检索结果-内蒙古大学图书馆

Empirical comparison between CENTRIST and LBP for CBIR

International Journal of Advancements in Computing Technology 2012年第1期4卷 42-49页

作者： Gao, Yanyan Zhang, Honggang Guo, Jun Cao, Yudong Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China College of Electronics and Information Engineering Liaoning University of Technology Jinzhou China

CENTRIST (CENsus TRansform hISTogram) is a descriptor which is firstly proposed for scene classification. In this paper, the differences between CENTRIST and LBP are analyzed on theory. And then it is exploited in the task of content-based image retrieval firstly integrated with the spatial information by multi scale spatial pyramid. The experimental results firstly show that the similarity of two images computed by histogram intersection is better than obtained by Euclidean distance for CENTRIST descriptor. And then the paper demonstrates the most difference between CENTRIST and LBP is that whether the constraints and the transitivity among neighbored pixels exist on experiments. Although CENTRIST can achieve higher precision at top 40 returned images compared with LBP and its extensions only for some categories chosen from Corel and Caltech101 database, the average P-R curve of CENTRIST is higher than LBPs.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Person Search Method for Video Surveillance 22

An Unsupervised Person Search Method for Video Surveillance

引用

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

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

ISBN: (纸本)9781450396110

We propose an unsupervised person search method for video surveillance. This method considers both the spatial features of persons within each frame and the temporal relationship of the same person among different frames. Thus, the spatial features are extracted by region convolutional neural network, and the temporal relationship is organized by gate recurrent unit. The spatio-temporal features are generated by the following average pooling layer and indexed by locality sensitive hashing. A surveillance video database is constructed to evaluate the proposed method, and the experimental results demonstrate that our method improves the search accuracy by utilizing the spatio-temporal features. © 2022 ACM.

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

Efficient VLSI architecture for multi-dimensional discrete wavelet transform

Efficient VLSI architecture for multi-dimensional discrete w...

引用

MIPPR 2005: SAR and Multispectral Image Processing

作者： Xiong, Cheng-Yi Tian, Jin-Wen Liu, Jian College of Electronic Information Engineering South-Center University for Nationalities Wuhan 430074 China Institute of Pattern Recognition and Artificial Intelligence Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

Efficient VLSI architectures for multi-dimensional (m-D) discrete wavelet transform (DWT), e.g. m=2, 3, are presented, in which the lifting scheme of DWT is used to reduce efficiently hardware complexity. The parallelism of 2 m subbands transforms in lifting-based m-D DWT is explored, which increases efficiently the throughput rate of separable m-D DWT. The proposed architecture is composed of m2m-1 1-D DWT modules working in parallel and pipelined, which is designed to process 2m input samples per clock cycle, and generate 2m subbands coefficients synchronously. The total time of computing one level of decomposition for a 2-D image (3-D image sequence) of size N2 (MN2) is approximately N2/4 (MN2/8) intra- clock cycles (ccs). An efficient line-based architecture framework for both 2D+t and t+2D 3-D DWT is first proposed. Compared with the similar works reported in previous literature, the proposed architecture has good performance in terms of production of computation time and hardware cost. The proposed architecture is simple, regular, scalable and well suited for VLSI implementation.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

PropagationNet: propagate points to curve to learn structure information

arXiv

引用

arXiv 2020年

作者： Huang, Xiehe Deng, Weihong Shen, Haifeng Zhang, Xiubao Ye, Jieping Pattern Recognition & Intelligent System Laboratory School of Information and Communication Engineering Beijing University of Posts and Telecommunications AI Labs DiDi Chuxing

Deep learning technique has dramatically boosted the performance of face alignment algorithms. However, due to large variability and lack of samples, the alignment problem in unconstrained situations, e.g. large head poses, exaggerated expression, and uneven illumination, is still largely unsolved. In this paper, we explore the instincts and reasons behind our two proposals, i.e. Propagation Module and Focal Wing Loss, to tackle the problem. Concretely, we present a novel structure-infused face alignment algorithm based on heatmap regression via propagating landmark heatmaps to boundary heatmaps, which provide structure information for further attention map generation. Moreover, we propose a Focal Wing Loss for mining and emphasizing the difficult samples under in-the-wild condition. In addition, we adopt methods like CoordConv and Anti-aliased CNN from other fields that address the shift-variance problem of CNN for face alignment. When implementing extensive experiments on different benchmarks, i.e. WFLW, 300W, and COFW, our method outperforms state-of-the-arts by a significant margin. Our proposed approach achieves 4.05% mean error on WFLW, 2.93% mean error on 300W full-set, and 3.71% mean error on COFW. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MRI denoising using randomized version of nonlocal means method

MRI denoising using randomized version of nonlocal means met...

引用

2016 International Conference on Image Processing, Computer Vision, and pattern recognition, IPCV 2016

作者： Hu, Jinrong He, Jia Fu, Ying Wu, Xi Zhou, Jiliu School of Computer and Soft Engineering Xihua University Chengdu610039 China Key Laboratory of Pattern Recognition and Intelligent Information Processing Chengdu University Chengdu610106 China School of Computer Science Chengdu University of Information Technology Chengdu610225 China

ISBN: (纸本)1601324421

- Non-local mean (NLM) algorithm has been implemented effectively in MRI denoising and is always limited by its computational complexity. To reduce the computational burden of NLM in 3D MRI dataset, in this paper, we used a randomized version of NLM algorithm to remove the noise in MRI data. The random NLM algorithm seeds up the classical NLM by computing a small subset of image patch distances, which are randomly select according to the uniform sampling pattern. Numerical experiments demonstrate that the random NLM can achieve a competitive denoising result at a low sampling rate (0.05) in 3D MRI dataset while reducing the runtime dramatically. © CSREA Press.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Shadow detection using regression tree fields with paired regions

引用

Journal of Computational Information systems 2013年第11期9卷 4309-4317页

作者： Tao, Wei Zhou, Yue Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai 200240 China

In this paper, we try to deal with the problem of shadow detection from static images and video sequences. In instead to considering individual regions separately, we use relative illumination conditions between segmented regions and perform pair-wise classification based on such information. We use Regression Tree Fields to solve the labeling of shadow and non-shadow regions. And we use continuous value to describe the possibility of the shadow of the region. We evaluate our method on static images and a series of video sequences. © 2013 by Binary Information Press.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

CODEBOOK OPTIMIZATION USING WORD ACTIVATION FORCES FOR SCENE CATEGORIZATION

CODEBOOK OPTIMIZATION USING WORD ACTIVATION FORCES FOR SCENE...

引用

IEEE International Conference on Image Processing

作者： Qun Li Honggang Zhang Jun Guo Le An Bir Bhanu Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Center for Research in Intelligent Systems University of California Riverside CA USA

Visual codebook based quantization of robust appearance descriptors extracted from local image patches is an effective means of capturing image statistics for texture analysis and natural scene classification. In this paper, based on the newly proposed statistics of word activation forces (WAFs), we optimize the codebook. Currently, codebooks are typically created from a set of training images using a clustering algorithm. However, these codebooks are often functionally limited due to redundancy. We show that WAFs can remove the redundancy efficiently. In the experiment, the proposed method achieved the state-of-the-art performance on the Caltech- 101, fifteen natural scene categories and VOC2007 databases. The optimization method also offers insights into the success of several recently proposed images classification approaches, including vector quantization (VQ) coding in the Spatial Pyramid Matching (SPM), sparse coding SPM (ScSPM), and Locality-constrained Linear Coding (LLC).

关键词： Optimization Visualization Encoding Training Image coding Accuracy Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Image super-resolution based wavelet framework with gradient prior

引用

Lecture Notes in Computer Science

作者： Xu, Yan Li, Xueming M. Suen, Chingyi Y. Beijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing 100876 China Centre for Pattern Recognition and Machine Intelligence Concordia University Montreal QC H3G 1M8 Canada

ISBN: (纸本)9783642236778

A novel super-resolution approach is presented. It is based on the local Lipschitz regularity of wavelet transform along scales to predict the new detailed coefficients and their gradients from the horizontal, vertical and diagonal directions after extrapolation. They form inputs of a synthesis wavelet filter to perform the undecimated inverse wavelet transform without registration error, to obtain the output image and its gradient map respectively. Finally, the gradient descent algorithm is applied to the output image combined with the newly generated gradient map. Experiments show that our method improves in both the objective evaluation of peak signal-to-noise ratio (PSNR) with the greatest improvement of 1.32 dB and the average of 0.56 dB, and the subjective evaluation in the edge pixels and even in the texture regions, compared to the "bicubic" interpolation algorithm. © 2011 Springer-Verlag.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Relation-Aware Learning for Multi-Task Multi-Agent Cooperative Games

引用

IEEE Transactions on Games 2024年 1-12页

作者： Yu, Yang Yang, Likun Guo, Zhourui Ren, Yongjian Yin, Qiyue Zhang, Junge Huang, Kaiqi Center for Research on Intelligent System and Engineering Institute of Automation Chinese Academy of Sciences Beijing China Center for Research on Intelligent System and Engineering and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

Collaboration among multiple tasks is advantageous for enhancing learning efficiency in multi-agent reinforcement learning. To guide agents in cooperating with different teammates in multiple tasks, contemporary approaches encourage agents to exploit common cooperative patterns or identify the learning priorities of multiple tasks. Despite the progress made by these methods, they all assume that all cooperative tasks to be learned are related and desire similar agent policies. This is rarely the case in multi-agent cooperation, where minor changes in team composition can lead to significant variations in cooperation, resulting in distinct cooperative strategies compete for limited learning resources. In this paper, to tackle the challenge posed by multi-task learning in potentially competing cooperative tasks, we propose a novel framework called Relation-Aware Learning (RAL). RAL incorporates a relation awareness module in both task representation and task optimization, aiding in reasoning about task relationships and mitigating negative transfers among dissimilar tasks. To assess the performance of RAL, we conduct a comparative analysis with baseline methods in a multi-task StarCraft environment. The results demonstrate the superiority of RAL in multi-task cooperative scenarios, particularly in scenarios involving multiple conflicting tasks. Index Terms—Cooperation games, multi-task learning, reinforcement learning. IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PropagationNet: Propagate Points to Curve to Learn Structure Information

PropagationNet: Propagate Points to Curve to Learn Structure...

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Xiehe Huang Weihong Deng Haifeng Shen Xiubao Zhang Jieping Ye Pattern Recognition & Intelligent System Laboratory School of Information and Communication Engineering Beijing University of Posts and Telecommunications AI Labs DiDi Chuxing

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Deep learning technique has dramatically boosted the performance of face alignment algorithms. However, due to large variability and lack of samples, the alignment problem in unconstrained situations, e.g. large head poses, exaggerated expression, and uneven illumination, is still largely unsolved. In this paper, we explore the instincts and reasons behind our two proposals, i.e. Propagation Module and Focal Wing Loss, to tackle the problem. Concretely, we present a novel structure-infused face alignment algorithm based on heatmap regression via propagating landmark heatmaps to boundary heatmaps, which provide structure information for further attention map generation. Moreover, we propose a Focal Wing Loss for mining and emphasizing the difficult samples under in-the-wild condition. In addition, we adopt methods like CoordConv and Anti-aliased CNN from other fields that address the shift variance problem of CNN for face alignment. When implementing extensive experiments on different benchmarks, i.e. WFLW, 300W, and COFW, our method outperforms the state-of-the-arts by a significant margin. Our proposed approach achieves 4.05% mean error on WFLW, 2.93% mean error on 300W full-set, and 3.71% mean error on COFW.

关键词： Heating systems Face Convolution Adaptation models Lighting Training

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：