检索结果-内蒙古大学图书馆

11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016

作者： Tian, Xiaolin Zhao, Sujie Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center of Intelligent Perception and Computation International Collaboration Joint Lab in Intelligent Perception and Computation Xidian University XianShaanxi710071 China

ISBN: (纸本)9789811036101

In this paper, we propose a novel visual tracking method based on ensemble learning using logistic regression model. We adopt logistic regression to achieve ensemble classifier to deal with object tracking problem. By using fast computable features, our approach learns the appearance of the target during tracking. And thus, the proposed method is able to adapt online to target appearance changes and its surrounding background. Moreover, ensemble learning converts rough rules of thumb into highly accurate prediction rule. Experimental results show that our method outperforms relative trackers. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

A Dual Residual Network with Channel Attention for image Restoration 16th

A Dual Residual Network with Channel Attention for Image Res...

引用

Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

作者： Nie, Shichao Ma, Chengconghui Chen, Dafan Yin, Shuting Wang, Haoran Jiao, LiCheng Liu, Fang Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Joint International Research Laboratory of Intelligent Perception and Computation School of Artificial Intelligence Xidian University Xi’an Shaanxi710071 China

ISBN: (纸本)9783030682378

Deep learning models have achieved significant performance on image restoration task. However, restoring the images with complicated and combined degradation types still remains a challenge. For this purpose, we proposed a dual residual network with channel attention (DRANet) to address complicated degradation in the real world. We further exploit the potential of encoder-decoder structure. To fuse feature more efficiently, we adopt the channel attention module with skip-connections. To better process low- and high-level information, we introduce the dual residual connection into the network architecture. And we explore the effect of multi-level connection to image restoration. Experimental results demonstrate the superiority of our proposed approach over state-of-the-art methods on the UDC T-OLED dataset. © 2020, Springer Nature Switzerland AG.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A large-scale data clustering algorithm based on BIRCH and artificial immune network 9th

A large-scale data clustering algorithm based on BIRCH and a...

引用

9th International Conference on Swarm Intelligence, ICSI 2018

作者： Li, Yangyang Liu, Guangyuan Li, Peidao Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China International Research Center for Intelligent Perception and Computation School of Artificial Intelligence Xidian University Xi’an710071 China

ISBN: (纸本)9783319938141

This paper describes a large-scale data clustering algorithm which is a combination of Balanced Iterative Reducing and Clustering using Hierarchies Algorithm (BIRCH) and Artificial Immune Network Clustering Algorithm (aiNet). Compared with traditional clustering algorithms, aiNet can better adapt to non-convex datasets and does not require a given number of clusters. But it is not suitable for handling large-scale datasets for it needs a long time to evolve. Besides, the aiNet model is very sensitive to noise, which greatly restricts its application. Contrary to aiNet, BIRCH can better process large-scale datasets but cannot deal with non-convex datasets like traditional clustering algorithms, and requires the cluster number. By combining these two methods, a new large-scale data clustering algorithm is obtained which inherits the advantages and overcomes the disadvantages of BIRCH and aiNet simultaneously. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Tracking algorithm based on dual residual network and kernel correlation filters 2nd

Tracking algorithm based on dual residual network and kernel...

引用

2nd CCF International Conference on Artificial Intelligence, CCF-ICAI 2019

作者： Tian, Xiaolin Li, Fang Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center of Intelligent Perception and Computation International Collaboration Joint Lab in Intelligent Perception and Computation Xidian University XianShaanxi Province710071 China

ISBN: (纸本)9789813292970

Visual target tracking is a target detection task for a period of time. During this period, the tracking target will undergo significant appearance changes due to deformation, sudden movement, complex background and occlusion. These changes make visual target tracking challenging. In this paper, a target tracking algorithm based on dual residual neural network and kernel correlation filters is proposed, which mainly solves the problems of inaccurate tracking. This method combines depth residual neural network with kernel correlation filter tracking algorithm. The template matches the depth residual feature to determine the location of the target and the kernel correlation filter based on residual feature is designed to detect the target, finally, the template matching result and kernel correlation filtering result are fused to determine the location of the target. The experimental results on a large-scale standard data set show that the proposed algorithm has the advantages of high accuracy. Compared with the previous algorithm, the proposed algorithm has good performance in tracking visual deformation, occlusion and fuzzy video objects. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Hybrid immune algorithm with Lamarckian local search for multi-objective optimization

引用

Memetic Computing 2010年第1期2卷 47-67页

作者： Gong, Maoguo Liu, Chao Jiao, Licheng Cheng, Gang Key Lab of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University 710071 Xi'an China

Lamarckian learning has been introduced into evolutionary computation as local search mechanism. The relevant research topic, memetic computation, has received significant amount of interests. In this study, a novel Lamarckian learning strategy is designed for improving the Nondominated Neighbor Immune Algorithm, a novel hybrid multi-objective optimization algorithm, Multi-objective Lamarckian Immune Algorithm (MLIA), is proposed. The Lamarckian learning performs a greedy search which proceeds towards the goal along the direction obtained by Tchebycheff approach and generates the improved progenies or improved decision vectors, so single individual will be optimized locally and the newcomers yield an enhanced exploitation around the nondominated individuals in less-crowded regions of the current trade-off front. Simulation results based on twelve benchmark problems show that MLIA outperforms the original immune algorithm and NSGA-II in approximating Pareto-optimal front in most of the test problems. When compared with the state of the art algorithm MOEA/D, MLIA shows better performance in terms of the coverage of two sets metric, although it is laggard in the hypervolume metric. © 2009 Springer-Verlag.

关键词： Artificial immune system Lamarckian learning Memetic algorithm Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Fine-grained image categorization with fisher vector 11th

Fine-grained image categorization with fisher vector

引用

11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016

作者： Tian, Xiaolin Ding, Xin Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center of Intelligent Perception and Computation International Collaboration Joint Lab in Intelligent Perception and Computation Xidian University Xi’anShaanxi Province710071 China

ISBN: (纸本)9789811036132

Fine-grained image categorization is a categorization task, where classifying objects should be the same basic-level class and have similar shape or visual appearances. Generally, the bag-of-words (BoW) model is popular in image categorization. However, in BoW model, the feature quantization for image representation is also a lossy process, which severely limits the descriptive power of the image representation. Fisher vectors employ soft assignments and reduce information loss due to quantization by calculating the gradient for each parameter separately, which have been shown to outperform other global representations on most benchmark datasets. In this paper, the acquired template is represented by Fisher Vector (FV). Combing FV with improved spatial pyramid matching (SPM) respectively, we use an approach, i.e., FV+SPM, to obtain feature representation. Experimental results show that our method outperforms state-of-the-art categorization approaches on the Caltech-UCSD Birds dataset. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

A new change detection method based on non-parametric density estimation and Markov random fields

A new change detection method based on non-parametric densit...

引用

MIPPR 2009 - Medical Imaging, Parallel Processing of images, and Optimization Techniques: 6th International Symposium on Multispectral image Processing and Pattern Recognition

作者： Wang, Guiting Fan, Yuanzhang Jiao, Licheng Institute of Intelligent Information Processing Xidian University Xi'an 710071 China Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education of China China

ISBN: (纸本)9780819478085

A new change detection approach based on non-parametric density estimation and Markov random fields is proposed in this paper. As the concrete form of gray statistical distribution of remote sensing images is often difficult to be known, the non-parameter density estimation method does not need the specific forms in advance, and is especially suitable for the estimation problem of small samples, so we adopt the non-parametric density estimation method to obtain the precise estimation of the probability density of statistical distribution of differencing image in the paper, and then perform multitemporal remote sensing image change detection combining with MRF(Markov random fields)model for spatial smoothing. The final experimental results show that the proposed method is effective. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

A stochastic variance reduced extragradient method for sparse machine learning problems

A stochastic variance reduced extragradient method for spars...

引用

19th IEEE International Conference on Data Mining Workshops, ICDMW 2019

作者： Kong, Lin Bai, Xiaying Hu, Yang Shang, Fanhua Liu, Yuanyuan Liu, Hongying Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China

ISBN: (纸本)9781728146034

This paper mainly considers the optimization problem of minimizing the average of a number of smooth convex functions and a general convex function capable of proximal mapping. In particular, we consider non-smooth functions, and assume that the smooth convex function is strongly convex, which often occur in data mining and deep learning. For non-smooth large-scale high-dimensional machine learning problems, this paper introduces both the variance reduction technique in SVRG and extragradient descent, and proposes an efficient proximal stochastic variance reduced extragradient algorithm, called EProx-SVRG. From our theoretical results, we know that in the expected form, EProx-SVRG converges to the optimum at a linear convergence rate for strongly convex problems, and the convergence guarantee for non-strongly convex problems is also provided. Moreover, EProx-SVRG achieves the same oracle complexity as Prox-SVRG. Finally, our experimental results show that our algorithm can obtain an improved performance compared with Prox-SVRG and Katyusha. © 2019 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Detection for flood change with SAR images based on fusion and T-distribution

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2011年第2期48卷 271-280页

作者： Li, Jinji Jiao, Licheng Zhang, Xiangrong Yang, Dongdong Key Laboratory of Intelligent Perception and Image Understanding Xidian University Xi'an 710071 China

Based on fusion and T-distribution model, a new approach for detecting flood changes with multi-temporal SAR images is presented. Firstly, by incorporating the advantages of image differencing and log-ratio operator, a novel fusion strategy based on experience is introduced. Then, the final difference image with better effect in vision can be obtained by fusing with difference image and log-ratio image. According to the histogram of the final difference image obtained by fusion strategy, the two ranges of absolute changed and absolute unchanged classes in the histogram can be got, respectively. Then the fuzzy range between the two ranges is obtained, which are unable to identify changed or unchanged classes. Under the T-distribution assumption of the fuzzy range in the histogram, a thresholding approach based on the Kittler-Illingworth (KI) threshold selection criterion (TM_KI) is proposed. Finally, the change-detection map is produced by using the proposed thresholding procedure to the fusing difference image. Through experimental comparisons, analysis of results confirm the proposed method not only can reduce the affection by speckle noise and enhance the subtle changed areas brought by flooding, but also effectively detect small changed areas, so that this method can improve the performance of change detection.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A Directed Search Many Objective Optimization Algorithm Embodied with Kernel Clustering Strategy 5th

A Directed Search Many Objective Optimization Algorithm Embo...

引用

5th IFIP TC 12 International Conference on Intelligence Science, ICIS 2022

作者： Okoth, Michael Aggrey Shang, Ronghua Zhang, Weitong Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Shaanxi Xi’an710071 China

ISBN: (纸本)9783031149023

With the vast existence of multi-objective optimization problems to the scientific research and engineering applications, Many-objective Evolutionary Algorithms (MaOEAs) demand to systematically perpetuate population diversity and convergence distributions in the objective space with high dimensionality. To fulfill the balance in the relationship between convergence, distributions, and diversity, this paper proposes a directed search many-objective optimization algorithm embodied with kernel clustering strategy (DSMOA-KCS) in decision space where some mechanisms such as adaptive environmental selection which efficiently assimilates design for control of diversity and convergence in the distribution of the solutions in the decision scopes. DSMOA-KCS is a stochastic, multi-start algorithm using clustering to increase efficiency. DSMOA-KCS finds the starting point in the regions of interest. Then, it improves them by the directed search method. DSMOA-KCS is compared with several existing state-of-the-art algorithms (NSGA-III, RSEA, and MOEADPas) on many-objective problems with 5 to 30 objective functions using the Inverted Generational Distance (IGD) performance metric. DSMOA-KCS evaluation results illustrate that it is competitive and promising, performing better with some problems. Then, even distribution, convergence, and diversity are maintained. © 2022, IFIP International Federation for Information Processing.

关键词： Evolutionary algorithms

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：