检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Xiong, Zeyu Liu, Daizong Zhou, Pan Zhu, Jiahao Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Peking University Wangxuan Institute of Computer Technology China

ISBN: (纸本)9781728163277

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video. Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Specifically, we propose a novel Temporal Sentence Tracking Network (TSTNet), which contains (A) a Cross-modal Targets Generator to generate multi-modal templates and search space, filtering objects and activities, and (B) a Temporal Sentence Tracker to track multi-modal targets for modeling the targets' behavior and to predict query-related segment. Extensive experiments and comparisons with state-of-the-arts are conducted on challenging benchmarks: Charades-STA and TACoS. And our TSTNet achieves the leading performance with a considerable real-time speed. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation for Large-Vocabulary Object Detectors 38

Domain Adaptation for Large-Vocabulary Object Detectors

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jiang, Kai Huang, Jiaxing Xie, Weiying Lei, Jie Li, Yunsong Shao, Ling Lu, Shijian State Key Laboratory of Integrated Services Networks Xidian University Xi'an710071 China S-Lab School of Computer Science and Engineering Nanyang Technological University Singapore School of Electrical and Data Engineering The University of Technology Sydney Australia UCAS-Terminus AI Lab University of Chinese Academy of Sciences China

Large-vocabulary object detectors (LVDs) aim to detect objects of many categories, which learn super objectness features and can locate objects accurately while applied to various downstream data. However, LVDs often struggle in recognizing the located objects due to domain discrepancy in data distribution and object vocabulary. At the other end, recent vision-language foundation models such as CLIP demonstrate superior open-vocabulary recognition capability. This paper presents KGD, a knowledge Graph Distillation technique that exploits the implicit knowledge graphs (KG) in CLIP for effectively adapting LVDs to various downstream domains. KGD consists of two consecutive stages: 1) KG extraction that employs CLIP to encode downstream domain data as nodes and their feature distances as edges, constructing KG that inherits the rich semantic relations in CLIP explicitly;and 2) KG encapsulation that transfers the extracted KG into LVDs to enable accurate cross-domain object classification. In addition, KGD can extract both visual and textual KG independently, providing complementary vision and language knowledge for object localization and object classification in detection tasks over various downstream domains. Experiments over multiple widely adopted detection benchmarks show that KGD outperforms the state-of-the-art consistently by large margins. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning Approach for Cooperative Target Defense 7th

A Deep Reinforcement Learning Approach for Cooperative Targ...

引用

7th International Conference on data Mining and Big data, DMBD 2022

作者： Xiong, Yanxue Wang, Zhigang Ke, Liangjun State Key Laboratory for Manufacturing Systems Engineering School of Automation Science and Engineering Xi’an Jiaotong University Xi’an China CETC Key Laboratory of Data Link Technology Xi’an Xi’an China

ISBN: (纸本)9789811992964

This paper considers a new variant of the pursuit-evasion problem, called the cooperative target defense problem with three agents (attacker, targeter, and defender) in a 3D space. The targeter tries to fly as quickly as possible from a starting point to the terminal, while the defender seeks to protect it from the attacker. The problem is difficult to solve under traditional game theory methods, while deep reinforcement learning (DRL) has shown strong adaptability in these complex and higher-dimensional tasks. Inspired by the successful applications of Proximal Policy Optimization (PPO), this paper proposes a PPO-based algorithm for the problem, intending to derive the optimal behavioral policies for both sides. We design the corresponding state space, action space, and rewards of the agents. Three kinds of reward functions are proposed for the attacker and compared by experimental results. Our study provides a good foundation for the cooperative target defense problem. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on active defense decision-making method for cloud boundary networks based on reinforcement learning of intelligent agent

引用

High-Confidence Computing 2024年第2期4卷 50-61页

作者： Huan Wang Yunlong Tang Yan Wang Ning Wei Junyi Deng Zhiyan Bin Weilong Li School of Computer Science and Technology Guangxi University of Science and TechnologyLiuzhou 545000China Liuzhou Key Laboratory of Big Data Intelligent Processing and Security Liuzhou 545000China Guangxi Education System Network Security Monitoring Center Liuzhou 545000China Center of Graphics and Information Guangxi ECO-Engineering Vocational&Technical CollegeLiuzhou 545004China

The cloud boundary network environment is characterized by a passive defense strategy,discrete defense actions,and delayed defense feedback in the face of network attacks,ignoring the influence of the external environment on defense decisions,thus resulting in poor defense ***,this paper proposes a cloud boundary network active defense model and decision method based on the reinforcement learning of intelligent agent,designs the network structure of the intelligent agent attack and defense game,and depicts the attack and defense game process of cloud boundary network;constructs the observation space and action space of reinforcement learning of intelligent agent in the non-complete information environment,and portrays the interaction process between intelligent agent and environment;establishes the reward mechanism based on the attack and defense gain,and encourage intelligent agents to learn more effective defense *** designed active defense decision intelligent agent based on deep reinforcement learning can solve the problems of border dynamics,interaction lag,and control dispersion in the defense decision process of cloud boundary networks,and improve the autonomy and continuity of defense decisions.

关键词： Active defense decision-making Cloud boundary network security Intelligent agent reinforcement learning Offensive and defensive game

来源：评论

学校读者我要写书评

暂无评论

An Adjusted Gray Map Technique for Constructing Large Four-Level Uniform Designs

引用

Journal of Systems Science & Complexity 2023年第1期36卷 433-456页

作者： ELSAWAH A M VISHWAKARMA G K MOHAMED H S FANG Kai-Tai Department of Statistics and Data Science Faculty of Science and TechnologyBeijing Normal University-Hong Kong Baptist University United International CollegeZhuhai 519087China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International CollegeZhuhai 519087China Department of Mathematics Faculty of ScienceZagazig UniversityZagazig 44519Egypt Department of Mathematics&Computing Indian Institute of Technology DhanbadDhanbad 826004India College of Transportation and Civil Engineering Fujian Agriculture and Forestry UniversityFuzhou 350002China The Key Lab of Random Complex Structures and Data Analysis The Chinese Academy of SciencesBeijing 100190China

A uniform experimental design(UED)is an extremely used powerful and efficient methodology for designing experiments with high-dimensional inputs,limited resources and unknown underlying models.A UED enjoys the following two significant advantages:(i)It is a robust design,since it does not require to specify a model before experimenters conduct their experiments;and(ii)it provides uniformly scatter design points in the experimental domain,thus it gives a good representation of this domain with fewer experimental trials(runs).Many real-life experiments involve hundreds or thousands of active factors and thus large UEDs are *** large UEDs using the existing techniques is an NP-hard problem,an extremely time-consuming heuristic search process and a satisfactory result is not *** paper presents a new effective and easy technique,adjusted Gray map technique(AGMT),for constructing(nearly)UEDs with large numbers of four-level factors and runs by converting designs with s two-level factors and n runs to(nearly)UEDs with 2^(t−1)s four-level factors and 2tn runs for any t≥0 using two simple transformation *** justifications for the uniformity of the resulting four-level designs are given,which provide some necessary and/or sufficient conditions for obtaining(nearly)uniform four-level *** results show that the AGMT is much easier and better than the existing widely used techniques and it can be effectively used to simply generate new recommended large(nearly)UEDs with four-level factors.

关键词： Aberration adjusted Gray map technique Gray map technique Hamming distance moment aberration threshold accepting algorithm uniform design

来源：评论

学校读者我要写书评

暂无评论

A dual-stream spatial-temporal detector for action recognition 4

A dual-stream spatial-temporal detector for action recogniti...

引用

4th International Conference on Computer Vision and Pattern Analysis, ICCPA 2024

作者： Wei, Pingping Li, Jiale Liu, Peiran Li, Li Xu, Yifei Wang, Ling State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiao-Tong University Xi’an710049 China School of Software Xi’an Jiao-Tong University Shaanxi Xi’an710049 China Shaanxi Joint Key Laboratory for Artifact Intelligence Shaanxi 710054 China Xi’an Key Laboratory for Social Intelligence and Complex Data Processing Shaanxi 710054 China Alltuu Inc. Zhejiang Hangzhou310000 China

ISBN: (纸本)9781510682528

In response to the issue that existing human action recognition models can not make full use of complementary information from different modalities, this thesis proposes a multi-path attention module MA to form the MA-GCN model. modalities, this thesis proposes a dual-stream human action recognition model SRHAR that fuses skeleton data and RGB data. This model utilizes LAF proposed in this thesis to fuse skeleton features and RGB features. The introduction of skeleton modality enables the RGB modality to obtain the RGB features. The introduction of skeleton modality enables the RGB modality to obtain complementary information, resulting in more accurate prediction results. This algorithm focuses more on recognition accuracy and has a slower recognition speed, but achieves leading performance in terms of accuracy on public datasets. © 2024 SPIE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Sedimentary record of climate change in a high latitude fjord—Kongsfjord

引用

Acta Oceanologica Sinica 2023年第1期42卷 91-102页

作者： Hang Wu Binbin Deng Jinlong Wang Sheng Zeng Juan Du Peng Yu Qianqian Bi Jinzhou Du State Key Laboratory of Estuarine and Coastal Research East China Normal UniversityShanghai200241China Monitoring Center of Aquatic Environment of Pearl River Basin Guangzhou510611China Research Centre for Eco-Environmental Engineering Dongguan University of TechnologyDongguan523808China Big Data Institute of Digital Natural Disaster Monitoring in Fujian Xiamen University of TechnologyXiamen361024China

The sedimentary record of climate change in the Arctic region is useful for understanding global *** is located in the subpolar region of the Arctic and is a suitable site for studying climate *** retreat is occurring in this region due to climate change,leading to an increase in meltwater outflow with a high debris *** August 2017,we collected a sediment Core Z3 from the central fjord near the Yellow River ***,we used the widely used chronology method of 210Pb,^(137)Cs,and other parameters to reflect the climate change record in the sedimentary environment of *** results showed that after the mid-late 1990s,the mass accumulation rate of this core increased from 0.10 g/(cm^(2)·a)to 0.34 g/(cm^(2)·a),while the flux of^(210)Pb_(ex)increased from 125 Bq/(m^(2)·a)to 316 Bq/(m^(2)·a).The higher sedimentary inventory of^(210)Pb_(ex)in Kongsfjord compared to global fallout might have been caused by sediment focusing,boundary scavenging,and riverine *** between the inventory of^(137)Cs and global fallout indicated that terrestrial particulate matter was the main source of^(137)Cs in fjord *** sedimentation rate increased after 1997,possibly due to the increased influx of glacial meltwater containing *** addition,the^(137)Cs activity,percentage of organic carbon(OC),and OC/total nitrogen concentration ratio showed increasing trends toward the top of the core since 1997,corresponding to a decrease in the mass balance of glaciers in the *** results ofδ^(13)C,δ^(15)N and OC/TN concentration ratio showed both terrestrial and marine sources contributed to the organic matter in Core *** relative contribution of terrestrial organic matter which was calculated by a two-endmember model showed an increased trend since *** these data indicate that global climate change has a significant impact on Arctic glaciers.

关键词： Kongsfjord radionuclide organic carbon/total nitrogen(OC/TN)concentration ratio δ^(13)C δ^(15)N sediment record climate change

来源：评论

学校读者我要写书评

暂无评论

Interest Points Analysis for Internet Forum Based on Long-Short Windows Similarity

引用

Computers, Materials & Continua 2022年第8期72卷 3247-3267页

作者： Xinghai Ju Jicang Lu Xiangyang Luo Gang Zhou Shiyu Wang Shunhang Li Yang Yang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001China School of Computing and Information Systems Singapore Management University188065Singapore College of Computer Science and Big Data Fuzhou UniversityFuzhou350116China

For Internet forum Points of Interest(PoI),existing analysis methods are usually lack of usability analysis under different conditions and ignore the long-term variation,which lead to blindness in method *** address this problem,this paper proposed a PoI variation prediction framework based on similarity analysis between long and short *** on the framework,this paper presented 5 PoI analysis algorithms which can be categorized into 2 types,i.e.,the traditional sequence analysis methods such as autoregressive integrated moving average model(ARIMA),support vector regressor(SVR),and the deep learning methods such as convolutional neural network(CNN),long-short term memory network(LSTM),Transformer(TRM).Specifically,this paper firstly divides observed data into long and short windows,and extracts key words as PoI of each ***,the PoI similarities between long and short windows are calculated for training and ***,series of experiments is conducted based on real Internet forum *** results show that,all the 5 algorithms could predict PoI variations well,which indicate effectiveness of the proposed *** the length of long window is small,traditional methods perform better,and SVR is the *** the contrary,the deep learning methods show superiority,and LSTM performs *** results could provide beneficial references for PoI variation analysis and prediction algorithms selection under different parameter configurations.

关键词： Point of interest(PoI)analysis long and short windows sequential analysis deep learning

来源：评论

学校读者我要写书评

暂无评论

An intelligent solar flare prediction model based on X-ray flux curves using Long Short-Term Memory

引用

Astronomical Techniques and Instruments 2025年第2期2卷 65-72页

作者： Yan Gao Li Zhang Long Xu College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data Guizhou UniversityGuiyang 550025China Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China

Solar flares are violent solar outbursts which have a great influence on the space environment surrounding Earth,potentially causing disruption of the ionosphere and interference with the geomagnetic field,thus causing magnetic ***,it is very important to accurately predict the time period of solar *** paper proposes a flare prediction model,based on physical images of active solar *** employ X-ray flux curves recorded directly by the Geostationary Operational Environmental Satellite,used as input data for the model,allowing us to largely avoid the influence of accidental errors,effectively improving the model prediction efficiency.A model based on the X-ray flux curve can predict whether there will be a flare event within 24 *** reverse can also be verified by the peak of the X-ray flux curve to see if a flare has occurred within the past 24 *** True Positive Rate and False Positive Rate of the prediction model,based on physical images of active regions are 0.6070 and 0.2410 respectively,and the accuracy and True Skill Statistics are 0.7590 and *** model can effectively improve prediction efficiency compared with models based on the physical parameters of active regions or magnetic field records,providing a simple method for solar flare prediction.

关键词： Neural Network Long Short-Term Memory Solar flare prediction X-ray flux curve

来源：评论

学校读者我要写书评

暂无评论

Theory of magnetism for rare-earth magnets on the Shastry-Sutherland lattice with non-Kramers ions

引用

Physical Review B 2024年第21期110卷 214410-214410页

作者： Guijing Duan Rong Yu Changle Liu School of Physics and Beijing Key Laboratory of Opto-electronic Functional Materials and Micro-nano Devices Renmin University of China Beijing 100872 China Key Laboratory of Quantum State Construction and Manipulation (Ministry of Education) Renmin University of China Beijing 100872 China School of Engineering Dali University Dali Yunnan 671003 China

Motivated by the rapid experimental progress on rare-earth Shastry-Sutherland lattice magnets, we propose a generic effective spin model that describes interacting non-Kramers local moments on the Shastry-Sutherland lattice. We point out that the local moments consist of both magnetic dipole and quadrupole components and the effective model turns out to be an extended XYZ model with an intrinsic field that accounts for the crystal field splitting. We then study the ground-state phase diagram of the model and find that pure quadrupole orders, which are invisible to conventional experimental probes, can be stabilized over a broad regime. In particular, we show that a hidden 1/3 magnetization plateau with quadrupole orders generally exists and discuss its experimental signatures. Finally, we discuss the relevance of our results to the rare-earth Shastry-Sutherland lattice magnets Pr2Ga2BeO7 and Pr2Be2GeO7.

关键词： Antiferromagnetism Exchange interaction Frustrated magnetism Magnetic anisotropy Spin dynamics

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：