检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Chenglong Xue, Wanlin Jia, Yaqing Qu, Zhichen Luo, Bin Tang, Jin Sun, Dengdi Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

RGBT tracking receives a surge of interest in the computer vision community, but this research field lacks a large-scale and high-diversity benchmark dataset, which is essential for both the training of deep RGBT trackers and the comprehensive evaluation of RGBT tracking methods. To this end, we present a Large-scale High-diversity benchmark for short-term RGBT tracking (LasHeR) in this work. LasHeR consists of 1224 visible and thermal infrared video pairs with more than 730K frame pairs in total. Each frame pair is spatially aligned and manually annotated with a bounding box, making the dataset well and densely annotated. LasHeR is highly diverse capturing from a broad range of object categories, camera viewpoints, scene complexities and environmental factors across seasons, weathers, day and night. We conduct a comprehensive performance evaluation of 12 RGBT tracking algorithms on the LasHeR dataset and present detailed analysis. In addition, we release the unaligned version of LasHeR to attract the research interest for alignment-free RGBT tracking, which is a more practical task in real-world applications. The datasets and evaluation protocols are availab.e at: https://***/mmic-lcl/Datasets-and-benchmark-code. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A unified generalization analysis of re-weighting and logit-adjustment for imbalanced learning 23

A unified generalization analysis of re-weighting and logit-...

引用

Proceedings of the 37th International Conference on Neural Information processing Systems

作者： Zitai Wang Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang SKLOIS Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences

Real-world datasets are typically imbalanced in the sense that only a few classes have numerous samples, while many classes are associated with only a few samples. As a result, a naïve ERM learning process will be biased towards the majority classes, making it difficult to generalize to the minority classes. To address this issue, one simple but effective approach is to modify the loss function to emphasize the learning on minority classes, such as re-weighting the losses or adjusting the logits via class-dependent terms. However, existing generalization analysis of such losses is still coarse-grained and fragmented, failing to explain some empirical results. To bridge this gap, we propose a novel technique named data-dependent contraction to capture how these modified losses handle different classes. On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment in a unified manner. Furthermore, a principled learning algorithm is developed based on the theoretical insights. Finally, the empirical results on benchmark datasets not only validate the theoretical results but also demonstrate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shot Transition Detection Based on Locally Linear Embedding

Shot Transition Detection Based on Locally Linear Embedding

引用

2010 International Conference on Measuring Technology and Mechatronics Automation(ICMTMA 2010)(2010年检测技术与机电自动化国际会议)

作者： MaoSheng Fu DaMing Zhang Min Kong Bin Luo Key Lab of Intelligent Computing & Signal Processing of Ministry of Education Anhui University Hefei230039. P. R. China Department of Computer Science and Technology in West Anhui University Anhui Lu'an 237012. P. R. China

ISBN: (纸本)9781424450015

Detection of shot transitions servers as the preliminary step to video indexing and retrieval. Locally linear embedding (LLE) algorithm fails when it is applied to video with multi-shot. In this paper, we present a novel framework of shot transitions detection. The method involves two processes: First we extract the manifold feature of shot transition using LLE through addition of virtual frames on an enriched set, and then they are classified by *** show that the recognition rate of shot transition is reached over 90％.

关键词： shot transition detection locally linear embedding feature extraction

来源：评论

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collab.rative metric learning algorithm 22

The minority matters: a diversity-promoting collaborative me...

引用

Proceedings of the 36th International Conference on Neural Information processing Systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Video rain/snow removal by transformed online multiscale convolutional sparse coding

arXiv

引用

arXiv 2019年

作者： Li, Minghan Cao, Xiangyong Zhao, Qian Zhang, Lei Gao, Chenqiang Meng, Deyu School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi'an Jiaotong University Shaanxi China Department of Computing Hong Kong Polytechnic University Hung Hom Hong Kong Chongqing Key Laboratory of Signal and Information Processing Chongqing University of Posts and Telecommunications Chongqing400065 China

Video rain/snow removal from surveillance videos is an important task in the computer vision community since rain/snow existed in videos can severely degenerate the performance of many surveillance system. Various methods have been investigated extensively, but most only consider consistent rain/snow under stable background scenes. Rain/snow captured from practical surveillance camera, however, is always highly dynamic in time with the background scene transformed occasionally. To this issue, this paper proposes a novel rain/snow removal approach, which fully considers dynamic statistics of both rain/snow and background scenes taken from a video sequence. Specifically, the rain/snow is encoded as an online multi-scale convolutional sparse coding (OMS-CSC) model, which not only finely delivers the sparse scattering and multi-scale shapes of real rain/snow, but also well encodes their temporally dynamic configurations by real-time ameliorated parameters in the model. Furthermore, a transformation operator imposed on the background scenes is further embedded into the proposed model, which finely conveys the dynamic background transformations, such as rotations, scalings and distortions, inevitably existed in a real video sequence. The approach so constructed can naturally better adapt to the dynamic rain/snow as well as background changes, and also suitable to deal with the streaming video attributed its online learning mode. The proposed model is formulated in a concise maximum a posterior (MAP) framework and is readily solved by the ADMM algorithm. Compared with the state-of-the-art online and offline video rain/snow removal methods, the proposed method achieves better performance on synthetic and real videos datasets both visually and quantitatively. Specifically, our method can be implemented in relatively high efficiency, showing its potential to real-time video rain/snow removal. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Method of ICA based on estimating the PDF of signals

引用

Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University 2005年第4期32卷 574-578页

作者： Li, Xiao-Jun Lou, Shun-Tian Zhang, Xian-Da Key Lab. of Radar Signal Processing Xidian Univ. Xi'an 710071 China State Key Lab. of Intelligent Technology and Systems Dept. of Automation Tsinghua Univ. Beijing 100084 China

Independent component analysis (ICA) is a method for finding independent components from multivariate (multidimensional) statistical data. Based on the optimal estimation function, a method for the estimation of the score function is developed. By using the Gaussian mixture model, an EM algorithm for approximating the probability density of the data is presented, and a stochastic gradient method is given to separate the independent components. To improve the accuracy and stability of the algorithm, an iterative method for estimating the PDF of data is presented, which can perform the separation of mixed sub-Gaussian from super-Gaussian sources. The performance of the method is shown by computer simulations.

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

A Broadband Dual-Polarized Magneto-Electric Dipole Antenna for 2G/3G/LTE Applications

A Broadband Dual-Polarized Magneto-Electric Dipole Antenna f...

引用

IEEE Asia-Pacific Conference on Antennas and Propagation

作者： Wensheng Yu Zhongxiang Zhang Aoyun Zhang Xianliang Wu Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University School of Electronic and Information Engineering Hefei Normal University

ISBN: (纸本)9781538616093

A broadband dual-polarized magneto-electric dipole antenna excited by Γ-shaped strips is presented in this communication. The proposed antenna contains three parts. The radiating element of the proposed antenna is a combination of the vertically oriented shorted patch, the planar dipole and the bottom plate. The two orthogonal Γ-shaped feeding strips connected with 50 Ω SMA launchers are used to excite the proposed antenna. The corner reflector can effectively improve the radiation performance of the proposed antenna. As shown in simulated results, the impedance bandwidth of the proposed antenna is 48% for standing-wave ratio (SWR) ≤2 (0.86-2.47 GHz), the availab.e bandwidth of the antenna covers the 2G/3G/LTE bands, and the antenna obtains a stable gain that the average value is 10 dBi. Meanwhile, the antenna has good performance in radiation characteristics. The proposed antenna can be applied to the base station communication systems.

关键词： Broadband Dual-polarization Corner reflector Magneto-electric dipole

来源：评论

学校读者我要写书评

暂无评论

A Pilot Allocation Method of Jointing Cell Grouping and Alliance Game in Massive MIMO System

引用

IOP Conference Series: Materials Science and Engineering 2019年第7期490卷

作者： Feiyue Wang Hui Zhi Ziju Huang Key Lab of Computing Intelligent and Signal Processing (Ministry of Education) Anhui University Hefei China

In order to improve the uplink channel estimation performance and reduce pilot contamination (PC), this paper proposes a pilot allocation method of jointing cell grouping and alliance game (JCG-AG) for massive multiple-input multiple-output (MIMO) cellular networks. It can be divided into two steps. First, by properly dividing all cells into different cell-groups, the users in different cell-groups are allocated different orthogonal pilot sets. Second, the users in the same cell-group are further divided into several mutually disjoint sub-alliances. Users belonging to different sub-alliances are allocated different pilots, and users belonging to the same sub-alliance reuse the same pilots. During the second step, the alliance formation algorithm is used to suppress PC. The JCG-AG method takes practical application as the starting point, focuses on the random distribution of users, and uses the idea of alliance game. All these make it more flexible and practical. As demonstrated in the simulation results, the JCG-AG method can greatly mitigate the PC and reduce the average mean square error (MSE) for all channel estimations in the uplink.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Downlink Performance of Massive MIMO Systems under Different Uplink Pilot Allocation Schemes

引用

IOP Conference Series: Materials Science and Engineering 2019年第7期490卷

作者： Ziju Huang Hui Zhi Feiyue Wang Key Lab of Computing Intelligent and Signal Processing (Ministry of Education) Anhui University Hefei China

In the scenario of time division duplexing (TDD) massive multiple-input multiple-output (MIMO) system, when there is pilot contamination (PC) in the uplink, different pilot allocation schemes will affect the results of the uplink channel estimation. When the channel estimation results are used for downlink transmission precoding, which will further affects the downlink performance. This paper analyses the impact of different pilot allocation (PA) schemes on downlink performance. Through theoretical analysis, the system downlink signal to interference plus noise ratio (SINR) and spectral efficiency expressions of different pilot allocation schemes are obtained respectively. The simulation results show that the pilot allocation schemes with cell grouping is better than the schemes without cell grouping. The SINR increases as the number of cell grouping increases, and the spectrum efficiency increases first and then decreases as the number of cell grouping increases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Wideband Dual-Band Magneto-Electric Dipole Antenna With Modified Feed Structure

A Wideband Dual-Band Magneto-Electric Dipole Antenna With Mo...

引用

IEEE International Conference on Microwave and Millimeter Wave Technology

作者： Fan Li Yufa Sun Haoran Zhu Hongyu Fang Ministry of Education Anhui University Hefei China Ministry of Education Key Lab of Intelligent Computing & Signal Processing Anhui University Hefei China

In this paper, a novel wideband dual-band magneto-electric dipole antenna with modified feed structure is proposed. Double-layer patches are utilized to design a pair of folding metal. The double-layer patches dipole can generate two resonant frequencies, which are employed to form a dual-band magneto-electric dipole antenna. A stair-shaped feeding strip with a hexagonal structure is designed to modify the impedance matching. It is found from simulated results that two operation bands with bandwidths of 60% from 1.61 to 2.99 GHz and 31.9% from 4.99 to 6.89 GHz under the return loss level of 10 dB were achieved. The gain of the antenna ranged from 7.56 to 10.56 dBi. Furthermore, low cross-polarization level and low back-radiation are also obtained with the proposed antenna.

关键词： Dipole antennas Dual band Antenna feeds Broadband antennas Magnetoelectric effects Impedance matching Magnetic resonance

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：