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
神经辐射场(NeRF)在二维图像到三维场景重建领域展现出优异的性能,使用二维图像作为训练数据,能够重建出场景的三维结构,并能进行高质量的新视图渲染。尽管NeRF在三维场景重建领域是十分有效的,但也存在训练速度慢、推理时间长的问题,...神经辐射场(NeRF)在二维图像到三维场景重建领域展现出优异的性能,使用二维图像作为训练数据,能够重建出场景的三维结构,并能进行高质量的新视图渲染。尽管NeRF在三维场景重建领域是十分有效的,但也存在训练速度慢、推理时间长的问题,并且样本质量与三维场景重建质量密切关联。为解决NeRF在低样本质量情况下的高质量三维重建问题,本文使用2组不同哈希编码的NeRF来学习同一个场景,评估候选视图信息增益之间的差距来引导视图采样。提出一种基于RGB特征的下一个最优视图(next best view)导航技术新框架,该框架在稀疏训练数据上具有很强的鲁棒性,能够通过RGB特征评估捕获高信息增益的下一个最优视图,并优化NeRF训练,可以用最少的额外视图来提高新视图合成质量。通过对NeRF训练流程的优化,网络收敛速度提升大约10倍,显存占用降低39.8%,大量实验验证了该模型的有效性和鲁棒性。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
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.
文摘神经辐射场(NeRF)在二维图像到三维场景重建领域展现出优异的性能,使用二维图像作为训练数据,能够重建出场景的三维结构,并能进行高质量的新视图渲染。尽管NeRF在三维场景重建领域是十分有效的,但也存在训练速度慢、推理时间长的问题,并且样本质量与三维场景重建质量密切关联。为解决NeRF在低样本质量情况下的高质量三维重建问题,本文使用2组不同哈希编码的NeRF来学习同一个场景,评估候选视图信息增益之间的差距来引导视图采样。提出一种基于RGB特征的下一个最优视图(next best view)导航技术新框架,该框架在稀疏训练数据上具有很强的鲁棒性,能够通过RGB特征评估捕获高信息增益的下一个最优视图,并优化NeRF训练,可以用最少的额外视图来提高新视图合成质量。通过对NeRF训练流程的优化,网络收敛速度提升大约10倍,显存占用降低39.8%,大量实验验证了该模型的有效性和鲁棒性。
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.
