检索结果-内蒙古大学图书馆

Robust Motion-Guided Frame Sampler with Interpretive Evaluation for Video Action Recognition

IEEE Transactions on Mobile Computing 2025年

作者： Bai, Jing Zhang, Yuxiang Wang, Yiran Xiao, Zhu Xiong, Yong Jiao, Licheng Xidian University School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xi'an710071 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Hunan Lianzhi Technology Co. Ltd Changsha410200 China

Due to the presence of redundancy and interference, frame sampling is a promising but challenging solution to mitigate the expensive computation of video action recognition. Although the motion prior has shown great potential for frame selection, existing motion-based strategies suffer from limitations in terms of robustness and interpretive evaluation. In this paper, we devise a robust frame sampling strategy called positive motion guided sampler (PMGSampler). It consists of two procedures, local motion capture and global motion statistics. At the local level, we propose two concepts about inter-frame motion amplitude and motion continuity, which helps to perceive the movement of subjects and identify abnormal events that may generate negative pseudo-motion information. Then, through a global analysis of the obtained local motions, the sampler becomes more sensitive to informative frames and robust to outliers. The proposed sampler can be applied to most existing models for improving recognition accuracy. We conduct extensive experiments on four widely-used benchmarks to demonstrate the superiority of our PMGSampler over other methods of the same type. In addition, to analyse how sampled frames influence action recognition, we present a visual interpretation method for video models, termed as spatio-temporal class activation map (STCAM). By introducing spatial and temporal branches, our STCAM is able to visualise the salience of spatio-temporal features. With the help of STCAM, we can further intuitively evaluate the performance of different sampling strategies. Code is available at https://***/zyx-cv/PMGSampler. © 2002-2012 IEEE.

关键词： Motion capture

来源：评论

学校读者我要写书评

暂无评论

Switching Controllability for SiC JFET/Si IGBT Cascode with External Absorption and Boost Capacitors

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Wu, Zhenhui Zeng, Rongzhou Lei, Shengchang Liao, Linyuan Li, Junhong Wu, Jipeng Tan, Hua Hu, Zhengquan Miao, Jiayi Hunan University of Technology College of Traffic Engineering Zhuzhou412007 China University of Electronic Science and Technology of China State Key Laboratory of Electronic Thin Films and Integrated Devices Chengdu610054 China

Silicon-based insulated gate bipolar transistor (Si IGBT) is a crucial device in high-power systems. However, the enormous switching loss (ESW) has always been the primary problem that limits its applications. To reduce ESW, inspired by the SiC JFET/Si MOSFET Cascode (SSMC), a SiC JFET and low voltage Si IGBT Cascode (***) is proposed and validated by experiment and technology computer aided design (TCAD) simulation . In the ON-state, due to the bipolar conduction mode, the *** has stronger current conductivity than SSMC. But the tail current (Itail) is still serious during turn-off transient. To optimize the switching transient and eliminate Itail, an absorption capacitor (CA) and a boost capacitor (CB) are adopted in ***. Through switch characteristic testing, the proposed *** with CA and CB is verified. The research results show that the ESW of *** is 42.5% lower than that of conventional Si IGBT at 600 V/60 A. At the current of 80 A and switching frequency of 200 kHz, the power loss of *** is 26.8% and 6.9% lower than that of the SiC MOSFET and SSMC, respectively. Additionally, In boost circuit testing, under a duty cycle of 70% and working current of 20 A, the *** achieves similar conversion efficiency to SiC MOSFET. The advantage become more apparent as the operating current increases. © 2013 IEEE.

关键词： Insulated gate bipolar transistors (IGBT)

来源：评论

学校读者我要写书评

暂无评论

Exploring Communication-efficient Federated Learning via Stateless In-network Aggregation

引用

IEEE Transactions on Mobile Computing 2025年

作者： Xia, Junxu Cheng, Geyao Wu, Wenfei Luo, Lailong Guo, Deke National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha Hunan410073 China National University of Defense Technology State Key Laboratory of Complex & Critical Software Environment College of Information and Communication Changsha Hunan410073 China Peking University School of Computer Science Beijing100091 China

As an ambitious training paradigm, federated learning has garnered increasing attention in recent years, which enables collaborative training of a global model without accessing users' private data. However, due to the simultaneous and constant model updates gathering from massive distributed clients, the central server generally becomes a performance bottleneck. Additionally, the stateful aggregation (retaining all the updates from each client) conducted by the central server further poses potential threats to privacy, since it may recover the raw data based on such model updates inversely. The state-of-the-art methodologies, however, fail to address these two problems concurrently and efficiently. To this end, we propose GAIN, a secure aggregation acceleration service for federated learning. At its core, GAIN leverages programmable switches deployed at the edge network to aggregate model updates in a stateless manner before transmitting them to the central server. Consequently, GAIN can accelerate the transmission and aggregation of model updates while eliminating the chance of recovering private data. We evaluate the performance of GAIN through FPGA-based experiments and large-scale simulations. The results show that GAIN can effectively reduce bandwidth overhead and achieve up to 4.11× training throughput acceleration while prioritizing privacy protection. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph 25

Way to Specialist: Closing Loop Between Specialized LLM and ...

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1

作者： Yutong Zhang Lixing Chen Shenghong Li Nan Cao Yang Shi Jiaxin Ding Zhe Qu Pan Zhou Yang Bai School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China College of Design and Innovation Tongji University Shanghai China John Hopcroft Center for Computer Science Shanghai Jiao Tong University Shanghai China School of Computer Science and Engineering Central South University Changsha Hunan China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan Hubei China Department of Automation Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798400712456

Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks necessitating specialized knowledge, e.g., emotional sociology and medicine. Prior investigations into specialized LLMs focused on domain-specific training, which entails substantial efforts in domain data acquisition and model parameter fine-tuning. To address these challenges, this paper proposes the Way-to-Specialist (WTS) framework, which synergizes retrieval-augmented generation with knowledge graphs (KGs) to enhance the specialized capability of LLMs in the absence of specialized training. In distinction to existing paradigms that merely utilize external knowledge from general KGs or static domain KGs to prompt LLM for enhanced domain-specific reasoning, WTS proposes an innovative ''LLM↻KG'' paradigm, which achieves bidirectional enhancement between specialized LLM and domain knowledge graph (DKG). The proposed paradigm encompasses two closely coupled components: the DKG-Augmented LLM and the LLM-Assisted DKG Evolution. The former retrieves question-relevant domain knowledge from DKG and uses it to prompt LLM to enhance the reasoning capability for domain-specific tasks; the latter leverages LLM to generate new domain knowledge from processed tasks and use it to evolve DKG. WTS closes the loop between DKG-Augmented LLM and LLM-Assisted DKG Evolution, enabling continuous improvement in the domain specialization as it progressively answers and learns from domain-specific questions. We validate the performance of WTS on 7 datasets (e.g., TweetQA, ChatDoctor5k) spanning 6 domains, e.g., emotional sociology, medical, ect. The experimental results show that WTS surpasses the previous SOTA in 5 specialized domains, and achieves a maximum performance improvement of 11.3%.

关键词： domain knowledge graph

来源：评论

学校读者我要写书评

暂无评论

I-Card: A Generative AI-Supported Intelligent Design Method Card Deck 25

I-Card: A Generative AI-Supported Intelligent Design Method ...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Liuqing Chen Wengteng Cheang Zhaojun Jiang Yuan Xu Zebin Cai Lingyun Sun Peter Childs Ji Han Preben Hansen Haoyu Zuo College of Computer Science and Technology Zhejiang University Hangzhou Zhejiang China School of Computer Science and Engineering Central South University Changsha Hunan China International Design Institute Zhejiang University Hangzhou Zhejiang China Dyson School of Design Engineering Imperial College London London United Kingdom Department of Innovation Technology and Entrepreneurship University of Exeter Exeter United Kingdom Dept of Computer and Systems Sciences Stockholm University Kista Sweden

来源：评论

学校读者我要写书评

暂无评论

An Adaptive and Scalable Framework for Resource-Efficient Deployment of Mixture of Experts in LLM-Based Intelligent IoT Networks

引用

IEEE Internet of Things Journal 2025年

作者： Liu, Chengxu Li, Yangfan Chen, Cen Zou, Xiaofeng Kuang, HaiLan Ma, Xiaolin Lu, Zeyu Zhang, Zhaoyuan Liu, Jing Liu, Xinhua Central South University School of Computer Science and Engineering Changsha410083 China Wuhan University of Technology School of Information Engineering Wuhan430000 China South China University of Technology School of Future Technology Guangzhou510641 China Pazhou Laboratory Guangzhou510335 China School of Information Engineering of Wuhan University of Technology Wuhan430000 China Guilin University of Electronic Technology Computer and Information Security Department Guilin China Hunan Post and Telecommunication College China

The exponential growth of the Internet of Things (IoT) necessitates the deployment of large-scale models capable of processing the complex and diverse data generated by IoT devices. However, the substantial memory requirements of these models pose significant challenges, especially in scenarios where rapid decision-making and low-latency responses are critical. To address these challenges, we propose three innovative strategies for optimizing large model usage in IoT environments. The first strategy is an adaptive loading scheme, which enables dynamic loading of individual model experts. The second strategy involves an expert-by-expert loading approach, further enhancing the ability to load experts as needed, which optimizes memory usage and accelerates computations. The third strategy employs an inter-layer expert reuse mechanism, facilitating the efficient reuse of experts across different layers, thus enhancing response rates without compromising model accuracy. Importantly, these strategies can be directly applied to Mixture of Experts (MoE) large language models without requiring additional training, thereby providing a seamless and efficient solution for leveraging these models in memory-constrained, high-performance IoT environments. © 2014 IEEE.

关键词： Constraint Hierarchical Storage Large-parameter Memory Requirement Model Resource Reuse Rate

来源：评论

学校读者我要写书评

暂无评论

engineering of topological tunneling transistors via quantum point contact

引用

Physical Review Applied 2025年第3期23卷 034074-034074页

作者： Gongwei Hu Jiaqi Yang Haozhen Chen Min Liu Shuaiwei Fan Fobao Huang Qiao Chen Minjiang Dan Hubei Engineering Research Center of Weak Magnetic-field Detection College of Science China Three Gorges University Yichang 443002 China College of Hydraulic & Environmental Engineering China Three Gorges University Yichang 443002 China School of Microelectronics Northwestern Polytechnical University Xi’an 710072 China Yangtze River Delta Research Institute of NPU Northwestern Polytechnical University Taicang 215400 China School of Computational Science and Electronics the lnnovation Institute of Advanced Functional Materials Hunan Institute of Engineering Xiangtan 411104 China Joint Laboratory for Extreme Conditions Matter Properties School of Mathematics and Physics Southwest University of Science and Technology Mianyang 621010 China

Owing to the versatile transport process, tunneling transistors (TTs) have become important building blocks for modern electronic, optoelectronic, and magnetic technologies. Although various TTs have been developed, their device operation still has challenges in terms of stability and reliability due to the tunneling process being susceptible to material size and interface scatterings. The robust edge channels in a topological insulator (TI) hold novel tunneling physics, but their TTs are still lacking. In this theoretical work, we propose topological tunneling and resonant TTs by using edge states (ESs) as transport channels in the quantum point contact (QPC) constriction. The finite size effect is the key to adjusting the band structure and tunneling barrier height of ESs by controlling the QPC width. By using the Bernevig-Hughes-Zhang (BHZ) model, we explore the single-QPC tunneling and double-QPC resonant tunneling transport, as well as their device characteristics via the quantum transport Kwant package. Topological TTs based on a single QPC possess excellent gate-modulated capability as well as a size-dependent current sensitivity of 0.1nm−1, several orders of magnitude lower than the conventional TTs. The transport results show that the tunneling probability is significantly influenced by the QPC width (barrier height) but is weakly dependent on the QPC length (barrier width). Moreover, topological resonant TTs are designed in a double-QPC structure and show a negative differential resistance with a large peak-valley current ratio (>104). The transmission spectrum exhibits multiple peaks due to the resonant tunneling driven by quantum well states. The distance between two QPCs can shift these resonant peaks by modulating the transverse confined effect. This study opens a window for designing stable, reliable, and high-performance tunneling devices via emerging quantum materials with great potential for low-power topological electronics applications.

关键词： Semiconductor quantum wells

来源：评论

学校读者我要写书评

暂无评论

Optimal Parameter Adaptation for Safety-Critical Control via Safe Barrier Bayesian Optimization

arXiv

引用

arXiv 2025年

作者： Wang, Shengbo Li, Ke Yan, Zheng Guo, Zhenyuan Zhu, Song Wen, Guanghui Wen, Shiping School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China Department of Computer Science University of Exeter ExeterEX4 4RN United Kingdom Australian AI Institute Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia College of Mathematics and Econometrics Hunan University Changsha410082 China School of Mathematics China University of Mining and Technology Xuzhou221116 China Department of Systems Science School of Mathematics Southeast University Nanjing China

Safety is of paramount importance in control systems to avoid costly risks and catastrophic damages. The control barrier function (CBF) method, a promising solution for safety-critical control, poses a new challenge of enhancing control performance due to its direct modification of original control design and the introduction of uncalibrated parameters. In this work, we shed light on the crucial role of configurable parameters in the CBF method for performance enhancement with a systematical categorization. Based on that, we propose a novel framework combining the CBF method with Bayesian optimization (BO) to optimize the safe control performance. Considering feasibility/safety-critical constraints, we develop a safe version of BO using the barrier-based interior method to efficiently search for promising feasible configurable parameters. Furthermore, we provide theoretical criteria of our framework regarding safety and optimality. An essential advantage of our framework lies in that it can work in model-agnostic environments, leaving sufficient flexibility in designing objective and constraint functions. Finally, simulation experiments on swing-up control and high-fidelity adaptive cruise control are conducted to demonstrate the effectiveness of our framework. Copyright © 2025, The Authors. All rights reserved.

关键词： Adaptive cruise control

来源：评论

学校读者我要写书评

暂无评论

A Low Cost Triple-Node-Upset Self-Recoverable Latch Design for Nanoscale CMOS

引用

IEEE Transactions on Device and Materials Reliability 2025年

作者： Bai, Na Zhang, Pengshuai Xu, Yaohua Guo, Yunhui Li, Hang Wang, Yi Wen, Xiaoqing Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Hefei230601 China National University of Defense Technology College of Computers Hunan Changsha410073 China Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering Fukuoka8208502 Japan

Due to the constant reduction of semiconductor feature sizes, the charge sharing effect is getting worse. The occurrence probability of triple-node upset (TNU), which has a significant impact on the circuit’s reliability, is rising in nanoscale digital circuits. This paper proposes a low overhead and TNU self-recovery latch (TNU-SR) based on the 28 nm CMOS technology to efficiently tolerate TNU and reduce the power dissipation and latency of the latch. The latch design proposed in this article adopts stacked transistors to reduce sensitive nodes and area overhead. The TNU-SR latch uses clock gating and high-speed transfer path technology, resulting in low power dissipation and low delay. For simulation results, compared with existing latches, it can be known that the TNU-SR latch performs well in terms of delay, power consumption, and area, so it is a good choice for radiation-hardened design for space applications. In addition, compared with the latest TNU self-recovery latch (HLTNURL), the TNU-SR latch proposed in this paper reduces the Power-Area-Delay Product (PADP) metric by 111.13%. © 2001-2011 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

TS-CGNet: Temporal-Spatial Fusion Meets Centerline-Guided Diffusion for BEV Mapping

arXiv

引用

arXiv 2025年

作者： Hong, Xinying Li, Siyu Zeng, Kang Shi, Hao Peng, Bomin Yang, Kailun Li, Zhiyong The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China

Bird’s Eye View (BEV) perception technology is crucial for autonomous driving, as it generates top-down 2D maps for environment perception, navigation, and decision-making. Nevertheless, the majority of current BEV map generation studies focusing on visual map generation lack depth-aware reasoning capabilities. They exhibit limited efficacy in managing occlusions and handling complex environments, with a notable decline in perceptual performance under adverse weather conditions or low-light scenarios. Therefore, this paper proposes TS-CGNet, which leverages Temporal-Spatial fusion with Centerline-Guided diffusion. This visual framework, grounded in prior knowledge, is designed for integration into any existing network for building BEV maps. Specifically, this framework is decoupled into three parts: Local mapping system involves the initial generation of semantic maps using purely visual information;The Temporal-Spatial Aligner Module (TSAM) integrates historical information into mapping generation by applying transformation matrices;The Centerline-Guided Diffusion Model (CGDM) is a prediction module based on the diffusion model. CGDM incorporates centerline information through spatial-attention mechanisms to enhance semantic segmentation reconstruction. We construct BEV semantic segmentation maps by our methods on the public nuScenes and the robustness benchmarks under various corruptions. Our method improves 1.90%, 1.73%, and 2.87% for perceived ranges of 60×30m, 120×60m, and 240×60m in the task of BEV HD mapping. TS-CGNet attains an improvement of 1.92% for perceived ranges of 100×100m in the task of BEV semantic mapping. Moreover, TS-CGNet achieves an average improvement of 2.92% in detection accuracy under varying weather conditions and sensor interferences in the perception range of 240×60m. The source code will be publicly available at https://***/krabs-H/TS-CGNet. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision making

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：