检索结果-内蒙古大学图书馆

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Wei, Yanxia Xiao, Hairong Feng, Deying Mu, Jian Yang, Jie School of Mechanical and Automotive Engineering Liaocheng University China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China Liaocheng University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)9781450396110

Recently, Discriminative Correlation Filter based trackers have increasingly become popular in the domain of visual object tracking, which is benefited by their effective and robustness in terms of tracking performance. However, the significant variations of target appearance, such as Occlusion or Deformation, always suppress the performance improvement. Although the multi-feature fusion strategy partly alleviates the above factors, the synthetic scheme also ambiguates the overall presentation ability of multiple features and results in degradation of discriminative power during classification filter learning. In this paper, we present a novel tracking framework based on the correlation filter with multiple kernel learning. Instead of directly integrating different features, we decompose a tracking process into several module, including low-dimension modules and high-dimension modules. The handcraft features extracted from low-dimension modules are robust to the small variation of target while the semantic convolutional features from the high-dimension modules can distinguish the target object from the relative complex tracking environment. In addition, we also design a reliability detection mechanism based on the confidence map to accurately measure the important degree of each kernel learning and precisely estimate the target state in the subsequent frames. For verifying our proposed tracker, we conduct extensive experiments on several standard sequence benchmark. Experiment results show that our proposed trackers perform favorably against other state-of-the-art trackers. © 2022 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Lighting control with Myo armband based on customized classifier

引用

The Journal of China Universities of Posts and Telecommunications 2022年第4期29卷 106-116页

作者： Jiang Yujian Yang Xue Zhang Junming Song Yang Key Laboratory of Acoustic Visual Technology and Intelligent Control System Communication University of ChinaBeijing 100024China Beijing Key Laboratory of Modern Entertainment Technology Communication University of ChinaBeijing 100024China School of Information and Communication Engineering Communication University of ChinaBeijing 100024China

This paper focuses on gesture recognition and interactive lighting *** collection of gesture data adopts the Myo armband to obtain surface electromyography(sEMG).Considering that many factors affect sEMG,a customized classifier based on user calibration data is used for gesture *** this paper,machine learning classifiers k-nearest neighbor(KNN),support vector machines(SVM),and naive Bayesian(NB)classifier,which can be used in small sample sets,are selected to classify four gesture *** performance of the three classifiers under different training parameters,different input features,including root mean square(RMS),mean absolute value(MAV),waveform length(WL),slope sign change(SSC)number,zero crossing(ZC)number,and variance(VAR)are tested,and different input channels are also *** results show that:The NB classifier,which assumes that the prior probability of features is polynomial distribution,has the best performance,reaching more than 95%***,an interactive stage lighting control system based on Myo armband gesture recognition is implemented.

关键词： Myo armband gesture recognition surface electromyography customized classifier lighting control

来源：评论

学校读者我要写书评

暂无评论

Uav anti-collision visual detection algorithm 4

Uav anti-collision visual detection algorithm

引用

4th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2023

作者： Han, Jun Yu Li, Zhe Li, Sheng Hou Zhao, Bo Shen Air Traffic Control and Navigation School Air Force Engineering University Xi'an710038 China Key Laboratory of Meta-Synthesis for Electornic and Information System Xi'an710051 China

ISBN: (纸本)9798350326444

In order to solve the problem of unsafe flight of traditional 'low, slow and small' civil UAVs, and reduce pres sure on air traffic control personnel., an improved YOLOv5m target detection algorithm is proposed for active target detection of UAVs. According to the characteristics of low-altitude UAV detection, an attention mechanism was added to the YO LOv5 feature extraction network, and the original weighted NMS was optimized to SOFT-NMS Finally, the accuracy and real-time performance of the model are verified by constructi ng real UAV conflict target detection data set. The experimen tal results show that the average accuracy, recall rate, accura cy are 2.31 %, 3.66% and 5.59% higher than before the impr ovement, meet the anti-collision detection requirements of civi 1 UAV s in low altitude airspace. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Music emotion prediction based on multidimensional feature fusion 3

Music emotion prediction based on multidimensional feature f...

引用

3rd IEEE International Conference on information Technology, Big Data and Artificial Intelligence, ICIBA 2023

作者： Zhou, Xuanye Su, Zhibin Ren, Hui Communication University of China School of Information and Communication Engineering Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China

ISBN: (纸本)9781665490788

Audience sentiment analysis is a popular research task in Music information Retrieval (MIR). In this work, we aim to lean the prediction model of fine-grained music emotion for intelligent editing and retrieval. To satisfy the properties of time-series of music, the RNN-based model of BILSTM was selected as the bone. In particular, the traditional features and deep features extracted from the CNN architecture of spectrogram was fused with attention mechanism to enhance the recognition ability for different emotions. The ablation experiment has proved the necessary of the multi-dimensional features. Finally, the contrasting experiments on recent algorithms demonstrate that our proposed method for emotion prediction is effective, which is also suitable for small data sets. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

On the Equilibrium of a Class of Leader-Follower Games with Decision-Dependent Chance Constraints

arXiv

引用

arXiv 2024年

作者： Wang, Jingxiang Wang, Zhaojian Yang, Bo Liu, Feng Guan, Xinping The Key Laboratory of System Control and Information Processing Ministry of Education of China The Department of Automation Shanghai Jiao Tong University Shanghai China The State Key Laboratory of Power System The Department of Electrical Engineering Tsinghua University Beijing100084 China

In this paper, we study the existence of equilibrium in a single-leader-multiple-follower game with decision-dependent chance constraints (DDCCs), where decision-dependent uncertainties (DDUs) exist in the constraints of followers. DDUs refer to the uncertainties impacted by the leader’s strategy, while the leader cannot capture their exact probability distributions. To address such problems, we first use decision-dependent ambiguity sets under moment information and Cantelli’s inequality to transform DDCCs into second-order cone constraints. This simplifies the game model by eliminating the probability distributions. We further prove that there exists at least one equilibrium point for this game by applying Kakutani’s fixed-point theorem. Finally, a numerical example is provided to show the impact of DDUs on the equilibrium of such game models. Copyright © 2024, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds

DELFlow: Dense Efficient Learning of Scene Flow for Large-Sc...

引用

International Conference on Computer Vision (ICCV)

作者： Chensheng Peng Guangming Wang Xian Wan Lo Xinrui Wu Chenfeng Xu Masayoshi Tomizuka Wei Zhan Hesheng Wang Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai Jiao Tong University Mechanical Systems Control Laboratory University of California Berkeley

Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation. To mitigate these issues in scene flow learning, we regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation 1) preserves most points in the given scene, 2) brings in a significant boost of efficiency, and 3) eliminates the density gap between points and pixels, allowing us to perform effective feature fusion. We also present a novel warping projection technique to alleviate the information loss problem resulting from the fact that multiple points could be mapped into one grid during projection when computing cost volume. Sufficient experiments demonstrate the efficiency and effectiveness of our method, outperforming the prior-arts on the FlyingThings3D and KITTI dataset. Our source codes will be released on https://***/IRMVLab/DELFlow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transfer learning with a spatiotemporal graph convolution network for city flowprediction

引用

Frontiers of information Technology & Electronic Engineering 2025年第1期26卷 79-92页

作者： Binkun LIU Yu KANG Yang CAO Yunbo ZHAO Zhenyi XU Department of Automation University of Science and Technology of ChinaHefei 230026China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China

Recently,deep learning based city flow prediction has been extensively used in the establishment of *** methods are data-hungry,making them unscalable to areas lacking *** transfer learningcan use data-rich source domains to assist target domain cities in city flow prediction,the performance of existingmethods cannot meet the needs of actual use,because the long-distance road network connectivity is *** this problem,we propose a transfer learning method based on spatiotemporal graph convolution,in which weconstruct a co-occurrence space between the source and target domains,and then align the mapping of the sourceand target domains’data in this space,to achieve the transfer learning of the source city flow prediction modelon the target ***,a dynamic spatiotemporal graph convolution module along with a temporalencoder is devised to simultaneously capture the concurrent spatiotemporal features,which implies the inherentrelationship among the road network structures,human travel habits,and city bike ***,these concurrentfeatures are leveraged as cross-city invariant representations and nonlinearly spanned to a co-occurrence *** domain features are thereby aligned with the source domain features in the co-occurrence space by using aMahalanobis distance loss,to achieve cross-city bike flow *** proposed method is evaluated on the publicbike flow datasets in Chicago,New York,and Washington in 2015,and significantly outperforms state-of-the-arttechniques.

关键词： Transfer learning City flow prediction Spatiotemporal graph convolution

来源：评论

学校读者我要写书评

暂无评论

Molecular dynamics study of the effects of deposition parameters on Si0.5Ge0.5 film growth on Ge(100) substrate

引用

Computational Materials Science 2025年 256卷

作者： Xie, Jianan Lin, Tao Wang, Cailin College of Automation and Information Engineering Xi'an University of Technology Xi'an710048 China Shannxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an710048 China

With the widespread application of SiGe films in the semiconductor field, precisely controlling the growth process to obtain high-quality films has become an important research direction. This study focuses on the growth of Si0.5Ge0.5 films on Ge (100) substrates and investigates the effects of different deposition parameters (such as deposition interval, incident energy, incident angle, and substrate off-angle) on film quality. Through molecular dynamics simulations, the effects of these deposition parameters on the crystal structure, dislocation density, and surface roughness of the films are systematically analyzed. The results show that shorter deposition intervals lead to faster atomic deposition, increasing the proportion of disordered atoms;longer deposition intervals effectively reduce the proportion of disordered atoms, but excessively long intervals may increase surface roughness and form island-like structures. Additionally, appropriate incident energy, incident angle, and substrate off-angle can significantly optimize the film quality, with the surface roughness being minimized when the incident energy is 1 eV. © 2025 Elsevier B.V.

关键词： Crystal atomic structure

来源：评论

学校读者我要写书评

暂无评论

Multipath planning based on multimodal optimization slime mold algorithm

Multipath planning based on multimodal optimization slime mo...

引用

2024 International Conference on Culture-Oriented Science and Technology, CoST 2024

作者： Gao, Luli Ren, Hui Communication University of China School of Information and Communication Engineering Bejing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Communication University of China Ministry of Culture and Tourism Bejing China Beijing Key Laboratory of Modern Entertainment Technology Communication University of China Bejing China

ISBN: (纸本)9798350380347

Multipath planning aims to find multiple optimal paths simultaneously, and its essence is a multimodal optimization problem. In recent years, swarm intelligence (SI) optimization algorithms have provided effective solutions for multimodal optimization. In this paper, the multimodal optimization slime mold algorithm (MOSMA) based on master-slave structure and local search strategy (LS) is proposed to solve multipath planning problems in small cultural complex. Firstly, a local search strategy is introduced to eliminate the influence of the 'centerbias' operator and improve the quality of solutions. Secondly, the master-salves structure is introduced to preserve the diversity of the population and enable it to simultaneously locate multiple solutions. Finally, the performance of MOSMA is analyzed on several multimodal functions, and an example of path planning in a small cultural complex is given. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Singing Formant Extraction Method Based on Peak Fitting

A Singing Formant Extraction Method Based on Peak Fitting

引用

2024 International Conference on Culture-Oriented Science and Technology, CoST 2024

作者： Liu, Jingyu Wu, Jiawei Jiang, Wei State Key Laboratory of Media Convergence and Communication Communication University of China 100024 China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Communication University of China 100024 China Communication University of China School of Information and Communication Engineering 100024 China

ISBN: (纸本)9798350380347

Analyzing the timbre characteristics of different singing genres is an important issue in the field of singing acoustics. Formants are an important characteristic parameter for timbre perception, but classical acoustic formant extraction methods lack accuracy and applicability in the analysis of singing genres. In order to solve the problem of insufficient accuracy and applicability of singing formants in singing genre analysis, this paper proposes a singing formant extraction method based on peak fitting. The paper summarizes the theory and methods of extracting vocal formants and based on a large amount of experimental data analysis, proposes a vocal formant feature extraction method based on peak fitting;The effectiveness of the singing formant extraction method based on peak fitting was verified through comparative experiments with existing formant algorithms. This article provides new research ideas and methods for extracting acoustic features in singing. © 2024 IEEE.

关键词： audio feature extraction formant peak fitting singing acoustic singing genre

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：