检索结果-南通市图书馆

Robust video question answering via contrastive cross-modality representation learning

Science China(Information Sciences) 2024年第10期67卷 211-226页

作者： Xun YANG Jianming ZENG Dan GUO Shanshan WANG Jianfeng DONG Meng WANG School of Information Science and Technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center School of computer Science and Information Engineering Hefei University of Technology Institutes of Physical Science and Information Technology Anhui University School of computer Science and Technology Zhejiang Gongshang University

Video question answering(VideoQA) is a challenging yet important task that requires a joint understanding of low-level video content and high-level textual semantics. Despite the promising progress of existing efforts, recent studies revealed that current VideoQA models mostly tend to over-rely on the superficial correlations rooted in the dataset bias while overlooking the key video content, thus leading to unreliable results. Effectively understanding and modeling the temporal and semantic characteristics of a given video for robust VideoQA is crucial but, to our knowledge, has not been well investigated. To fill the research gap, we propose a robust VideoQA framework that can effectively model the cross-modality fusion and enforce the model to focus on the temporal and global content of videos when making a QA decision instead of exploiting the shortcuts in datasets. Specifically, we design a self-supervised contrastive learning objective to contrast the positive and negative pairs of multimodal input, where the fused representation of the original multimodal input is enforced to be closer to that of the intervened input based on video perturbation. We expect the fused representation to focus more on the global context of videos rather than some static keyframes. Moreover, we introduce an effective temporal order regularization to enforce the inherent sequential structure of videos for video representation. We also design a Kullback-Leibler divergence-based perturbation invariance regularization of the predicted answer distribution to improve the robustness of the model against temporal content perturbation of videos. Our method is model-agnostic and can be easily compatible with various VideoQA backbones. Extensive experimental results and analyses on several public datasets show the advantage of our method over the state-of-the-art methods in terms of both accuracy and robustness.

关键词： video question answering cross-modality fusion contrastive learning cross-media reasoning

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Functional predictability of universal gene circuits in diverse microbial hosts

引用

Quantitative Biology 2024年第2期12卷 129-140页

作者： Chenrui Qin Tong Xu Xuejin Zhao Yeqing Zong Haoqian M.Zhang Chunbo Lou Qi Ouyang Long Qian Peking-Tsinghua Joint center for Life Sciences Peking UniversityBeijingChina CAS Key Laboratory of Microbial Physiological and Metabolic Engineering Institute of MicrobiologyChinese Academy of SciencesBeijingChina Bluepha Co. LtdBeijingChina center for Cell and Gene Circuit Design CAS Key Laboratory of Quantitative Engineering BiologyGuangdong Provincial Key Laboratory of Synthetic GenomicsShenzhen Key Laboratory of Synthetic GenomicsShenzhen Institute of Synthetic BiologyShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhenChina center for Quantitative Biology Academy for Advanced Interdisciplinary StudiesPeking UniversityBeijingChina

Although the principles of synthetic biology were initially established in model bacteria,microbial producers,extremophiles and gut microbes have now emerged as valuable prokaryotic chassis for biological *** the host range in which designed circuits can function reliably and predictably presents a major challenge for the concept of synthetic biology to *** this work,we systematically characterized the cross-species universality of two transcriptional regulatory modules—the T7 RNA polymerase activator module and the repressors module—in three non-model *** found striking linear relationships in circuit activities among different organisms for both *** model fitting revealed host non-specific parameters defining the universality of both ***,a genetic NOT gate and a band-pass filter circuit were constructed from these modules and tested in non-model *** models employing host non-specific parameters were successful in quantitatively predicting circuit behaviors,underscoring the potential of universal biological parts and predictive modeling in synthetic bioengineering.

关键词： circuit predictability host-independent genetic circuits host-nonspecific parameters parts characterization transcriptional regulatory modules

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Robust Facial Biometric Authentication System Using Pupillary Light Reflex for Liveness Detection of Facial Images

引用

computer Modeling in Engineering & Sciences 2024年第4期139卷 725-739页

作者： Puja S.Prasad Adepu Sree Lakshmi Sandeep Kautish Simar Preet Singh Rajesh Kumar Shrivastava Abdulaziz S.Almazyad Hossam M.Zawbaa Ali Wagdy Mohamed CSE Department Geethanjali College of EngineeringHyderabadTelangana501301India Department of computer Science LBEF CampusKathmandu44600Nepal School of computer Science Engineering and Technology(SCSET) Bennett UniversityGreater Noida201310India Department of computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia CeADAR Ireland’s Centre for AI Technological University DublinDublinD07 EWV4Ireland Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research center Applied Science Private UniversityAmman11937Jordan

Pupil dynamics are the important characteristics of face spoofing *** face recognition system is one of the most used biometrics for authenticating individual *** main threats to the facial recognition system are different types of presentation attacks like print attacks,3D mask attacks,replay attacks,*** proposed model uses pupil characteristics for liveness detection during the authentication *** pupillary light reflex is an involuntary reaction controlling the pupil’s diameter at different light *** proposed framework consists of two-phase *** the first phase,the pupil’s diameter is calculated by applying stimulus(light)in one eye of the subject and calculating the constriction of the pupil size on both eyes in different video *** above measurement is converted into feature space using Kohn and Clynes model-defined *** Support Vector Machine is used to classify legitimate subjects when the diameter change is normal(or when the eye is alive)or illegitimate subjects when there is no change or abnormal oscillations of pupil behavior due to the presence of printed photograph,video,or 3D mask of the subject in front of the *** the second phase,we perform the facial recognition ***-invariant feature transform(SIFT)is used to find the features from the facial images,with each feature having a size of a 128-dimensional *** features are scale,rotation,and orientation invariant and are used for recognizing facial *** brute force matching algorithm is used for matching features of two different *** threshold value we considered is 0.08 for good *** analyze the performance of the framework,we tested our model in two Face antispoofing datasets named Replay attack datasets and CASIA-SURF datasets,which were used because they contain the videos of the subjects in each sample having three modalities(RGB,IR,Depth).The CASIA-SURF datasets showed an 89.9%Equal Err

关键词： SIFT pupil CASIA-SURF pupillary light reflex replay attack dataset brute force

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Unleashing the Power of Multi-Agent Reinforcement Learning for Algorithmic Trading in the Digital Financial Frontier and Enterprise Information Systems

引用

computers, Materials & Continua 2024年第8期80卷 3123-3138页

作者： Saket Sarin Sunil K.Singh Sudhakar Kumar Shivam Goyal Brij Bhooshan Gupta Wadee Alhalabi Varsha Arya Chandigarh College of Engineering and Technology Chandigarh160019India Department of computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India Department of computer Science Immersive Virtual Reality Research GroupKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Business Administration Asia UniversityTaichung413Taiwan Department of Electrical and computer Engineering Lebanese American UniversityBeirut11022801Lebanon UCRD Chandigarh UniversityChandigarh140413India

In the rapidly evolving landscape of today’s digital economy,Financial Technology(Fintech)emerges as a trans-formative force,propelled by the dynamic synergy between Artificial Intelligence(AI)and Algorithmic *** in-depth investigation delves into the intricacies of merging Multi-Agent Reinforcement Learning(MARL)and Explainable AI(XAI)within Fintech,aiming to refine Algorithmic Trading *** meticulous examination,we uncover the nuanced interactions of AI-driven agents as they collaborate and compete within the financial realm,employing sophisticated deep learning techniques to enhance the clarity and adaptability of trading *** AI-infused Fintech platforms harness collective intelligence to unearth trends,mitigate risks,and provide tailored financial guidance,fostering benefits for individuals and enterprises navigating the digital *** research holds the potential to revolutionize finance,opening doors to fresh avenues for investment and asset management in the digital ***,our statistical evaluation yields encouraging results,with metrics such as Accuracy=0.85,Precision=0.88,and F1 Score=0.86,reaffirming the efficacy of our approach within Fintech and emphasizing its reliability and innovative prowess.

关键词： Neurodynamic Fintech multi-agent reinforcement learning algorithmic trading digital financial frontier

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

大规模集成的高性能本征可拉伸电子

引用

Science Bulletin 2024年第12期69卷 1813-1815页

作者：王誉儒黄儒翊王婉仪胡又凡 Key Laboratory for the Physics and Chemistry of Nanodevices Center for Carbon-Based Electronics and School of ElectronicsPeking UniversityBeijing 100871China Academy for advanced Interdisciplinary studies Peking UniversityBeijing 100871China

Skin-like electronics exhibit soft and stretchable mechanical properties,enabling seamless conformal contact with the human skin and organ surfaces[1].Consequently,skin-like electronics facilitate high-fidelity bio-signal monitoring and imperceptible interaction with the human body[2],thereby empowering future telemedicine[3],soft robotics[4],and augmented reality applications[5].

关键词： thereby Skin conformal

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Aggravation of Cancer,Heart Diseases and Diabetes Subsequent to COVID-19 Lockdown via Mathematical Modeling

引用

computer Modeling in Engineering & Sciences 2024年第7期140卷 485-512页

作者： Fatma Nese Efil Sania Qureshi Nezihal Gokbulut Kamyar Hosseini Evren Hincal Amanullah Soomro Near East University Department of MathematicsNicosia99010North Cyprus Mehran University of Engineering and Technology Department of Basic Sciences and Related StudiesJamshoro76090Pakistan Department of computer Science and Mathematics Lebanese American UniversityP.O.Box 13-5053BeirutLebanon Near East University Mathematics Research CenterNicosia99010North Cyprus

The global populationhas beenandwill continue to be severely impacted by theCOVID-19 *** primary objective of this research is to demonstrate the future impact of COVID-19 on those who suffer from other fatal conditions such as cancer,heart disease,and ***,using ordinary differential equations(ODEs),two mathematical models are developed to explain the association between COVID-19 and cancer and between COVID-19 and diabetes and heart *** that,we highlight the stability assessments that can be applied to these *** analysis is used to examine how changes in certain factors impact different aspects of *** sensitivity analysis showed that many people are still nervous about seeing a doctor due to COVID-19,which could result in a dramatic increase in the diagnosis of various ailments in the years to *** correlation between diabetes and cardiovascular illness is also illustrated *** effects of smoking and obesity are also found to be significant in disease *** fitting is also provided for interpreting the relationship between real data and the results of *** people,in particular,need tomonitor their health conditions closely and practice heart health *** with heart diseases should undergo regular checks so that they can protect themselves from diabetes and take some precautions including suitable *** main purpose of this study is to emphasize the importance of regular checks,to warn people about the effects of COVID-19(including avoiding healthcare centers and doctors because of the spread of infectious diseases)and to indicate the importance of family history of cancer,heart diseases and *** provision of the recommendations requires an increase in public consciousness.

关键词： COVID-19 mathematical modeling cancer diabetes heart diseases sensitivity analysis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Exploring van der Waals materials with high anisotropy:geometrical and optical approaches

引用

Light(Science & Applications) 2024年第4期13卷 645-653页

作者： Aleksandr S.Slavich Georgy A.Ermolaev Mikhail K.Tatmyshevskiy Adilet N.Toksumakov Olga G.Matveeva Dmitriy V.Grudinin Kirill V.Voronin Arslan Mazitov Konstantin V.Kravtsov Alexander V.Syuy Dmitry M.Tsymbarenko Mikhail S.Mironov Sergey M.Novikov Ivan Kruglov Davit A.Ghazaryan Andrey A.Vyshnevyy Aleksey V.Arsenin Valentyn S.Volkov Kostya S.Novoselov Moscow center for advanced studies Kulakova str.20Moscow 123592Russia. Emerging Technologies Research center XPANCEOInternet CityEmmay TowerDubaiUnited Arab Emirates. Donostia International Physics center(DIPC) Donostia/San-Sebastián 20018Spain. Institute of Materials Ecole Polytechnique Federale de Lausanne1015 LausanneSwitzerland. Department of Chemistry Lomonosov Moscow State UniversityMoscow 119991Russia. Laboratory of advanced Functional Materials Yerevan State UniversityYerevan 0025Armenia. National Graphene Institute(NGI) University of ManchesterManchester M139PLUK. Department of Materials Science and Engineering National University of SingaporeSingapore 03-09 EASingapore. Institute for Functional Intelligent Materials National University of Singapore117544 SingaporeSingapore

The emergence of van der Waals(vdW)materials resulted in the discovery of their high optical,mechanical,and electronic anisotropic properties,immediately enabling countless novel phenomena and *** success inspired an intensive search for the highest possible anisotropic properties among vdW ***,the identification of the most promising among the huge family of vdW materials is a challenging quest requiring innovative ***,we suggest an easy-to-use method for such a survey based on the crystallographic geometrical perspective of vdW materials followed by their optical *** our approach,we found As2S3 as a highly anisotropic vdW *** demonstrates high in-plane optical anisotropy that is~20%larger than for rutile and over two times as large as calcite,high refractive index,and transparency in the visible range,overcoming the century-long record set by *** these benefits,As2S3 opens a pathway towards nextgeneration nanophotonics as demonstrated by an ultrathin true zero-order quarter-wave plate that combines classical and the Fabry–Pérot optical phase ***,our approach provides an effective and easy-to-use method to find vdW materials with the utmost anisotropic properties.

关键词： anisotropy anisotropic high

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CuO–TiO_(2) based self-powered broad band photodetector

引用

Nano Materials Science 2024年第3期6卷 345-354页

作者： Chiranjib Ghosh Arka Dey Iman Biswas Rajeev Kumar Gupta Vikram Singh Yadav Ashish Yadav Neha Yadav Hongyu Zheng Mohamed Henini Aniruddha Mondal Department of Physics National Institute of Technology DurgapurWest BengalIndia Department of Physics University of Petroleum&Energy Studies DehradunUttarakhandIndia Babasaheb Bhimrao Ambedkar University Lucknow226031India center for advanced Laser Manufacturing(CALM) Shandong University of TechnologyZibo255000PR China School of Physics and Astronomy University of NottinghamNottinghamNG72RDUnited Kingdom

An efficient room-temperature self-powered,broadband(300 nm–1100 nm)photodetector based on a CuO–TiO_(2)/TiO_(2)/p-Si(100)heterostructure is *** CuO–TiO_(2)nanocomposites were grown in a two-zone horizontal tube furnace on a 40 nm TiO_(2)thin film deposited on a p-type Si(100)*** CuO–TiO_(2)/TiO_(2)/p-Si(100)devices exhibited excellent rectification characteristics under dark and individual photoillumination *** devices showed remarkable photo-response under broadband(300–1100 nm)light illumination at zero bias voltage,indicating the achievement of highly sensitive self-powered photodetectors at visible and near-infrared light *** maximum response of the devices is observed at 300 nm for an illumination power of 10 *** response and recovery times were calculated as 86 ms and 78 ms,***,under a small bias,the devices showed a prompt binary response by altering the current from positive to negative under illumination *** main reason behind this binary response is the low turn-on voltage and photovoltaic characteristics of the *** illumination conditions,the generation of photocurrent is due to the separation of photogenerated electron-hole pairs within the built-in electric field at the CuO–TiO_(2)/TiO_(2)*** characteristics make the CuO–TiO_(2)/TiO_(2)broadband photodetectors suitable for applications that require high response speeds and self-sufficient functionality.

关键词： Self-powered CuO–TiO_(2) nanocomposite Broadband photodetector Two-zone horizontal tube furnace Responsivity

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Machine-learned wearable sensors for real-time hand-motion recognition: toward practical applications

引用

National Science Review 2024年第2期11卷 231-263页

作者： Kyung Rok Pyun Kangkyu Kwon Myung Jin Yoo Kyun Kyu Kim Dohyeon Gong Woon-Hong Yeo Seungyong Han Seung Hwan Ko Department of Mechanical Engineering Seoul National University IEN center for Human-Centric Interfaces and Engineering Institute for Electronics and NanotechnologyGeorgia Institute of Technology School of Electrical and computer Engineering Georgia Institute of Technology Department of Chemical Engineering Stanford University Department of Mechanical Engineering Ajou University George W.Woodruff School of Mechanical Engineering Georgia Institute of Technology Institute of advanced Machinery and Design(SNU-IAMD) Seoul National University

Soft electromechanical sensors have led to a new paradigm of electronic devices for novel motion-based wearable applications in our daily lives. However, the vast amount of random and unidentified signals generated by complex body motions has hindered the precise recognition and practical application of this technology. Recent advancements in artificial-intelligence technology have enabled significant strides in extracting features from massive and intricate data sets, thereby presenting a breakthrough in utilizing wearable sensors for practical applications. Beyond traditional machine-learning techniques for classifying simple gestures, advanced machine-learning algorithms have been developed to handle more complex and nuanced motion-based tasks with restricted training data sets. Machine-learning techniques have improved the ability to perceive, and thus machine-learned wearable soft sensors have enabled accurate and rapid human-gesture recognition, providing real-time feedback to users. This forms a crucial component of future wearable electronics, contributing to a robust human–machine interface. In this review, we provide a comprehensive summary covering materials, structures and machine-learning algorithms for hand-gesture recognition and possible practical applications through machine-learned wearable electromechanical sensors.

关键词： wearable sensor soft electronics artificial intelligence machine learning human–machine interfaces gesture recognition

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Estimating Key Phenological Dates of Multiple Rice Accessions Using Unmanned Aerial Vehicle-Based Plant Height Dynamics for Breeding

引用

Rice science 2024年第5期31卷 617-628,I0066-I0070页

作者： HONG Weiyuan LI Ziqiu FENG Xiangqian QIN Jinhua WANG Aidong JIN Shichao WANG Danying CHEN Song State Key Laboratory of Rice Biology and Breeding China National Rice Research InstituteHangzhou 311400China College of computer Science and Technology Zhejiang Sci-Tech UniversityHangzhou 310018China College of Agriculture Yangtze UniversityJingzhou 434025China Plant Phenomics Research Centre Academy for Advanced Interdisciplinary StudiesNanjing Agricultural UniversityNanjing 210095China

Efficient and high-quality estimation of key phenological dates in rice is of great significance in breeding work. Plant height(PH) dynamics are valuable for estimating phenological dates. However, research on estimating the key phenological dates of multiple rice accessions based on PH dynamics has been limited. In 2022, field traits were collected using unmanned aerial vehicle(UAV)-based images across 435 plots, including 364 rice varieties. PH, dates of initial heading(IH) and full heading(FH), and panicle initiation(PI), and growth period after transplanting(GPAT) were collected during the rice growth stage. PHs were extracted using a digital surface model(DSM) and fitted using Fourier and logistic models. Machine learning algorithms, including multiple linear regression, random forest(RF), support vector regression, least absolute shrinkage and selection operator, and elastic net regression, were employed to estimate phenological dates. Results indicated that the optimal percentile of the DSM for extracting rice PH was the 95th(R^(2) = 0.934, RMSE = 0.056 m). The Fourier model provided a better fit for PH dynamics compared with the logistic models. Additionally, curve features(CF) and GPAT were significantly associated with PI, IH, and FH. The combination of CF and GPAT outperformed the use of CF alone, with RF demonstrating the best performance among the algorithms. Specifically, the combination of CF extracted from the logistic models, GPAT, and RF yielded the best performance for estimating PI(R^(2) = 0.834, RMSE = 4.344 d), IH(R^(2) = 0.877, RMSE = 2.721 d), and FH(R^(2) = 0.883, RMSE = 2.694 d). Overall, UAV-based rice PH dynamics combined with machine learning effectively estimated the key phenological dates of multiple rice accessions, providing a novel approach for investigating key phenological dates in breeding work.

关键词： phenological date plant height unmanned aerial vehicle machine learning rice breeding

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：