检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yi Xie Yihong Lin Wenjie Cai Xuemiao Xu Huaidong Zhang Yong Du Shengfeng He South China University of Technology Independent Researcher State Key Laboratory of Subtropical Building Science Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Ministry of Education Key Laboratory of Big Data and Intelligent Robot Ocean University of China Singapore Management University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint between the query network and the larger gallery network. However, these one-to-one constraint approaches often fail to maintain retrieval order consistency, especially when the query network has limited representational capacity. To overcome this problem, we introduce the Decoupled Differential Distillation (D3still) framework. This framework shifts from absolute one-to-one supervision to optimizing the relational differences in pairwise similarities produced by the query and gallery networks, thereby preserving a consistent retrieval order across both networks. Our method involves computing a pairwise similarity differential matrix within the gallery domain, which is then decomposed into three components: feature representation knowledge, inconsistent pairwise similarity differential knowledge, and consistent pairwise similarity differential knowledge. This strategic decomposition aligns the retrieval ranking of the query network with the gallery network effectively. Extensive experiments on various bench-mark datasets reveal that D3still surpasses state-of-the-art methods in asymmetric image retrieval. Code is available at https://***/SCY-X/D3still.

关键词： Computer vision Codes Accuracy Image retrieval Pattern recognition Matrix decomposition Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Multi-source Infection Pattern Mining Algorithms over Moving Objects 25

Multi-source Infection Pattern Mining Algorithms over Moving...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Chen, Yu Dai, Hua Yang, Geng Chen, Yanli Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210003 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing210003 China

ISBN: (纸本)9781665405270

Using the trajectory data of moving objects to analyze and study the infection mode of viruses or germs has practical application value. The definition of infection pattern in existing works only considers one-to-one infection mode rather than many-to-one mode, and thus some infection events could be ignored. This paper presents multi-source infection pattern mining algorithms oriented to moving objects for the first time. The multi-source infection event (MSIE) is defined. On the basis of MSIE, the multi-source infection pattern mining algorithm (MIPM) is proposed, which uses sliding window mechanism. The sliding window is used to record the set of candidate infection source that may infect each normal object at each time point, and then the determined infection events are mined. To improve performance, an optimized mining algorithm (MIPM+) based on the R-tree index is proposed, which can reduce the number of objects to be detected at each time point. The experimental results show that our proposed multi-source infection pattern mining algorithms can mine more potential infection events. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Detecting DTI Using Graph Embedding and Multi-Head Attention Mechanism

Detecting DTI Using Graph Embedding and Multi-Head Attention...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xiaoli Chen, Yaoyu Yang, Wenli Yu, HaiPing Wu, Zimo Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan China China Graphics Society School of Information Wuhan Vocational College Professional Committee of Graphics and Big Data Wuhan China

ISBN: (纸本)9798350386226

Drug-target interaction (DTI) prediction has an important role in drug discovery, significantly expediting the drug design and development process. This paper proposes a new model, ERW-BiAN, that seamlessly integrates graph embedding representations with deep learning network. Specifically, we utilize an improved graph embedding model, ERW, to generate comprehensive feature vectors for each node within the knowledge graph. Subsequently, these feature vectors are fed into the BiAN model, which leverages an attention mechanism to assign precise weights to sequences. Experimental results demonstrate the superior accuracy and predictive prowess of ERW-BiAN in DTI prediction tasks. Furthermore, the case about COVID-19 shows that ERW-BiAN has the better application potential for predicting drug-target interactions. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

High Efficiency Harmonic Suppression Power Amplifier Design Across Quadrature Frequencies

High Efficiency Harmonic Suppression Power Amplifier Design ...

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Yonghui Song Mingming Gao Sitong Qiu Shiquan Shan Liaoning Technical University Huludao City Liaoning Province China Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications

ISBN: (数字)9798350389968

ISBN: (纸本)9798350389975

Power amplifiers play a crucial role in current wireless communication systems, where harmonic suppression has always been a key design challenge. In this paper, a harmonic suppression network is designed with an Elliptic low-pass filter prototype, which is capable of achieving harmonic suppression up to four times the frequency. The design improves the efficiency of the power amplifier to a certain extent and provides a great advantage in frequency coverage. Simulation results show that the power amplifier has a gain of more than 10.4 dB in the frequency band from 0.4 GHz to 1.6 GHz, with a maximum gain of up to 14.1 dB, and the efficiency is maintained at more than 60%, with the maximum efficiency able to reach 81.67% and the saturated output power is 39.5-42.4 dBm. The structure not only effectively suppresses harmonics, but also realizes high-efficiency power amplification in P-band and L-band. The amplifier structure designed in this paper is of great significance for wireless communication, aviation radio navigation and water mobility.

关键词： Wireless communication Harmonics suppression Time-frequency analysis Simulation Power amplifiers Radio navigation Low-pass filters

来源：评论

学校读者我要写书评

暂无评论

keypoint-based progressive chain-of-thought distillation for LLMs 24

Keypoint-based progressive chain-of-thought distillation for...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Kaituo Feng Changsheng Li Xiaolu Zhang Jun Zhou Ye Yuan Guoren Wang Beijing Institute of Technology Ant Group Beijing Institute of Technology and Hebei Province Key Laboratory of Big Data Science and Intelligent Technology

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale produced by LLMs, often facing the following challenges: (i) Tokens within a rationale vary in significance, and treating them equally may fail to accurately mimic keypoint tokens, leading to reasoning errors. (ii) They usually distill knowledge by consistently predicting all the steps in a rationale, which falls short in distinguishing the learning order of step generation. This diverges from the human cognitive progression of starting with easy tasks and advancing to harder ones, resulting in sub-optimal outcomes. To this end, we propose a unified framework, called KPOD, to address these issues. Specifically, we propose a token weighting module utilizing mask learning to encourage accurate mimicry of keypoint tokens by the student during distillation. Besides, we develop an in-rationale progressive distillation strategy, starting with training the student to generate the final reasoning steps and gradually extending to cover the entire rationale. To accomplish this, a weighted token generation loss is proposed to assess step reasoning difficulty, and a value function is devised to schedule the progressive distillation by considering both step difficulty and question diversity. Extensive experiments on four reasoning benchmarks illustrate our KPOD outperforms previous methods by a large margin.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Feng, Kaituo Li, Changsheng Ren, Dongchun Yuan, Ye Wang, Guoren Beijing Institute of Technology China ALLRIDE.AI Hebei Province Key Laboratory of Big Data Science and Intelligent Technology China

End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neural networks render them impractical for deployment on resource-constrained systems, which unavoidably requires more computational time and resources during reference. To handle this, knowledge distillation offers a promising approach that compresses models by enabling a smaller student model to learn from a larger teacher model. Nevertheless, how to apply knowledge distillation to compress motion planners has not been explored so far. In this paper, we propose PlanKD, the first knowledge distillation framework tailored for compressing end-to-end motion planners. First, considering that driving scenes are inherently complex, often containing planning-irrelevant or even noisy information, transferring such information is not beneficial for the student planner. Thus, we design an information bottleneck based strategy to only distill planning-relevant information, rather than transfer all information indiscriminately. Second, different waypoints in an output planned trajectory may hold varying degrees of importance for motion planning, where a slight deviation in certain crucial waypoints might lead to a collision. Therefore, we devise a safety-aware waypoint-attentive distillation module that assigns adaptive weights to different waypoints based on the importance, to encourage the student to accurately mimic more crucial waypoints, thereby improving overall safety. Experiments demonstrate that our PlanKD can boost the performance of smaller planners by a large margin, and significantly reduce their reference time. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence in Remote Sensing Image Registration:A survey

引用

International Journal of Automation and computing 2021年第1期18卷 1-17页

作者： Yue Wu Jun-Wei Liu Chen-Zhuo Zhu Zhuang-Fei Bai Qi-Guang Miao Wen-Ping Ma Mao-Guo Gong Key Laboratory of Big Data and Intelligent Vision School of Computer Science and TechnologyXidian UniversityXi′an 710071China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial IntelligenceXidian UniversityXi′an 710071China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic EngineeringXidian UniversityXi′an 710071China

In recent years,computational intelligence has been widely used in many fields and achieved remarkable *** computing and deep learning are important branches of computational *** methods based on evolutionary computation and deep learning have achieved good performance in remote sensing image *** paper introduces the application of computational intelligence in remote sensing image registration from the two directions of evolutionary computing and deep *** the part of remote sensing image registration based on evolutionary calculation,the principles of evolutionary algorithms and swarm intelligence algorithms are elaborated and their application in remote sensing image registration is *** application of deep learning in remote sensing image registration is also *** the same time,the development status and future of remote sensing image registration are summarized and their prospects are examined.

关键词： Computational intelligence evolutionary computation neural network deep learning remote sensing image registration

来源：评论

学校读者我要写书评

暂无评论

Improving Named Entity Recognition via Bridge-based Domain Adaptation 61

Improving Named Entity Recognition via Bridge-based Domain A...

引用

61st Annual Meeting of the the Association-for-Computational-Linguistics (ACL)

作者： Xu, Jingyun Zheng, Changmeng Cai, Yi Chua, Tat-Seng South China Univ Technol Sch Software Engn Guangzhou Guangdong Peoples R China MOE China Key Lab Big Data & Intelligent Robot SCUT Guangzhou Guangdong Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Natl Univ Singapore Sch Comp Singapore Singapore

ISBN: (纸本)9781959429623

Recent studies have shown remarkable success in cross-domain named entity recognition (cross-domain NER). Despite the promising results, existing methods mainly utilize pre-training language models like BERT to represent words. As such, the original chaotic representations may challenge them to distinguish entity types of entities, leading to entity type misclassification. To this end, we attempt to utilize contrastive learning to refine the original representations and propose a model-agnostic framework named MoCL for cross-domain NER. Additionally, we respectively combine MoCL with two distinctive cross-domain NER methods and two pre-training language models to explore its generalization ability. Empirical results on six domains show the effectiveness and good generalization ability of MoCL.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

An age-structured tuberculosis model with information and immigration:Stability and simulation study

引用

International Journal of Biomathematics 2023年第2期16卷 153-176页

作者： Lili Liu Jian Zhang Yazhi Li Xinzhi Ren Shanci Key Laboratory of Mathematical Techniques and Big Data Analysis on Disease Control and Prevention Complea Systems Research Center Shanci University Taiyuan 030006P.R.China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Province School of Mathematics and Statistics Qiannan Normal University for Nationalities Duyun 558000 P.R.China School of Mathematics and Statistics Southwest University Chongqing 400715P.R.China

This paper establishes an age-structured Tuberculosis(TB)model to investigate the joint impacts of information and immigration of population on the spread of TB ***,we show that the model is point dissipative,and the semi-flow generated by the model has the property of asymptotic smoothness,and then study the existence and global stability of positive steady state by the direct Lyapunov ***,by using Matlab software,we verify the theoretical results,and further explore the influence of information(including information coverage and disease-related memory delay)and immigration on the final size of TB *** simulation results show that both information coverage and immigration are positive correlated with the final size of disease,and disease-related memory delay can affect the arrival time of positive steady state,which implies us that improving information coverage,enlarging disease-related memory,and reducing the immigration of population(especially latent and infected individuals)can effectively control the progression of TB disease.

关键词： TB transmission model age-structured information-related immigration global stability.

来源：评论

学校读者我要写书评

暂无评论

Severity Assessment of Cervical Spondylotic Myelopathy Based on intelligent Video Analysis

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2022年第9期26卷 4486-4496页

作者： Zheng, Shuhao Liang, Guoyan Chen, Junying Duan, Qifei Chang, Yunbing South China Univ Technol Sch Software Engn Guangzhou 510006 Guangdong Peoples R China Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou 510006 Guangdong Peoples R China Guangdong Acad Med Sci Guangdong Prov Peoples Hosp Dept Spine Guangzhou 510080 Guangdong Peoples R China

Cervical spondylotic myelopathy (CSM) has a high incidence in the middle-aged and elderly people. According to clinical research, there is a connection between hand dexterity and cervical nerves. So the surgeon makes a preliminary assessment of the severity of CSM based on a 10-second grip and release (G&R) test. At present, the statistics of G&R test rely on the surgeon's manual counting. When a patient's hand motion speed is too fast, the surgeon's manual counting is prone to error, leading to potential misdiagnosis. On the other hand, in recent years, artificial intelligence has been developed rapidly, where three-dimensional convolutional neural networks (3D-CNNs) have been widely used in video analysis. This work proposes a hand motion analysis model using a 3D-CNN combined with a de-jittering mechanism to assess the severity of CSM on 10-second G&R videos. We collect 1500 10-second G&R videos recorded by 750 subjects to establish a dataset. The proposed model using 3D-MobileNetV2 as the classifier obtains a Levenshtein accuracy of 97.40% and an average GPU inference time of 3.31 seconds for each 10-second G&R video. Such accuracy and inference speed ensure that the proposed model can be used as a screening examination tool for CSM and a medical assistance tool to help decision making during CSM treatment planning.

关键词： Analytical models Cameras Streaming media data models Smart phones Lighting Motion segmentation 10-Second G&R test cervical spondylotic myelopathy hand motion analysis video analysis

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：