With the rapid development of the Internet, recent years have seen the explosive growth of social media. This brings great challenges in performing efficient and accurate image retrieval on a large scale. Recent work ...With the rapid development of the Internet, recent years have seen the explosive growth of social media. This brings great challenges in performing efficient and accurate image retrieval on a large scale. Recent work shows that using hashing methods to embed high-dimensional image features and tag information into Hamming space provides a powerful way to index large collections of social images. By learning hash codes through a spectral graph partitioning algorithm, spectral hashing(SH) has shown promising performance among various hashing approaches. However, it is incomplete to model the relations among images only by pairwise simple graphs which ignore the relationship in a higher order. In this paper, we utilize a probabilistic hypergraph model to learn hash codes for social image retrieval. A probabilistic hypergraph model offers a higher order repre-sentation among social images by connecting more than two images in one hyperedge. Unlike a normal hypergraph model, a probabilistic hypergraph model considers not only the grouping information, but also the similarities between vertices in hy-peredges. Experiments on Flickr image datasets verify the performance of our proposed approach.展开更多
The homomorphic hash algorithm(HHA)is introduced to help on-the-fly verify the vireless sensor network(WSN)over-the-air programming(OAP)data based on rateless codes.The receiver calculates the hash value of a group of...The homomorphic hash algorithm(HHA)is introduced to help on-the-fly verify the vireless sensor network(WSN)over-the-air programming(OAP)data based on rateless codes.The receiver calculates the hash value of a group of data by homomorphic hash function,and then it compares the hash value with the receiving message digest.Because the feedback channel is deliberately removed during the distribution process,the rateless codes are often vulnerable when they face security issues such as packets contamination or attack.This method prevents contaminating or attack on rateless codes and reduces the potential risks of decoding failure.Compared with the SHA1 and MD5,HHA,which has a much shorter message digest,will deliver more data.The simulation results show that to transmit and verify the same amount of OAP data,HHA method sends 17.9% to 23.1%fewer packets than MD5 and SHA1 under different packet loss rates.展开更多
A novel hashing method based on multiple heterogeneous features is proposed to improve the accuracy of the image retrieval system. First, it leverages the imbalanced distribution of the similar and dissimilar samples ...A novel hashing method based on multiple heterogeneous features is proposed to improve the accuracy of the image retrieval system. First, it leverages the imbalanced distribution of the similar and dissimilar samples in the feature space to boost the performance of each weak classifier in the asymmetric boosting framework. Then, the weak classifier based on a novel linear discriminate analysis （LDA） algorithm which is learned from the subspace of heterogeneous features is integrated into the framework. Finally, the proposed method deals with each bit of the code sequentially, which utilizes the samples misclassified in each round in order to learn compact and balanced code. The heterogeneous information from different modalities can be effectively complementary to each other, which leads to much higher performance. The experimental results based on the two public benchmarks demonstrate that this method is superior to many of the state- of-the-art methods. In conclusion, the performance of the retrieval system can be improved with the help of multiple heterogeneous features and the compact hash codes which can be learned by the imbalanced learning method.展开更多
传统的ACF+AdaBoost行人检测框架在达到较为理想的检测率时,误检率也会迅速增高,难以满足实际需求。针对该问题,本文提出了一种自适应加权的Hash码特征,用来增加行人特征的多样性。在此基础上,通过级联一个辅助网络降低系统的误检率,该...传统的ACF+AdaBoost行人检测框架在达到较为理想的检测率时,误检率也会迅速增高,难以满足实际需求。针对该问题,本文提出了一种自适应加权的Hash码特征,用来增加行人特征的多样性。在此基础上,通过级联一个辅助网络降低系统的误检率,该辅助网络采用了浅层的CNN结构,在保证系统实时性的前提下对AdaBoost分类器的分类结果进行二次分类。在INRIA数据中进行检测实验的结果表明,改进的Hash码简单、易算,对行人的表征能力强,在不影响实时性的前提下,把系统的MR-FPPI(Miss rate against false positives per image)从17.05%降低到16.31%。系统级联辅助CNN后系统的MR-FPPI降低到16.93%,而加入Hash码通道,且级联辅助CNN后,系统的MR-FPPI降低到15.96%,检测性能得到较为明显的提高。展开更多
When developing programs or websites, it is very convenient to use relational databases, which contain powerful and convenient tools that allow to work with data very flexibly and get the necessary information in a ma...When developing programs or websites, it is very convenient to use relational databases, which contain powerful and convenient tools that allow to work with data very flexibly and get the necessary information in a matter of milliseconds. A relational database consists of tables and records in these tables, each table must have a primary key, in particular, it can be a number of BIGINT type, which is a unique index of a record in the table, which allows to fetch operation with maximum speed and O (1) complexity. After the operation of writing a row to the table of database, the program receives the row identifier ID in the form of a number, and in the future this ID can be used to obtain this record. In the case of a website, this could be the GET method of the http protocol with the entry ID in the request. But very often it happens that the transmission of an identifier in the clear form is not safe, both for business reasons and for security reasons of access to information. And in this case, it is necessary to create additional functionality for checking access rights and come up with a way to encode data in such a way that it would be impossible to determine the record identifier, and this, in turn, leads to the fact that the program code becomes much more complicated and also increases the amount of data, necessary to ensure the operation of the program. This article presents an algorithm that solves these problems “on the fly” without complicating the application logic and does not require resources to store additional information. Also, this algorithm is very reliable since it is based on the use of hash functions and synthesized as a result of many years of work related to writing complex systems that require an increased level of data security and program performance.展开更多
基金Project supported by the National Basic Research Program(973)of China(No.2012CB316400)
文摘With the rapid development of the Internet, recent years have seen the explosive growth of social media. This brings great challenges in performing efficient and accurate image retrieval on a large scale. Recent work shows that using hashing methods to embed high-dimensional image features and tag information into Hamming space provides a powerful way to index large collections of social images. By learning hash codes through a spectral graph partitioning algorithm, spectral hashing(SH) has shown promising performance among various hashing approaches. However, it is incomplete to model the relations among images only by pairwise simple graphs which ignore the relationship in a higher order. In this paper, we utilize a probabilistic hypergraph model to learn hash codes for social image retrieval. A probabilistic hypergraph model offers a higher order repre-sentation among social images by connecting more than two images in one hyperedge. Unlike a normal hypergraph model, a probabilistic hypergraph model considers not only the grouping information, but also the similarities between vertices in hy-peredges. Experiments on Flickr image datasets verify the performance of our proposed approach.
基金Supported by the National Science and Technology Support Program(Y2140161A5)the National High Technology Research and Development Program of China(863Program)(O812041A04)
文摘The homomorphic hash algorithm(HHA)is introduced to help on-the-fly verify the vireless sensor network(WSN)over-the-air programming(OAP)data based on rateless codes.The receiver calculates the hash value of a group of data by homomorphic hash function,and then it compares the hash value with the receiving message digest.Because the feedback channel is deliberately removed during the distribution process,the rateless codes are often vulnerable when they face security issues such as packets contamination or attack.This method prevents contaminating or attack on rateless codes and reduces the potential risks of decoding failure.Compared with the SHA1 and MD5,HHA,which has a much shorter message digest,will deliver more data.The simulation results show that to transmit and verify the same amount of OAP data,HHA method sends 17.9% to 23.1%fewer packets than MD5 and SHA1 under different packet loss rates.
基金The National Natural Science Foundation of China(No.61305058)the Natural Science Foundation of Higher Education Institutions of Jiangsu Province(No.12KJB520003)+1 种基金the Natural Science Foundation of Jiangsu Province(No.BK20130471)the Scientific Research Foundation for Advanced Talents by Jiangsu University(No.13JDG093)
文摘A novel hashing method based on multiple heterogeneous features is proposed to improve the accuracy of the image retrieval system. First, it leverages the imbalanced distribution of the similar and dissimilar samples in the feature space to boost the performance of each weak classifier in the asymmetric boosting framework. Then, the weak classifier based on a novel linear discriminate analysis （LDA） algorithm which is learned from the subspace of heterogeneous features is integrated into the framework. Finally, the proposed method deals with each bit of the code sequentially, which utilizes the samples misclassified in each round in order to learn compact and balanced code. The heterogeneous information from different modalities can be effectively complementary to each other, which leads to much higher performance. The experimental results based on the two public benchmarks demonstrate that this method is superior to many of the state- of-the-art methods. In conclusion, the performance of the retrieval system can be improved with the help of multiple heterogeneous features and the compact hash codes which can be learned by the imbalanced learning method.
文摘传统的ACF+AdaBoost行人检测框架在达到较为理想的检测率时,误检率也会迅速增高,难以满足实际需求。针对该问题,本文提出了一种自适应加权的Hash码特征,用来增加行人特征的多样性。在此基础上,通过级联一个辅助网络降低系统的误检率,该辅助网络采用了浅层的CNN结构,在保证系统实时性的前提下对AdaBoost分类器的分类结果进行二次分类。在INRIA数据中进行检测实验的结果表明,改进的Hash码简单、易算,对行人的表征能力强,在不影响实时性的前提下,把系统的MR-FPPI(Miss rate against false positives per image)从17.05%降低到16.31%。系统级联辅助CNN后系统的MR-FPPI降低到16.93%,而加入Hash码通道,且级联辅助CNN后,系统的MR-FPPI降低到15.96%,检测性能得到较为明显的提高。
文摘When developing programs or websites, it is very convenient to use relational databases, which contain powerful and convenient tools that allow to work with data very flexibly and get the necessary information in a matter of milliseconds. A relational database consists of tables and records in these tables, each table must have a primary key, in particular, it can be a number of BIGINT type, which is a unique index of a record in the table, which allows to fetch operation with maximum speed and O (1) complexity. After the operation of writing a row to the table of database, the program receives the row identifier ID in the form of a number, and in the future this ID can be used to obtain this record. In the case of a website, this could be the GET method of the http protocol with the entry ID in the request. But very often it happens that the transmission of an identifier in the clear form is not safe, both for business reasons and for security reasons of access to information. And in this case, it is necessary to create additional functionality for checking access rights and come up with a way to encode data in such a way that it would be impossible to determine the record identifier, and this, in turn, leads to the fact that the program code becomes much more complicated and also increases the amount of data, necessary to ensure the operation of the program. This article presents an algorithm that solves these problems “on the fly” without complicating the application logic and does not require resources to store additional information. Also, this algorithm is very reliable since it is based on the use of hash functions and synthesized as a result of many years of work related to writing complex systems that require an increased level of data security and program performance.
