检索结果-南通市图书馆

Visuals to Text:A Comprehensive Review on Automatic Image Captioning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

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

维普期刊数据库

BOM-BASED DESIGN KNOWLEDGE REPRESENTATION AND REASONING FOR COLLABORATIVE PRODUCT DEVELOPMENT

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science and Systems Engineering 2016年第2期25卷 159-176页

作者： Gongzhuang Peng Huachao Mao Hongwei Wang Heming Zhang National CIMSEngineeringResearch Center Tsinghua University Beijing 100084 China School of Engineering University of Portsmouth Anglesea Read Portsmouth PO1 3D J UK

Modem product development becomes increasingly collaborative and integrated, which raises the need for effectively and efficiently sharing and re-using design knowledge in a distributed and collaborative environment. To address this need, a framework is developed in this research to support design knowledge representation, retrieval, reasoning and fusion, which takes account of structural, functional and behavioral data, various design attributes and knowledge reasoning cases. Specifically, a multi-level knowledge representation based on the Base Object Model （BOM） is proposed to enable knowledge sharing using Web services technologies. On this basis, a multi-level knowledge reuse method is developed to support the retrieval, matching and assembly of knowledge records. Due to the tree structure of BOM, both depth-first and breadth-first searching strategies are employed in the retrieval algorithm while a novel measure is proposed to evaluate similarity. Moreover, a method based on the D-S evidence theory is developed to enable knowledge fusion and thus support effective decision-making. The framework has been implemented and integrated into an HLA-based simulation platform on which the development of a missile simulation example is conducted. It is demonstrated in the case study that the proposed framework and methods are useful and effective for design knowledge representation and reuse.

关键词： Complex product development multi-level knowledge reuse knowledge fusion Base Object Model D-S evidence theory

Robotic complete mesocolic excision for right colon cancer:Learning curve,training,techniques,approach,platforms,and future perspectives

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Laparoscopic, Endoscopic and Robotic Surgery 2024年第2期7卷 53-59页

作者： Guglielmo NiccolòPiozzi Sentilnathan Subramaniam Rauand Duhoky Werner Hohenberger Jim S.Khan Department of Colorectal Surgery Portsmouth Hospitals University NHS TrustPortsmouthUK Colorectal Surgery Unit Department of General SurgeryHospital SelayangSelangorMalaysia Faculty of Technology University of PortsmouthPortsmouthUK Department of General Surgery Universitatsklinikum ErlangenErlangenGermany Faculty of Science and Health University of PortsmouthPortsmouthUK

Colon cancer has the fifth highest incidence worldwide and has the sixth highest *** with rectal cancer,colon cancer currently has the worst 5-year overall survival for patients with stage Ⅱ and Ⅲ *** mesocolic excision has been developed as a standardized and optimized surgical technique for the excision of colon *** technique has traditionally been performed through an open approach since laparoscopy is generally considered technically *** robotic approach has been slowly implemented for colon cancer,but the newest robotic platforms allow for a safer and optimized approach for right colon *** robotic approaches have been developed and *** expansion of the current robotic platform ecosystem is gradually providing new outputs in the application of the robotic approach to complete mesocolic *** review gains an oversight of existing literature on robotic complete mesocolic excision for right colon cancer(learning curve,training,techniques,approach,platforms,and future perspectives).

关键词： Robotic surgery Complete mesocolic excision Robotic platform Colon cancer Colorectal surgery

Open-porous magnesium-based scaffolds withstand in vitro corrosion under cyclic loading:A mechanistic study

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Bioactive Materials 2023年第1期19卷 406-417页

作者： Roxane Bonithon Colin Lupton Marta Roldo Joseph Nicholas Dunlop Gordon William Blunn Frank Witte Gianluca Tozzi Zeiss Global Centre School of Mechanical and Design EngineeringUniversity of PortsmouthAnglesea RoadPO13DJPortsmouthUnited Kingdom School of Pharmacy and Biomedical Sciences University of PortsmouthWhite Swan RoadPO12DTPortsmouthUnited Kingdom School of the Environment Geography&GeosciencesUniversity of PortsmouthBurnaby RoadPO13QLPortsmouthUnited Kingdom Department of Prosthodontics Geriatric Dentistry and Craniomandibular DisordersCharite-Universitätsmedizin BerlinAßmannshauser Straße 4-614197BerlinGermany Biotrics Bioimplants AG Ullsteinstr.10812109BerlinGermany

The successful application of magnesium(Mg)alloys as biodegradable bone substitutes for critical-sized defects may be comprised by their high degradation rate resulting in a loss of mechanical *** study investigates the degradation pattern of an open-porous fluoride-coated Mg-based scaffold immersed in circulating Hanks’Balanced Salt Solution(HBSS)with and without in situ cyclic compression(30 N/1 Hz).The changes in morphological and mechanical properties have been studied by combining in situ high-resolution X-ray computed tomography mechanics and digital volume *** in situ cyclic compression induced acceleration of the corrosion rate,probably due to local disruption of the coating layer where fatigue microcracks were formed,no critical failures in the overall scaffold were observed,indicating that the mechanical integrity of the Mg scaffolds was *** changes,due to the accumulation of corrosion debris between the scaffold fibres,resulted in a significant increase(p<0.05)in the material volume fraction from 0.52±0.07 to 0.47±0.03 after 14 days of ***,despite an increase in fibre material loss,the accumulated corrosion products appear to have led to an increase in Young’s modulus after 14 days as well as lower third principal strain(εp3)accumulation(-91000±6361μεand-60093±2414μεafter 2 and 14 days,respectively).Therefore,this innovative Mg scaffold design and composition provide a bone replacement,capable of sustaining mechanical loads in situ during the postoperative phase allowing new bone formation to be initially supported as the scaffold resorbs.

关键词： Magnesium alloys Bone regeneration In vitro corrosion X-ray computed tomography(XCT) Digital volume correlation(DVC)

Study of Human Action Recognition Based on Improved Spatio-temporal Features

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2014年第5期11卷 500-509页

作者： Xiao-Fei Ji Qian-Qian Wu Zhao-Jie Ju Yang-Yang Wang School of Automation Shenyang Aerospace University School of Computing University of Portsmouth

Most of the exist action recognition methods mainly utilize spatio-temporal descriptors of single interest point while ignoring their potential integral information, such as spatial distribution information. By combining local spatio-temporal feature and global positional distribution information(PDI) of interest points, a novel motion descriptor is proposed in this paper. The proposed method detects interest points by using an improved interest point detection method. Then, 3-dimensional scale-invariant feature transform(3D SIFT) descriptors are extracted for every interest point. In order to obtain a compact description and efficient computation, the principal component analysis(PCA) method is utilized twice on the 3D SIFT descriptors of single frame and multiple frames. Simultaneously, the PDI of the interest points are computed and combined with the above features. The combined features are quantified and selected and finally tested by using the support vector machine(SVM) recognition algorithm on the public KTH dataset. The testing results have showed that the recognition rate has been significantly improved and the proposed features can more accurately describe human motion with high adaptability to scenarios.

关键词： Action recognition spatio-temporal interest points 3-dimensional scale-invariant feature transform (3D SIFT) positional distribution information dimension reduction

维普期刊数据库

Accurate and Robust Eye Center Localization via Fully Convolutional Networks

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第5期6卷 1127-1138页

作者： Yifan Xia Hui Yu Fei-Yue Wang the School of Creative Technologies University of PortsmouthPortsmouthPO1 2DJUK the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Eye center localization is one of the most crucial and basic requirements for some human-computer interaction applications such as eye gaze estimation and eye tracking. There is a large body of works on this topic in recent years, but the accuracy still needs to be improved due to challenges in appearance such as the high variability of shapes, lighting conditions, viewing angles and possible occlusions. To address these problems and limitations, we propose a novel approach in this paper for the eye center localization with a fully convolutional network(FCN),which is an end-to-end and pixels-to-pixels network and can locate the eye center accurately. The key idea is to apply the FCN from the object semantic segmentation task to the eye center localization task since the problem of eye center localization can be regarded as a special semantic segmentation problem. We adapt contemporary FCN into a shallow structure with a large kernel convolutional block and transfer their performance from semantic segmentation to the eye center localization task by *** experiments show that the proposed method outperforms the state-of-the-art methods in both accuracy and reliability of eye center localization. The proposed method has achieved a large performance improvement on the most challenging database and it thus provides a promising solution to some challenging applications.

关键词： Deep learning eye center localization eye gaze estimation eye tracking fully convolutional network (FCN) humancomputer interaction

维普期刊数据库

An Immunization Scheme for Ransomware

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第8期64卷 1051-1061页

作者： Jingping Song Qingyu Meng Chenke Luo Nitin Naik Jian Xu Software College Northeastern UniversityShenyang110169China School of Cyber Science and Engineering Wuhan UniversityWuhan430072China School of Computing University of PortsmouthPortsmouthPO12DTUK

In recent years,as the popularity of anonymous currencies such as Bitcoin has made the tracking of ransomware attackers more difficult,the amount of ransomware attacks against personal computers and enterprise production servers is increasing *** ransomware has a wide range of influence and spreads all over the *** is affecting many industries including internet,education,medical care,traditional industry,*** paper uses the idea of virus immunity to design an immunization solution for ransomware viruses to solve the problems of traditional ransomware defense methods(such as anti-virus software,firewalls,etc.),which cannot meet the requirements of rapid detection and immediate prevention of new outbreaks *** scheme includes two parts:server and *** server provides an immune configuration file and configuration file management functions,including a configuration file module,a cryptography algorithm module,and a display *** client obtains the immunization configuration file from server in real time,and performs the corresponding operations according to the configuration file to make the computer have an immune function for a specific ransomware,including an update module,a configuration file module,a cryptography algorithm module,a control module,and a log *** scheme controls mutexes,services,files and registries respectively,to destroy the triggering conditions of the virus and finally achieve the purpose of immunizing a computer from a specific ransomware.

关键词： Malware ransomware malware immunization

Development of Muscle Tendon Junction in vitro Using Aligned Electrospun PCL Fibres

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineered Regeneration 2024年第3期5卷 409-420页

作者： Nodoka Iwasaki Marta Roldo Aikaterina Karali Alberto Sensini Gordon Blunn School of Pharmacy and Biomedical Sciences University of PortsmouthPortsmouthUK School of Mechanical and Design Engineering University of PortsmouthPortsmouthUK Complex Tissue Regeneration Department MERLN Institute for Technology-Inspired Regenerative MedicineMaastricht UniversityMaastrichtthe Netherlands Cell Biology-Inspired Tissue Regeneration Department MERLN Institute for Technology-Inspired Regenerative MedicineMaastricht UniversityMaastrichtthe Netherlands

The muscle tendon junction(MTJ)transmits the force generated by the muscle to the tendon and ultimately to the *** and strains commonly occur at the MTJ where regeneration is limited due poor vascularisation and the complexity of the *** treatments for a complete MTJ tear are often *** creation of a tissue engineered MTJ would therefore be beneficial in the development of a novel *** this study,aligned electrospun polycaprolactone fibres were fabricated and human myoblasts and tenocytes were cultured on the *** effect of 10%cyclic strain and co-culture of myoblasts and tenocytes on the MTJ formation was *** application of strain significantly increased cell elongation,and MTJ marker gene ***-culture of myoblasts and tenocytes with strain induced higher MTJ marker gene expression compared with myoblasts and tenocytes cultured *** and collagen 22,naturally found in the MTJ,were also produced when cells were combined and grown in a 10%strain *** the first time these results showed that the combination of the strain and co-culture of myoblasts and tenocytes promotes gene expression and production of proteins that are found in the MTJ.

关键词： Muscle tendon junction Tissue engineering Electrospinning Bioreactor Strain

Enhanced Temporal Correlation for universal Lesion Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第3期138卷 3051-3063页

作者： Muwei Jian Yue Jin Hui Yu School of Computer Science and Technology Shandong University of Finance and EconomicsJinanChina School of Information Science and Technology Linyi UniversityLinyiChina School of Creative Technologies University of PortsmouthPortsmouthUK

universal lesion detection(ULD)methods for computed tomography(CT)images play a vital role in the modern clinical medicine and intelligent *** is well known that single 2D CT slices lack spatial-temporal characteristics and contextual information compared to 3D CT ***,3D CT blocks necessitate significantly higher hardware resources during the learning ***,efficiently exploiting temporal correlation and spatial-temporal features of 2D CT slices is crucial for ULD *** this paper,we propose a ULD network with the enhanced temporal correlation for this purpose,named *** designed TCE module is applied to enrich the discriminate feature representation of multiple sequential CT ***,we employ multi-scale feature maps to facilitate the localization and detection of lesions in various *** experiments are conducted on the DeepLesion benchmark demonstrate that thismethod achieves 66.84%and 78.18%for FS@0.5 and FS@1.0,respectively,outperforming compared state-of-the-art methods.

关键词： universal lesion detection computational biology medical computing deep learning enhanced temporal correlation