检索结果-内蒙古大学图书馆

Causal Attention Transformer for Video Text Retrieval

IET Image processing 2025年第1期19卷

作者： Lan, Hua Lv, Chaohui School of Information and Communication Engineering Communication University of China Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China

In the metaverse, video text retrieval is an urgent and challenging need for users in social entertainment. The current attention-based video text retrieval models have not fully explored the interaction between video and text, and only brute force feature embedding. Moreover, Due to the unsupervised nature of attention weight training, existing models have weak generalization performance for dataset bias. Essentially, the model learns that false relevant information in the data is caused by confounding factors. Therefore, this article proposes a video text retrieval method based on causal attention transformer. Assuming that the confounding factors affecting the performance of video text retrieval all come from the dataset, a structural causal model that conforms to the video text retrieval task is constructed, and the impact of confounding effects during data training is reduced by adjusting the front door. In addition, we use causal attention transformer to construct a causal inference network to extract causal features between video text pairs, and replace the similarity statistical probability with causal probability in the video text retrieval framework. Experiments are conducted on the MSR-VTT, MSVD, and LSMDC datasets, which proves the effectiveness of the retrieval model proposed in this paper. © 2025 The Author(s). IET Image processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

关键词： Interactive computer graphics

来源：评论

学校读者我要写书评

暂无评论

Toward Enhancing Cyber-Physical system Security with system Unidentifiability

引用

IFAC-PapersOnLine 2023年第2期56卷 1692-1697页

作者： Xiangyu Mao Jianping He Chongrong Fang Yunfeng Peng The Dept. of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

A substantial amount of research has shown that most attacks on cyber-physical systems rely on knowledge of system models, where the models can be obtained using identification methods. Hence, achieving unidentifiability is an attractive way for the security of systems. This paper focuses on the unidentifiability of systems and designs a controller against the attacks relying on identification. The key insight is that we propose a quantitative evaluation to measure the unidentifiability of the system. This evaluation can be taken as a criterion for evaluating the security of the system. Different from the existing research, the evaluation gives the exact number of unidentifiable parameters in the system. Moreover, we give the necessary and sufficient condition for each parameter to be unidentifiable. Finally, we design a controller based on this evaluation to maximize the number of unidentifiable parameters. Simulation demonstrates the effectiveness of our algorithm.

关键词： system Identification Security and Unidentifiability Fisher information

来源：评论

学校读者我要写书评

暂无评论

Spatial Temporal Block Transformer Network for Skeleton-Based Action Recognition

Spatial Temporal Block Transformer Network for Skeleton-Base...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Yang, Fan Li, Dewei Wang, Gang Shanghai Jiao Tong University Department of Automation Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China

ISBN: (纸本)9781665465335

Recently, skeleton-based action recognition has be-come very popular in areas such as autonomous driving and environmental awareness due to its small data size and high ac-curacy. Graph convolutional networks (GCN) can model skeleton data well by adapting to the graph structure of the skeleton. However, GCN lacks the ability to extract global spatial and temporal dependencies. Moreover, an action is not only formed by one single skeleton point or frame but several skeleton points and frames. In this paper, a novel spatial-temporal block transformer network based on the self-attention mechanism is proposed, which efficiently models global spatial-temporal dependencies. The model uses spatial-temporal blocks as input, and spatial-temporal feature aggregation modules are applied to enhance the information exchange between blocks. Extensive experiments on the two skeleton-based action recognition datasets show the remarkable performance of our model, which outperforms most GCN-based methods and all transformer-based methods. © 2022 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Online-Learning-Enabled Distributionally Robust Motion control via Uncertainty Propagation and Ambiguity Set Compression

Online-Learning-Enabled Distributionally Robust Motion Contr...

引用

IEEE Conference on Decision and control

作者： Han Wang Chao Ning Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

We develop a safe, efficient, and flexible motion control framework for collision-free navigation of robots in uncertain and dynamic environments. With the gathered real-time data at each control time, the motion distribution of obstacles is estimated from data streams by leveraging the Dirichlet process mixture model. We propose a novel uncertainty propagation method, which theoretically admits the derivation of obstacle position distributions over the entire prediction horizon only based on the current position and motion distribution of obstacles. To enhance the robustness against estimated distribution errors, an ambiguity set utilizing local-moment information of position distributions is constructed. Additionally, we introduce a compression scheme to automatically adjust the complexity (granularity) of the ambiguity set by aggregating distributions that are close in Wasserstein space, thereby flexibly striking a trade-off between control performance and computation time. The distributionally robust collision avoidance constraint based on the compressed ambiguity set is reformulated into separating hyperplanes, which are applied in the model predictive controller to obtain the optimal collision-free trajectory. To resolve the infinite-dimensionality issue inherent in the computation of the separating hyperplanes, we equivalently derive a tractable semi-definite programming formulation exploiting distributionally robust optimization techniques. The efficacy of the proposed framework is demonstrated through simulation.

关键词： Uncertainty Simulation Programming Robustness Real-time systems Trajectory Safety Collision avoidance Robots Streams

来源：评论

学校读者我要写书评

暂无评论

A High-precision Time Synchronization Algorithm for Aviation Swarm Task Cooperation 2

A High-precision Time Synchronization Algorithm for Aviation...

引用

2nd IEEE International Conference on Electronic Technology, Communication and information, ICETCI 2022

作者： Yaobo, Shang Dongwei, Zhang Lei, Wang Zhe, Li Shujing, Li Air Traffic Control and Navigation College Air Force Engineering University Xi'an China Shaanxi Key Laboratory of Meta-Synthesis for Electronic and Information System Xi'an China

ISBN: (数字)9781728181158

ISBN: (纸本)9781728181158

Aiming at the high-precision time synchronization problem of aviation swarm task cooperation, a high-precision time synchronization algorithm suitable for this working environment is proposed. Based on RTT-REP principle, firstly, the influence of node mobility on synchronization accuracy under the condition of system maneuvering is analyzed, and it is proved that synchronization accuracy is closely related to relative distance and relative movement speed. Then, a method of eliminating maneuver error based on state sharing is put forward. This method shares position information through communication system, and then uses coordinate transformation to measure relative movement speed and relative distance to eliminate displacement error. Finally, the test methods are designed under static conditions in the laboratory and dynamic conditions in the field, and the performance of the system is tested. The experimental results show that the synchronization accuracy error of this system is less than 20ns, which proves that this method has high synchronization accuracy and strong practicability. © 2022 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Research on High-Precision Contouring control of Gantry Dual-Drive H-Type Planar Motion Platform

Research on High-Precision Contouring Control of Gantry Dual...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Chao Chen Haoyu Li Chaochen Gu Department of Automation Ministry of Education of China Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

The H-type two-axis linear plane motion platform with dual gantry drive is one of the most crucial components in contour processing equipment. The dual gantry structure employs independently controlled dual-side motors to collectively drive the motion of the gantry crossbeam axis. While the introduction of dual gantry drive brings higher single-axis positioning accuracy and greater operational speed to contour processing *** these issues, this paper starts with the dynamic modeling of the dual gantry H-type plane motion platform. It modifies and extends the task coordinates within the framework of the Global Task Coordinate Frame (GTCF). Subsequently, it effectively addresses the coordination between axes and the synchronization of dual drive in the task space, obtaining both motion coordination and dual-axis synchronization capabilities, leading to more accurate contour error calculation and evaluation. The paper includes a comprehensive design of experiments to assess the dual gantry synchronization performance in contour control. The proposed control method is compared with the traditional GTCF-based contour control method, demonstrating the effectiveness and superiority of the integrated coordination and synchronization contour control method.

关键词： Accuracy Uncertainty Tracking Robot kinematics Dynamics Aerospace electronics Motors

来源：评论

学校读者我要写书评

暂无评论

Leader-Follower Consensus on Matrix-Weighted Switching Networks

Leader-Follower Consensus on Matrix-Weighted Switching Netwo...

引用

International Conference on control and Automation (ICCA)

作者： Kai Wang Lulu Pan Haibin Shao Dewei Li Yuanlong Li Shaoying He Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

This paper examines the consensus problem on leader-follower matrix-weighted undirected switching networks. First, we introduce the leader-follower matrix-weighted integral network for analyzing such a category of networks. The connection between the null space of matrix-valued Laplacian associated with the integral network and that associated with the series of switching matrix-weighted networks has been established. Under some mild assumptions, sufficient conditions for leader-follower consensus under matrix-weighted periodic switching networks are provided. Simulation results are presented to demonstrate the theoretical results.

关键词： Sufficient conditions Laplace equations Automation Simulation Null space Switches

来源：评论

学校读者我要写书评

暂无评论

Immovable Cultural Relics Preservation Through 3D Reconstruction Using NeRF 5

Immovable Cultural Relics Preservation Through 3D Reconstruc...

引用

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Lai, Zhiqing Lian, Mingchang Chen, Songhang Chen, Guoqing Lai, Xiaoling Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China Jingwei Space Information Technology Co. Ltd Longyan364030 China

ISBN: (纸本)9781643684840

Urban and rural development poses significant threats to immovable cultural relics, leading to their degradation and potential extinction. To address this issue, 3D reconstruction has emerged as an effective preservation method. However, traditional radar-based techniques require close scanning and extensive manual intervention, limiting their efficiency. This paper explores the application of neural radiance fields (NeRF) for visually reconstructing immovable cultural relics. NeRF employs a fully connected non-convolutional neural network to generate high-quality 3D models from 2D images. The study discusses NeRF's sampling strategy, positional encoding, field architecture, and rendering process. Experimental investigations evaluate the impact of Fourier parameters on reconstruction quality. A case study reconstructing Tianhou Temple using NeRF is presented, comparing it with ContextCapture software. All results demonstrate that NeRF offers an efficient, and cost-saving solution for reconstructing and preserving immovable cultural relics, providing accurate and realistic models with superior structural integrity. © 2024 The Authors.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Timeslot Clustering-Based Hybrid Traffic Scheduling in Time-Sensitive Networking

A Timeslot Clustering-Based Hybrid Traffic Scheduling in Tim...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Zhihao Yang Shouliang Wang Qimin Xu Xin Li Cailian Chen Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

The development of Industrial Internet of Things necessitates deterministic transmission of hybrid traffic with varying real-time requirements. Time-Sensitive Networking offers schemes combining scheduling mechanisms like the Time-Aware Shaper (TAS) and Cyclic Queuing and Forwarding (CQF). Current methods utilize the combination of TAS&CQF to schedule Time-Triggered (TT) and Audio-Video Bridging (AVB) traffic under corresponding mechanisms, respectively. However, the prior TT traffic orchestration restricts the scheduling solution space of AVB traffic, decreasing the effectiveness of combination and finally resulting in low schedulability. In this paper, we focus on enhancing the schedulability of TT&AVB scheduling by integrating TAS and Cyclic Specified Queuing and Forwarding (CSQF), which brings larger scheduling solution space to AVB traffic. The integration of TAS&CSQF is proposed by analyzing the impact of TAS on CSQF to expand the allocatable resource for AVB traffic. Then TAS&CSQF scheduling model is formulated to ensure deterministic requirements. Within this model, Timeslot Clustering Optimization (TCO) is proposed to optimize the scheduling solution space of AVB traffic and slice timeslot by refining the scheduling of TAS. Based on TCO, Flow Congestion Metric (FCM) is designed to improve schedulability by the congestion level of each link. An FCM-based algorithm is further presented to generate TT&AVB solutions incrementally. Simulation results demonstrate that our method reduces scheduling time cost by over 168 times and improves schedulability by 32% for 3000 flows compared to existing methods.

关键词： Measurement Schedules Job shop scheduling Simulation Refining Real-time systems Internet Informatics Optimization Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Dynamic Event-Triggered Consensus on Matrix-Weighted Networks: Leadless Case 42

Dynamic Event-Triggered Consensus on Matrix-Weighted Network...

引用

42nd Chinese control Conference, CCC 2023

作者： Dou, Lintao Wei, Haoyu Huang, Jian Pan, Lulu Shao, Haibin Li, Dewei College of Intelligent Science National University of Defense Technology Changsha410003 China Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

ISBN: (纸本)9789887581543

This paper examines the event-triggered consensus of the multi-agent system on matrix-weighted networks, where the interdependencies among higher-dimensional states of neighboring agents are characterized by matrix-weighted edges in the network. Specifically, a novel distributed dynamic event-triggered coordination strategy is proposed for this category of generalized networks, in which an auxiliary system is employed for each agent to dynamically adjust the triggering threshold, which plays an essential role in guaranteeing that the triggering time sequence does not exhibit Zeno behavior. Distributed event-triggered control protocols are proposed to guarantee leaderless consensus for multi-agent systems on matrix-weighted networks, respectively. Remarkably, the spectrum of matrix-valued weights is crucial in event-triggered mechanism design for matrix-weighted networks, generalizing those results only applicable for scalar-weighted networks. The proposed approach allows each agent to broadcast and receive information only at its triggering instants. Finally, simulation examples are provided to demonstrate the theoretical results. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Multi agent systems

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：