检索结果-内蒙古大学图书馆

ViGT: proposal-free video grounding with a learnable token in the transformer

science China(Information sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Accurately predicting hypersonic transitional flow on cone via a symmetry approach

引用

Chinese Journal of Aeronautics 2023年第7期36卷 337-347页

作者： Weitao BI Kexin ZHENG Zhou WEI Zhensu SHE State Key Laboratory for Turbulence and Complex Systems and Department of Mechanics and Engineering Science College of EngineeringPeking UniversityBeijing 100871China State Key Laboratory of Aerodynamics and Computational Aerodynamics Institute China Aerodynamics Research and Development CenterMianyang 621000China

A new algebraic transition model is proposed based on a Structural Ensemble Dynamics(SED)theory of wall turbulence,for accurately predicting the hypersonic flow heat transfer on *** model defines the eddy viscosity in terms of a two-dimensional multi-regime distribution of a Stress Length(SL)function,and hence is named as *** paper presents clear evidence of precise predictions of transition onset location and peak heat flux of a wide range of hypersonic Transitional Boundary Layers(TrBL)around straight cone at zero incidence,to an unprecedented accuracy as validated by over 70 measurements for varying five crucial influential factors(Mach number,temperature ratio,cone half angle,nose Reynolds number and noise level).The results demonstrate the universality of the postulated multi-regime similarity structure,in characterizing not only the spatial non-uniform distribution of the eddy viscosity in hypersonic TrBL on cone,but also the dependence of the transition onset location on the five influential *** latter yields a novel correlation formula for transition center Reynolds number which takes similar functional form as the SL function within the symmetry *** is concluded that the SED-SL model simulates TrBL around cone with uniformly high accuracy,and then points out to an optimistic alternative way to construct hypersonic transition model.

关键词： Cones Heat flux Hypersonic boundary layers Transition flow Turbulence models

来源：评论

学校读者我要写书评

暂无评论

Microstructural Mechanical Analysis and Dynamics Simulation of Hollow Soft Magnetic Particle-Based Magnetorheological Fluids 2nd

Microstructural Mechanical Analysis and Dynamics Simulation ...

引用

2nd International Conference of Mechanical System Dynamics, ICMSD 2023

作者： Wang, Shun He, Bin Han, Wenjiao Chen, Xingcheng Wang, Xin National Key Laboratory of Complex Multibody Systems Dynamics Nanjing University of Science and Technology Nanjing210094 China

ISBN: (纸本)9789819980475

The hollow soft magnetic particle-based magnetorheological (MR) fluid has been extensively studied due to its good anti-settling property. However, studies are mainly focused on experiments, and the discussion of the mechanism is still inadequate, especially considering multiple influencing factors under coupled fields. In this paper, based on the magnetic dipole theory, we established a dynamic model of hollow particles in magnetorheological fluid under the magnetic-shear coupling field. Molecular dynamics simulations were adopted to simulate the microstructure evolution of the magnetorheological fluid in two-dimensional scale, and the effects of hollow radius, magnetic field strength, volume fraction and shear rate on the rheological properties were analyzed. The results show that these factors significantly affect the response time and yield stress of the magnetorheological fluid. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Yield stress

来源：评论

学校读者我要写书评

暂无评论

Parallel Seeds:From Foundation Models to Foundation Intelligence for Agricultural Sustainability

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 481-484页

作者： Laiyi Fu Shunkang Ling Danyang Wu Mengzhen Kang Fei-Yue Wang Hequan Sun the Shool of Automation Science and Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong University the College of Information Engineering Northwest A&F University IEEE the State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences

THE development of agriculture faces significant challenges due to population growth, climate change, land depletion, and environmental pollution, threatening global food security [1]. This necessitates the development of sustainable agriculture, where a fundamental step is crop breeding to improve agronomic or economic traits, e.g., increasing yields of crops while decreasing resource usage and minimizing pollution to the environment [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Journey/DAO/TAO of Embodied Intelligence: From Large Models to Foundation Intelligence and Parallel Intelligence

引用

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1313-1316页

作者： Tianyu Shen Jinlin Sun Shihan Kong Yutong Wang Juanjuan Li Xuan Li Fei-Yue Wang College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China School of Electrical and Information Engineering Jiangsu UniversityZhenjiang 212013China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and RoboticsCollege of EngineeringPeking UniversityBeijing 100871China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Peng Cheng Laboratory Shenzhen 518000China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China IEEE

THE tremendous impact of large models represented by ChatGPT[1]-[3]makes it necessary to con-sider the practical applications of such models[4].However,for an artificial intelligence(AI)to truly evolve,it needs to possess a physical“body”to transition from the virtual world to the real world and evolve through interaction with the real *** this context,“embodied intelligence”has sparked a new wave of research and technology,leading AI beyond the digital realm into a new paradigm that can actively act and perceive in a physical environment through tangible entities such as robots and automated devices[5].

关键词： Intelligence DAO TAO

来源：评论

学校读者我要写书评

暂无评论

A survey for light field super-resolution

引用

High-Confidence Computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent Computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image

来源：评论

学校读者我要写书评

暂无评论

Theoretical analysis of surface waves in piezoelectric medium with periodic shunting circuits

引用

Applied Mathematics and Mechanics(English Edition) 2023年第8期44卷 1287-1304页

作者： Youqi ZHANG Rongyu XIA Jie XU Kefu HUANG Zheng LI State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering SciencePeking UniversityBeijing 100871China Department of Mechanics and Aerospace Engineering Southern University of Science and TechnologyShenzhen 518055Guangdong ProvinceChina

The investigations of surface waves in the piezoelectric medium bring out great possibility in designing smart surface acoustic wave(SAW)*** is important to study the dispersion properties and manipulation mechanism of surface waves in the semi-infinite piezoelectric medium connected with periodic arrangement of shunting *** this study,the extended Stroh formalism is developed to theoretically analyze the dispersion relations of surface waves under different external *** band structures of both the Rayleigh wave and the Bleustein-Gulyaev(BG)wave can be determined and manipulated with proper electrical boundary ***,the electromechanical coupling effects on the band structures of surface waves are discussed to figure out the manipulation mechanism of adjusting electric *** results indicate that the proposed method can explain the propagation behaviors of surface waves under the periodic electrical boundary conditions,and can provide an important theoretical guidance for designing novel SAW devices and exploring extensive applications in practice.

关键词： metamaterial phononic crystal surface wave piezoelectricity electromechanical coupling Stroh formalism

来源：评论

学校读者我要写书评

暂无评论

Parallel Light Fields: A Perspective and A Framework

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 542-544页

作者： Fei-Yue Wang Yu Shen IEEE State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of ScienceBeijing 100049

Dear Editor,Light fields give relatively complete description of scenes from perspective of angles and positions of rays. At present time, most of the computer vision algorithms take 2D images as input which are simplified expression of light fields with depth information discarded. In theory, computer vision tasks may achieve better performance as long as complete light fields are acquired.

关键词： computer Framework simplified

来源：评论

学校读者我要写书评

暂无评论

Object Helps U-Net Based Change Detectors

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 548-550页

作者： Lan Yan Qiang Li Kenli Li College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Dear Editor,This letter focuses on leveraging the object information in images to improve the performance of the U-Net based change *** detection is fundamental to many computer vision *** existing solutions based on ... 详细信息

关键词： Net computer networks

来源：评论

学校读者我要写书评

暂无评论

Taiji-TianQin-LISA network:Precisely measuring the Hubble constant using both bright and dark sirens

引用

science China(Physics,Mechanics & Astronomy) 2024年第2期67卷 59-77页

作者： Shang-Jie Jin Ye-Zhu Zhang Ji-Yu Song Jing-Fei Zhang Xin Zhang Key Laboratory of Cosmology and Astrophysics(Liaoning)&College of Sciences Northeastern UniversityShenyang 110819China Key Laboratory of Data Analytics and Optimization for Smart Industry(Ministry of Education) Northeastern UniversityShenyang 110819China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern UniversityShenyang 110819China

In the coming decades,the space-based gravitational-wave(GW)detectors such as Taiji,TianQin,and LISA are expected to form a network capable of detecting millihertz GWs emitted by the mergers of massive black hole binaries(MBHBs).In this work,we investigate the potential of GW standard sirens from the Taiji-TianQin-LISA network in constraining cosmological *** the optimistic scenario in which electromagnetic(EM)counterparts can be detected,we predict the number of detectable bright sirens based on three different MBHB population models,i.e.,popⅢ,Q3d,and *** results show that the TaijiTianQin-LISA network alone could achieve a constraint precision of 0.9%for the Hubble constant,meeting the standard of precision ***,the Taiji-TianQin-LISA network could effectively break the cosmological parameter degeneracies generated by the CMB data,particularly in the dynamical dark energy *** combined with the CMB data,the joint CMB+Taiji-TianQin-LISA data offerσ(w)=0.036 in the wCDM model,which is close to the latest constraint result obtained from the CMB+SN *** also consider a conservative scenario in which EM counterparts are not *** to the precise sky localizations of MBHBs by the Taiji-TianQin-LISA network,the constraint precision of the Hubble constant is expected to reach 1.2%.In conclusion,the GW standard sirens from the Taiji-TianQin-LISA network will play a critical role in helping solve the Hubble tension and shedding light on the nature of dark energy.

关键词： space-based gravitational wave detection standard sirens the Taiji-TianQin-LISA network the Hubble constant dark energy

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：