To achieve good results in convolutional neural networks(CNN) for text classification task, term-based pooling operation in CNNs is proposed. Firstly, the convolution results of several convolution kernels are combine...To achieve good results in convolutional neural networks(CNN) for text classification task, term-based pooling operation in CNNs is proposed. Firstly, the convolution results of several convolution kernels are combined by this method, and then the results after combination are made pooling operation, three sorts of CNN models(we named TBCNN, MCT-CNN and MMCT-CNN respectively) are constructed and then corresponding algorithmic thought are detailed on this basis. Secondly, relevant experiments and analyses are respectively designed to show the effects of three key parameters(convolution kernel, combination kernel number and word embedding) on three kinds of CNN models and to further demonstrate the effect of the models proposed. The experimental results show that compared with the traditional method of text classification in CNNs, term-based pooling method is addressed that not only the availability of the way is proved, but also the performance shows good superiority.展开更多
In this paper, we propose Term-based Semantic Peerto-Peer Networks (TSPN) to achieve semantic search. For each peer, TSPN builds a full text index of its documents. Through the analysis of resources, TSPN obtains se...In this paper, we propose Term-based Semantic Peerto-Peer Networks (TSPN) to achieve semantic search. For each peer, TSPN builds a full text index of its documents. Through the analysis of resources, TSPN obtains series of terms, and distributes these terms into the network. Thus, TSPN can use query terms to locate appropriate peers to perform semantic search. Moreover, unlike the traditional structured P2P networks, TSPN uses the terms, not the peers, as the logical nodes of DHT. This can withstand the impact of network chum. The experimental results show that TSPN has better performance compared with the existing P2P semantic searching algorithms.展开更多
行人重识别是计算机视觉领域中的一个重要研究方向,其目的是在不同的监控摄像头中识别并跟踪同一行人.由于视频帧间存在多种时间关系,从这些关系中可以获取到对象的运动模式以及细粒度特征,因此视频重识别相比图像重识别拥有更丰富的时...行人重识别是计算机视觉领域中的一个重要研究方向,其目的是在不同的监控摄像头中识别并跟踪同一行人.由于视频帧间存在多种时间关系,从这些关系中可以获取到对象的运动模式以及细粒度特征,因此视频重识别相比图像重识别拥有更丰富的时空线索,也更接近实际应用.问题的关键是如何挖掘这些时空线索作为视频重识别的特征.本文针对视频行人重识别问题,提出了一种基于Transformer的长短期时间关系网络(Long and Short Time Transformer,LSTT).该网络包含长短期时间关系模块,提取重要时序信息并强化特征表示.长期时间关系模块利用记忆线索存储每帧信息,并在每一帧建立全局联系;短期时间关系模块则考虑相邻帧之间交互,学习细粒度目标信息,提高特征表示能力.此外,为了提高模型对不同目标特征的适配性,本文还设计了一个包含不同规格卷积核的多尺度模块.该模块具有多种卷积感受野,能够更全面覆盖目标区域,从而进一步提高模型的泛化性能.在MARS、MARS_DL和iLIDS-VID 3个数据集上的实验结果表明,LSTT模型性能最优.展开更多
文摘To achieve good results in convolutional neural networks(CNN) for text classification task, term-based pooling operation in CNNs is proposed. Firstly, the convolution results of several convolution kernels are combined by this method, and then the results after combination are made pooling operation, three sorts of CNN models(we named TBCNN, MCT-CNN and MMCT-CNN respectively) are constructed and then corresponding algorithmic thought are detailed on this basis. Secondly, relevant experiments and analyses are respectively designed to show the effects of three key parameters(convolution kernel, combination kernel number and word embedding) on three kinds of CNN models and to further demonstrate the effect of the models proposed. The experimental results show that compared with the traditional method of text classification in CNNs, term-based pooling method is addressed that not only the availability of the way is proved, but also the performance shows good superiority.
基金Supported by the National Natural Science Foundation of China( 60873225, 60773191, 70771043)National High Technology Research and Development Program of China ( 2007AA01Z403)Wuhan Youth Science and Technology Chenguang Program (200950431171)
文摘In this paper, we propose Term-based Semantic Peerto-Peer Networks (TSPN) to achieve semantic search. For each peer, TSPN builds a full text index of its documents. Through the analysis of resources, TSPN obtains series of terms, and distributes these terms into the network. Thus, TSPN can use query terms to locate appropriate peers to perform semantic search. Moreover, unlike the traditional structured P2P networks, TSPN uses the terms, not the peers, as the logical nodes of DHT. This can withstand the impact of network chum. The experimental results show that TSPN has better performance compared with the existing P2P semantic searching algorithms.
文摘行人重识别是计算机视觉领域中的一个重要研究方向,其目的是在不同的监控摄像头中识别并跟踪同一行人.由于视频帧间存在多种时间关系,从这些关系中可以获取到对象的运动模式以及细粒度特征,因此视频重识别相比图像重识别拥有更丰富的时空线索,也更接近实际应用.问题的关键是如何挖掘这些时空线索作为视频重识别的特征.本文针对视频行人重识别问题,提出了一种基于Transformer的长短期时间关系网络(Long and Short Time Transformer,LSTT).该网络包含长短期时间关系模块,提取重要时序信息并强化特征表示.长期时间关系模块利用记忆线索存储每帧信息,并在每一帧建立全局联系;短期时间关系模块则考虑相邻帧之间交互,学习细粒度目标信息,提高特征表示能力.此外,为了提高模型对不同目标特征的适配性,本文还设计了一个包含不同规格卷积核的多尺度模块.该模块具有多种卷积感受野,能够更全面覆盖目标区域,从而进一步提高模型的泛化性能.在MARS、MARS_DL和iLIDS-VID 3个数据集上的实验结果表明,LSTT模型性能最优.