confidence-based data revision framework for Document-level Relation Extraction

引用

INFORMATION PROCESSING & MANAGEMENT 2025年第1期62卷

作者： Jiang, Chao Liao, Jinzhi Zhao, Xiang Zeng, Daojian Dai, Jianhua Natl Univ Def Technol Lab Big Data & Decis 109 Deya Rd Changsha 410073 Peoples R China Hunan Normal Univ Hunan Prov Key Lab Intelligent Comp & Language Inf Changsha 410081 Peoples R China

Noisy annotations have become a key issue limiting Doc ument-level R elation E xtraction (DocRE). Previous research explored the problem through manual re-annotation. However, the handcrafted strategy is of low efficiency, incurs high human costs and cannot be generalized to large-scale datasets. To address the problem, we construct a confidence-based Re vision framework for D ocRE (ReD), ReD ), aiming to achieve high-quality automatic data revision. Specifically, we first introduce a denoising training module to recognize relational facts and prevent noisy annotations. Second, a confidence-based data revision module is equipped to perform adaptive data revision for long-tail distributed relational facts. After the data revision, we design an iterative training module to create a virtuous cycle, which transforms the revised data into useful training data to support further revision. By capitalizing on ReD, we propose ReD-DocRED, which consists of 101,873 revised annotated documents from DocRED. ReDDocRED has introduced 57.1% new relational facts, and concurrently, models trained on ReD-DocRED have achieved significant improvements in F1 scores, ranging from 6.35 to 16.55. The experimental results demonstrate that ReD can achieve high-quality data revision and, to some extent, replace manual labeling.

关键词： Noisy annotations Adaptive data revision Denoising training Document level Relation Extraction

来源：评论

学校读者我要写书评

暂无评论

Transition to healthier lifestyle associated with reduced risk of incident dementia and decreased hippocampal atrophy

引用

JOURNAL OF AFFECTIVE DISORDERS 2024年 349卷 552-558页

作者： Sun, Kaili Jin, Shuyi Yang, Zhenqing Li, Xueqin Li, Chenxi Zhang, Jingyun Yang, Gan Yang, Chongming Abdelrahman, Zeinab Liu, Zuyun Zhejiang Univ Key Lab Intelligent Prevent Med Zhejiang Prov Sch Med Ctr Clin Big Data & AnalytAffiliated Hosp 2 Hangzhou Zhejiang Peoples R China Zhejiang Univ Sch Med Dept Big Data Hlth Sci Sch Publ Hlth Key Lab Intelligent Prevent Med Zhejiang Prov Hangzhou 310058 Zhejiang Peoples R China Brigham Young Univ Res Support Ctr Provo UT 84602 USA Queens Univ Belfast Ctr Publ Hlth Belfast BT12 6BA Antrim North Ireland Zhejiang Univ Affiliated Hosp 2 Ctr Clin Big Data & Analyt Sch Med 866 Yuhangtang Rd Hangzhou 310058 Zhejiang Peoples R China Zhejiang Univ Dept Big Data Hlth SciSch Publ Hlth Key Lab Intelligent Prevent Med Zhejiang Prov Sch Med 866 Yuhangtang Rd Hangzhou 310058 Zhejiang Peoples R China

Background: Research has estimated the associations of lifestyle at one-time point with the risk of dementia and hippocampal volume, but the impact of lifestyle transition on dementia and hippocampal volume remains unclear. This study aims to examine the associations of lifestyle transition with the risk of dementia and hippocampal volume. Methods: Based on data from the UK Biobank, a weighted lifestyle score was constructed by incorporating six lifestyle factors. Within each baseline lifestyle group (i.e., healthy, intermediate, and unhealthy), lifestyle transition was classified into decline, maintenance, and improvement. Cox proportional hazard regression was used to estimate the association of lifestyle transition and incident dementia (N = 16,305). A multiple linear regression model was used to estimate the association between lifestyle transition and hippocampal volume (N = 5849). Results: During a median follow-up period of 8.6 years, 120 (0.7 %) dementia events were documented. Among participants with healthy baseline lifestyles, the improvement group had a lower risk of incident dementia (HR: 0.18, 95 % CI: 0.04-0.81) and a larger hippocampal volume (beta = 111.69, P = 0.026) than the decline group. Similar results were observed among participants with intermediate baseline lifestyles regarding dementia risk but not hippocampal volume. No benefits were observed in the improvement group among those with unhealthy baseline lifestyles. Limitations: A lower incidence of dementia than other cohort study and this may have resulted in an underestimation of the risk of dementia. Conclusions: Earlier transitions to healthier lifestyle were associated with reduced risk of incident dementia and decreased hippocampal atrophy.

关键词： Lifestyle transition Health behaviors Dementia Hippocampus

来源：评论

学校读者我要写书评

暂无评论

big data and artificial intelligence in cancer research

引用

TRENDS IN CANCER 2024年第2期10卷 147-160页

作者： Wu, Xifeng Li, Wenyuan Tu, Huakang Zhejiang Univ Affiliated Hosp 2 Sch Publ Hlth Sch MedCtr Clin Big Data & AnalytDept Big Data H Hangzhou Zhejiang Peoples R China Zhejiang Univ Natl Inst Data Sci Hlth & Med Hangzhou Zhejiang Peoples R China Key Lab Intelligent Prevent Med Zhejiang Prov Hangzhou Zhejiang Peoples R China Zhejiang Univ Canc Ctr Hangzhou Zhejiang Peoples R China

The field of oncology has witnessed an extraordinary surge in the application of big data and artificial intelligence (AI). AI development has made multiscale and multimodal data fusion and analysis possible. A new era of extracting information from complex big data is rapidly evolving. However, challenges related to efficient data curation, in-depth analysis, and utilization remain. We provide a comprehensive overview of the current state of the art in big data and computational analysis, highlighting key applications, challenges, and future opportunities in cancer research. By sketching the current landscape, we seek to foster a deeper understanding and facilitate the advancement of big data utilization in oncology, call for interdisciplinary collaborations, ultimately contributing to improved patient outcomes and a profound understanding of cancer.

关键词： big data artificial intelligence precision medicine cancer data fusion platform

来源：评论

学校读者我要写书评

暂无评论

TITE: A transformer-based deep reinforcement learning approach for traffic engineering in hybrid SDN with dynamic traffic

引用

FUTURE GENERATION compUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2024年 161卷 95-105页

作者： Lin, Bin Guo, Yingya Luo, Huan Ding, Mingjie Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China Fuzhou Univ Fujian Prov Key Lab Network Comp & Intelligent Inf Fuzhou Peoples R China Minist Educ Engn Res Ctr Big Data Intelligence Fuzhou Peoples R China

Hybrid Software Defined Networks (Hybrid SDNs), with a partial upgrade of legacy routers to SDN switches in traditional distributed networks, currently stand as a prevailing network architecture. Traffic Engineering (TE) in hybrid SDN requires the efficient and timely acquisition of a routing policy to adapt to dynamically changing traffic demands, which has recently become a hot topic. Ignoring the hidden relations of consecutive states and the compact representation of the network environment, previous Deep Reinforcement Learning (DRL)-based studies suffer from the convergence problem by only establishing the direct relationship between individual Traffic Matrix (TM) and routing policy. Therefore, to enhance TE performance in hybrid SDNs under dynamically changing traffic demands, we propose to integrate the Transformer model with DRL to establish the relationship between consecutive states and routing policies. The temporal characteristic among consecutive states can effectively assist DRL in solving the convergence problem. To obtain a compact and accurate description of the network environment, we propose to jointly consider TM, routing action, and reward in designing the state of the network environment. To better capture the temporal relations among consecutive states of the network environment, we design a multi-feature embedding module and achieve positional encodings in the Transformer model. The extensive experiments demonstrate that once the convergence problem is solved, the proposed Transformer-based DRL method can efficiently generate routing policies that adapt well to dynamic network traffic.

关键词： Traffic Engineering Dynamic traffic Transformer Deep Reinforcement Learning Hybrid SDN

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：