Abstract:Recently, the explosive growth of image data, how to retrieve effective images has become an urgent problem. However, image retrieval often faces the following problems.In the current image retrieval model, the information of local area of interest is less considered. When images exist in two different domain distributions, cross-domain retrieval cannot be performed effectively.In view of the current existence of the above problems, this paper put forward based on the interested region of domain adaptive image retrieval methods, including the interest of the target detection technology of image area, the interference of background information filter is invalid, feature fusion method for multi-objective regional characteristics of effective at the same time to join the different domain image domain structure, realization of cross-domain retrieval.In this paper, we evaluated the effectiveness of our method on the PASCAL VOC dataset.

Alert Name:
Alerting to:
Authentication email will be sent to your email address in 24 hours
Frequency:
Email Message Format:	Plain text Graphical(HTML)

Complete the form below and we will recommend the selected titles to your friends on your behalf. * Indicates a required field.
Your name*:
Your email address*:
Recipient's name*:
Recipient's email address*:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find the page(s) useful.

Your name:
Your email address:
Recipient's name:
Recipient's email address:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find this page useful.

Disclaimer: This message was sent to your friend using the "Send it to a friend" facility on the Sciencepaper Online’ WWW site, http://www.paper.edu.cn/en. The Sciencepaper Online is not responsible for the content of this email, and anything said in this email does not necessarily reflect the Sciencepaper Online's views.


	1. Domain adaptive image retrieval based on region of interest
	Zhao Zhen,Ai Xinbo
	Computer Science and Technology 03 March 2020
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Recently, the explosive growth of image data, how to retrieve effective images has become an urgent problem. However, image retrieval often faces the following problems.In the current image retrieval model, the information of local area of interest is less considered. When images exist in two different domain distributions, cross-domain retrieval cannot be performed effectively.In view of the current existence of the above problems, this paper put forward based on the interested region of domain adaptive image retrieval methods, including the interest of the target detection technology of image area, the interference of background information filter is invalid, feature fusion method for multi-objective regional characteristics of effective at the same time to join the different domain image domain structure, realization of cross-domain retrieval.In this paper, we evaluated the effectiveness of our method on the PASCAL VOC dataset.
	TO cite this article:Zhao Zhen,Ai Xinbo. Domain adaptive image retrieval based on region of interest[OL].[ 3 March 2020] http://en.paper.edu.cn/en_releasepaper/content/4750996


	2. A Lightened Sphereface for Face Recognition
	ZHOU Xinjie,Zhenxue Chen,WANG Mengxue
	Computer Science and Technology 25 June 2019
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Convolution neural networks (CNN) have significantly promoted the development of face recognition technology. In order to achieve ultimate accuracy, CNN models tend to be deeper or multiple local facial patch ensembles, resulting in excessive amounts of calculation. This paper addresses these deep face recognition (FR) problems and studies a lightened deep learning framework under an open-set protocol to achieve a good classification effect and streamline the model itself. To this end, we improve the Sphereface that enables deep network to learn angularly discriminative features faster and more effectively. First, global average pooling (GAP) is introduced to replace the original fully connected layer, which greatly reduces the size of the model. Compared to the widely used fully connected layer, GAP can reduce the number of parameters and avoid overfitting. Then Network in Network (NIN) layers are added between convolution layers. These models are trained on the CASIA-WebFace dataset and evaluated on the LFW and YTF datasets, which show the superiority of lightened SphereFace (L-SphereFace) in FR tasks. At the same time, computational cost is reduced by over nine times in comparison with the released SphereFace model. The size of the model is also close to the original half.
	TO cite this article:ZHOU Xinjie,Zhenxue Chen,WANG Mengxue. A Lightened Sphereface for Face Recognition[OL].[25 June 2019] http://en.paper.edu.cn/en_releasepaper/content/4749157

Saved Papers

Saved Papers


	3. Multilevel LSTM for Action Recognition Based on Skeleton Sequence
	CHEN Yan-Ru, PAN Hua-Wei
	Computer Science and Technology 17 April 2019
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Skeleton-based human action recognition has a broad range of applications in human-computer interaction and intelligent monitoring, and human behavior can be represented by the trajectory of the skeleton joint. Long-term short-term memory (LSTM) networks exhibit outstanding performance in 3D human action recognition because they are capable of modeling dynamics and dependencies in sequential data. In this paper, we propose a skeleton-based multilevel LSTM network for action recognition. First, the data for each joint and parent joint is used as input to a fine-grained subnet based on the action link between them. Then the features of the upper body joint are merged into the upper body subnet, the features of the lower body are merged into the lower body subnet, and finally the features of the two subnets are structured and fused to achieve higher recognition accuracy. Experimental results on the public data set NTU RGB+D demonstrate the effectiveness of the proposed network.
	TO cite this article:CHEN Yan-Ru, PAN Hua-Wei. Multilevel LSTM for Action Recognition Based on Skeleton Sequence[OL].[17 April 2019] http://en.paper.edu.cn/en_releasepaper/content/4748531


	4. Reconstruction-based Robust Pavement Crack Detection
	LUO Ling,XU Guosheng,XU Guoai
	Computer Science and Technology 21 January 2019
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Pavement crack detection is of great importance for road maintenance. It is still very challenging to establish a unified and robust framework to perform accurate crack extraction from images with cluttered background, various morphological differences and even with shadow influence. In this paper, an improved semantic segmentation model with reconstruction branch is proposed for crack detection. Based on normal segmentation network, a deep convolutional encoder-decoder network is built to learn the image reconstruction mapping. This reconstruction guided semantic segmentation is aimed at improving detection accuracy by introducing reconstruction difference between crack and normal areas. The experiments demonstrated that our algorithm outperforms the convolutional segmentation method on two public datasets.
	TO cite this article:LUO Ling,XU Guosheng,XU Guoai. Reconstruction-based Robust Pavement Crack Detection[OL].[21 January 2019] http://en.paper.edu.cn/en_releasepaper/content/4747079


	5. Density-Sensitive Spectral Clustering Based on Natural Neighbor
	LEI Dajiang,Wang Mingda,ZHANG Lisheng
	Computer Science and Technology 21 December 2017
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:The key of spectral clustering algorithm lies in how to measure the relation between data points. In order to describe the neighbor relation between data points, a fast natural neighbor method is adopted to adaptively select the number of neighbors. Firstly, the natural neighbor is used to construct the neighborhood relationship between the data. Then the similarity matrix is constructed based on the local information density-sensitive. Finally, the clustering results obtained from eigenvalue decomposition of the Laplacian matrix. In this paper, a local information parameter is proposed to solve the low performance problem of density-sensitive spectral clustering methods due to the linear change of Euclidean distance between data points, meanwhile the problem of selecting scaling factor is solved in density-sensitive spectral clustering. With the massive experiments, the proposed algorithm is effective and feasible, and is superior to the classical spectral clustering algorithm
	TO cite this article:LEI Dajiang,Wang Mingda,ZHANG Lisheng. Density-Sensitive Spectral Clustering Based on Natural Neighbor[OL].[21 December 2017] http://en.paper.edu.cn/en_releasepaper/content/4742931


	6. Face Recognition based on Simplified CNN and Median Pooling
	XIONG Feng-ye, DONG Yuan, BAI Hong-liang
	Computer Science and Technology 13 October 2016
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Convolution neural network(CNN) is increasingly used by the groups studying face recognition. CNN dramatically improves the performance on many datasets such as LFW and IJB-A. But most of the groups extract features from big networks with large amount of parameters and FLOPS. In this work, a simplified CNN architecture, which achieves comparable results to the state of the art, with only 0.8M training data, 4.4M parameters and 0.6B FLOPS, is proposed. In addition, an anti-noise median pooling method is introduced when dealing with template-based comparison.
	TO cite this article:XIONG Feng-ye, DONG Yuan, BAI Hong-liang. Face Recognition based on Simplified CNN and Median Pooling[OL].[13 October 2016] http://en.paper.edu.cn/en_releasepaper/content/4706549


	7. A multiple-steps linear representation based classification for face recognition
	Tao Liu,Jian-Xun Mi
	Computer Science and Technology 19 February 2016
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Error detection is an important approach to improve the robustness of face recognition (FR) method. However, it is hard to directly detect the outliers in a facial image. We decompose the hard problem into many simpler sub-problems in this paper. That is, the process of detecting distorted pixels is divided into multiple easier steps and a part of invalid pixels are detected in every step. The goal is to decrease the ratio of outlier in the testing image, which reduces the influence of outliers in a recognition process. The performance that our method deals with occlusion and corruption problems is evaluated on different databases. In addition, we compare our method with state-the-of-art face recognition based methods, and the proposed method achieves the best results in face occlusion and disguise issues.
	TO cite this article:Tao Liu,Jian-Xun Mi. A multiple-steps linear representation based classification for face recognition[OL].[19 February 2016] http://en.paper.edu.cn/en_releasepaper/content/4676937


	8. A New Gabor Method for Face Recognition
	He Lianghua
	Computer Science and Technology 18 January 2012
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Because of containing enough texture information around base point, Local Binary Pattern features and Gabor features shows excellent performance under batch light varying and rotation. However, the complicated calculation and feature’s high dimension are the biggest restriction in application. Therefore, in this paper we proposed a novel method called Binary Gabor Codes based on above two methods. The key idea is calculating local binary patterns on the corresponding Gabor Magnitude Pictures (GMPs), the calculation and dimension are both decreased. Because of containing both information of local texture and block gray varying, BGC features are more overwhelming comparing with Local Binary Patterns (LBP), Gabor jets and independent component features. What’s more, Experimental results show that it has improved the recognition rate greatly, especially in bad condition.
	TO cite this article:He Lianghua. A New Gabor Method for Face Recognition[OL].[18 January 2012] http://en.paper.edu.cn/en_releasepaper/content/4462906


	9. A Novel Shadow Detection Method Based on Color and Texture Features
	Li Qiaohong,Zhang Honggang,Gu Fang,Dai Yourui,Yu Jie
	Computer Science and Technology 27 December 2011
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:This paper describes a new method for shadow detection of moving objects in video surveillance applications, improving the detection performance and fascinating the following image processing steps, such as object tracking, classification and behavior analysis. This method is based on the priori that shadow region and background region share the similar textural and chromatic characteristics. This method combines the virtues of color and texture features, to select the best criterion to discriminate shadow pixels from object pixels. Experiment shows that this method can achieve desirable performance under indoor and outdoor environment.
	TO cite this article:Li Qiaohong,Zhang Honggang,Gu Fang, et al. A Novel Shadow Detection Method Based on Color and Texture Features[OL].[27 December 2011] http://en.paper.edu.cn/en_releasepaper/content/4456940


	10. Rapid License Plate Location Using a Boosted Cascade of Haar-like Features
	Guo Tianqing,Lu Wenting,Zhang Honggang,Guo Jun
	Computer Science and Technology 10 December 2009
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:In this paper, authors represent location method for vehicle license plate by using a boosted cascade of Haar-like features and it’s capable of locating the license plate extremely rapid while achieving high detection rate. After coarse location by the cascade classifier, the candidates can be checked by binary image projection method according the prior knowledge. This method is of faster speed and higher accuracy than most of the existing methods used in license plate location. Experimental results demonstrate the method is applicable and robust in the real-time location system.
	TO cite this article:Guo Tianqing,Lu Wenting,Zhang Honggang, et al. Rapid License Plate Location Using a Boosted Cascade of Haar-like Features[OL].[10 December 2009] http://en.paper.edu.cn/en_releasepaper/content/37439

	Check out RSS, or use RSS reader to subscribe this item