检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Yuming Zhao, Wantong Huang, Caishuang Ye, Junjie Wang, Xiao Zheng, Huiyuan Nan, Yang Wang, Yuran Xu, Xueying Huang, Kaixin Zhang, Yunke Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Honor Device Co. Ltd. Institute of Modern Languages and Linguistics Fudan University China Pengcheng Laboratory China Research Institute of Intelligent Complex Systems Fudan University China Shanghai Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)9798891761964

Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent studies suggest that fine-tuning LLMs on extensive NER data can boost their performance. However, training directly on existing datasets neglects their inconsistent entity definitions and redundant data, limiting LLMs to dataset-specific learning and hindering out-of-domain adaptation. To address this, we present B2NERD, a compact dataset designed to guide LLMs' generalization in Open NER under a universal entity taxonomy. B2NERD is refined from 54 existing English and Chinese datasets using a two-step process. First, we detect inconsistent entity definitions across datasets and clarify them by distinguishable label names to construct a universal taxonomy of 400+ entity types. Second, we address redundancy using a data pruning strategy that selects fewer samples with greater category and semantic diversity. Comprehensive evaluation shows that B2NERD significantly enhances LLMs' Open NER capabilities. Our B2NER models, trained on B2NERD, outperform GPT-4 by 6.8-12.0 F1 points and surpass previous methods in 3 out-of-domain benchmarks across 15 datasets and 6 languages. The data, models, and code are publicly available at https://***/UmeanNever/B2NER. © 2025 Association for Computational Linguistics.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Multiscale Temporal-Convolution and Attention Improved Neural Network for Biased Mental State Recognition 17th

Multiscale Temporal-Convolution and Attention Improved Neur...

引用

17th International Conference on Brain Informatics, BI 2024

作者： Zuo, Guoyu Xiao, Erjun Zhang, Tielin Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing University of Technology Beijing100124 China Center for Excellence in Brain Science and Intelligence Technology University of Chinese Academy of Sciences Shanghai200031 China

ISBN: (纸本)9789819632930

Accurate detection of mental state is vital for sleep assessment and anesthesia monitoring. However, challenges exist, including 1) limited data sources caused by few modalities, few channels, biased sample distribution, or large individual differences;2) multiscale dynamic feature of mental state signals, containing complex and dynamic fluctuations. In this paper, we proposed a multiscale temporal convolution and attention improved neural network (MTA-NN) to handle these two challenges, including: a preprocessing method using a clustering-first and label-generation approach for data augmentation involves filtering the production samples to mitigate the impact of noise on model performance;multiscale temporal-convolution module for detecting different scales of temporal and frequency features;an attention module for decoding key features in different spatial and temporal channels, and for setting the importance of historical dependencies;a full-connection layer is designed to recognize different sleep stage. The proposed MTA-NN is then verified in three typical sleep-state recognition tasks, including SleepEDF-20, SleepEDF-78, and ISRUC3. Compared to some state-of-the-art algorithms, the proposed MTA-NN achieves higher performance. Further ablation experiments show the necessary and importance of these designed sub modules in MTA-NN. We consider the same algorithm can also be extended to further similar mental state recognition tasks such as anesthesia monitoring. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Anesthesiology

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Consensus of Second-Order Multiagent systems With Input Saturation via Hybrid Sliding-Mode Control

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 14623-14632页

作者： Jiang, Xiaowei Jiao, Ranran Li, Bo Zhang, Xianhe Yan, Huaicheng China University of Geosciences School of Automation Wuhan430079 China Ministry of Education Hubei Key Laboratory of Advanced Control and Intelligent Automation of Complex Systems Engineering Research Center of Intelligent Geodetection Technology Wuhan430074 China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai200240 China Anhui University of Finance and Economics School of Finance Bengbu233030 China Hubei Normal University School of Electrical Engineering and Automation Huangshi435002 China Ministry of Education East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai200237 China

This paper addresses the finite-time consensus (FTC) issue for second-order multi-agent systems (MASs) with nonlinear disturbances. To tackle the challenges posed by increasingly complex communication environments, an innovative integral sliding-mode surface is designed using event-triggered control. Furthermore, the study explores communication constraints between the leader and followers, employing impulsive control to facilitate communication only at specific intervals. A novel hybrid integral sliding-mode control protocol is advanced for the second-order MASs, which effectively eliminates the "Zeno phenomenon" and notably reduces both communication frequency and energy consumption, thereby enhancing overall communication efficiency. Ultimately, the efficacy of the put forward protocol is verified through simulation examples including comparison experiment. © 2004-2012 IEEE.

关键词： Protocols Sliding mode control Event detection Multi-agent systems Costs Training Topology Switches Sufficient conditions Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Features Fusion for Zero-Shot Object Pose Estimation 26

Multi-Level Features Fusion for Zero-Shot Object Pose Estima...

引用

26th International Conference on Industrial Technology, ICIT 2025

作者： Huang, Nanxin Xu, Chi School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

ISBN: (纸本)9798331521950

Driven by advancements in industrial production and artificial intelligence, the need for pose estimation of new ob-jects in areas like robotic manipulation and virtual reality is increasing. We introduce a zero-shot object pose estimation approach that identifies the poses of objects excluded from the training dataset, removing the requirement for re-modeling. The method is built around a multi-level features fusion framework de-signed to enhance generalization. First, a trainable feature extraction module filters and selects multi-level features extracted by the backbone network. Unlike traditional convolutional ker-nels, we incorporate a dynamic convolution kernel to enhance the feature extraction capability. Second, in the feature fusion module, we adopt a dynamic weight generation strategy to perform weighted fusion of multi-level features. This method enhances template matching by effectively describing similarities between unseen objects (those absent from the training set) and templates, leveraging robust and adaptive feature representations to narrow the gap with seen objects. Experimental results demonstrate that our approach achieves state-of-the-art performance on two popu-lar benchmark datasets, LineMod and LineMod-Occlusion, proves that our method has better generalization than previous models. © 2025 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

An Isochron-Based Solution to Pursuit–Evasion Games of Two Heterogeneous Players

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 2811-2826页

作者： Li, Shuai Wang, Chen Xie, Guangming Peking University State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Beijing100871 China Peking University National Engineering Research Center of Software Engineering Beijing100871 China Peking University Center for Multi-Agent Research Institute for Artificial Intelligence Beijing100871 China

In this article, we study a pursuit–evasion game between two players with heterogeneous kinematics, where the pursuer is with damped double-integrator dynamics and the evader is with single-integrator dynamics. The pursuer aims at capturing the evader as soon as possible, while the evader wants to avoid or delay the capture. Traditional methods to solve pursuit–evasion games rely on the Hamilton–Jacobi–Isaacs (HJI) equations and retrogressive path equations, which are very complicated and nonintuitive, thus failing to obtain a complete solution. To overcome these challenges, we develop an intuitive isochron-based method to thoroughly analyze all possible situations of the game and a concise geometric approach to calculate the optimal strategies, providing a complete solution to this game. Specifically, the isochron-based method effectively leverages three main factors: the players' motion capability, the pursuer's capture capability, and the players' states. Based on these, we analyze the players' superiority and the geometrical features of their isochrones and the intersections, thus acquiring concise conditions that determine the game's outcome. For the success-capture cases, we propose a new geometric approach to calculate the target points of the players and then obtain the closed-loop state feedback optimal pursuit and evasion strategies. We then get the corresponding value function and provide a validation using the HJI equation. For the success-evasion cases, we exploit the intersection of the players' isochrones to design some effective evasion strategies, which ensure that the evader can always avoid or delay the capture. Finally, some numerical simulations are carried out to validate the effectiveness and applicability of our results. © 1963-2012 IEEE.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Distributed Task Allocation With Minimum Makespan for Heterogeneous Multiplayer Pursuit–Evasion Games

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 2827-2842页

作者： Li, Shuai Wang, Chen Sun, Jinan Zhang, Shikun Xie, Guangming Peking University State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Beijing100871 China Peking University National Engineering Research Center of Software Engineering Beijing100871 China Peking University Center for Multi-Agent Research Institute for Artificial Intelligence Beijing100871 China

In the domain of multiplayer pursuit–evasion games, it is crucial to address the practical aspects of the players' heterogeneity, the distributed control manner, and the pursuers' goal of minimum makespan. However, the three topics have received limited attention in existing literature, both separately and in combination. In this article, we address the multiplayer pursuit–evasion game integrating these key topics, where the pursuers with simple motions strive to capture as many evaders, characterized by damped double integrators, as possible, meanwhile minimizing the task makespan. To this end, we establish an overall framework and sequentially tackle four key issues, leading to an effective solution to the entire problem. We first propose a novel isochron-based method to derive the capture condition and acquire the optimal pursuit and evasion strategies. Then, we enhance the usability of the capture condition by geometrically deriving the analytical form of the pursuer's winning region with respect to a given evader. Third, leveraging the concept of winning regions, we determine the lower boundary of pursuers' sensing range, ensuring sufficient information acquisition for evader allocation while avoiding selection conflicts. Finally, we propose a fully distributed allocation algorithm for each pursuer allowing the pursuer team to converge to the optimal evader allocation. By combining these contributions, we successfully provide an effective solution to the entire problem. Various simulations are conducted to show the effectiveness of our proposed methods. © 1963-2012 IEEE.

关键词： Games Resource management Sensors Robot sensing systems Mathematical models Heuristic algorithms Decentralized control Usability Biomimetics Topology

来源：评论

学校读者我要写书评

暂无评论

Influence Enhanced Sparse Coordination Graphs for Multi-Agent Reinforcement Learning

引用

Neural Networks 2025年 188卷 107454页

作者： Zhang, Xiwen Chen, Jie Gan, Ming-Gang Chen, Haoxiang State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

In contemporary Multi-Agent Reinforcement Learning (MARL), effectively enhancing the expressive capacity of value functions has been a persistent research focus. Many studies have employed value decomposition methods;however, due to the neglect of inter-agent collaboration, these methods fall short of achieving optimal performance. Subsequent research introduced coordination graphs into value decomposition methods;nevertheless, these approaches often rely on simplistic rules to evaluate inter-agent collaboration and fail to adequately describe the collaborative relationships of agents in complex environments. Consequently, we propose Influence Enhanced Sparse Coordination Graphs (IESCG) as a solution to provide insights into the aforementioned problem. In this study, we propose influence networks as quantitative descriptions of the importance of collaboration among agents, utilizing them as crucial basis for constructing the topology of Sparse Time-Varying Coordination Graphs. Additionally, we propose Recurrent Payoff Function Networks (RPFN) to incorporate temporal information while providing necessary input to influence networks. Furthermore, Sparse Graph Advantage Selection Coefficients (SGASC) are introduced to stabilize the overall value function across different time steps, ensuring training stability. Experimental investigations conducted on the StarCraft II micromanagement and MACO benchmark indicate that our algorithm not only accelerates convergence and improves winning probabilities but also exhibits more pronounced advantages in complex scenarios. © 2025

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Efficient Facial Expression Recognition Network Based on Spot-Adaptive Knowledge Distillation 26

Efficient Facial Expression Recognition Network Based on Spo...

引用

26th International Conference on Industrial Technology, ICIT 2025

作者： Wen, Xin Liu, Zhen-Tao Chen, Dan School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China

ISBN: (纸本)9798331521950

Facial expression recognition plays a key role in promoting the development of comprehensive intelligence and building friendly human-computer interaction. Due to the interference of feature noise in expression data, the lightweight facial expression recognition model with fewer parameters is difficult to learn more expression features through simple training, which limits the improvement of its recognition performance. An efficient facial expression recognition network based on Spot-adaptive Knowledge Distillation is proposed in this paper. Inspired by VoVNetV2, the network designed in this paper is lightweightly improved using Depthwise Separable Convolution and the parameter-free SimAM attention mechanism, reducing the number of parameters to 0.21 M. To further improve the recognition accuracy of the model, Spot-adaptive Knowledge Distillation is employed to improve the characterization ability of the model. The recognition accuracies of the student network designed in this paper on the KDEF and RAF-DB datasets are 93.05% and 81.17% respectively after spot-adaptive distillation. © 2025 IEEE.

关键词： Facial Expression Recognition Knowledge Distillation Lightweight Neural Network

来源：评论

学校读者我要写书评

暂无评论

A PARALLEL DOMAIN DECOMPOSITION METHOD FOR SOLVING ELLIPTIC EQUATIONS ON MANIFOLDS

引用

SIAM Journal on Scientific computing 2025年第2期47卷 A916-A942页

作者： Qin, Lizhen Wang, Feng Wang, Yun School of Mathematics Nanjing University Nanjing210093 China Key Laboratory of Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Ministry of Education Nanjing210023 China Jiangsu International Joint Laboratory of Big Data Modeling Computing and Application Nanjing Normal University Nanjing210023 China School of Mathematical Sciences Nanjing Normal University Nanjing210023 China School of Mathematical Sciences Center for Dynamical Systems and Differential Equations Soochow University Suzhou215006 China

We propose a new numerical domain decomposition method for solving elliptic equations on compact Riemannian manifolds. One advantage of this method is its ability to bypass the need for global triangulations or grids on the manifolds. Additionally, it features a highly parallel iterative scheme. To verify its efficacy, we conduct numerical experiments on some four-dimensional manifolds without and with boundary. © 2025 Society for Industrial and Applied Mathematics Publications. All rights reserved.

关键词： Domain decomposition methods

来源：评论

学校读者我要写书评

暂无评论

Directed Brain Network Transformer for Psychiatric Diagnosis 27th

Directed Brain Network Transformer for Psychiatric Diagnosis

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhu, Xu Qi, Zhiwei Yue, Kun Su, Yunshan Duan, Liang School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China School of Education Yunnan University Kunming China Department of Radiology Affiliated Hospital of Yunnan University Kunming China

ISBN: (纸本)9783031781940

Human brain is a complex organ that consists of billions of neurons and trillions of connections among the neurons. To describe the correlations among the time series of the brain regions, we model the brain as a functional brain network to diagnose psychosis. However, traditional methods of functional brain network construction are usually noisy and do not consider the causal relationships among brain regions. To obtain the causal relationships and improve diagnosis interpretability, we propose a directed brain network Transformer (DBNT) for psychiatric diagnosis. First, the causal relationships in the blood-oxygen-level-dependent time series of brain regions are extracted to generate a directed brain network. Then, the feature encoding method is proposed to obtain local and global features of the brain networks by using the DBNT. Experimental results demonstrate that the accuracy of DBNT increases by 8.1% and 6.4% compared to state-of-the-art methods on two large-scale brain network datasets. DBNT also highlights the brain regions associated with psychosis and provides interpretation for diagnosis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Network coding

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：