ID 原文 译文
57868 为此，改进了仅依靠对素描和视频数据中的人脸提取整体或者局部特征的识别算法，将人脸识别问题转为人脸检索问题，把这 2 种媒体数据表示为第 3 种数据，即图像列表. An improved recognition algorithm that only extracts global or local features from sketch and vide- o media data was presented. The problem of face recognition is turned into face retrieval. The above two medias data is represented as the so called third kind of data，i. e. image list and the final feature com- parison is completed by comparing image list.
57869 通过比较图像列表完成最终的特征比对.所设计的系统扩展了人脸识别的研究范围，且支持多种媒体数据的检索. The system designed here extends the research scope of face recognition and supports the retrieval of multi-media data.
57870 对比人脸视频分析融合系统，对素描－视频数据进行人脸识别，结果显示，所提出算法的正确识别率和曲线下面积都有相应提高，而等错误率降幅显著. Compared with face recognition of face video analysis combined system for sketch-video data，the proposed design improves the correct recogni- tion rate of precision and area under the curve，while the equal error rate of equal error rate decreases greatly.
57871 针对现有位置预测研究中忽略用户行为序列特性、预测精度提升受限的问题，提出了基于用户行为序列特征的位置预测模型. In order to solve the problem of ignoring the character of user behavior sequence and limiting the improvement of prediction accuracy，two location prediction models based on the character of user be- havior sequence were proposed.
57872 首先以人工提取的方式构建用户行为的序列特征，融合到位置预测模型中，构造了基于行为序列特征的循环神经网络模型( BCP-ＲNN) ; Firstly，behavior + context + profile + ＲNN ( BCP-ＲNN) model is con- structed by manually extracting sequence features of user behaviors and integrating the features into the location prediction model.
57873 借助 ＲNN 模型循环结构的特点，自动学习行为序列特征，并引入位置预测模型，构造了 3 层对称循环神经网络模型( TS-ＲNN) . Then three-layer symmetrical neural network ( TS-ＲNN) model is constructed by automatically learning behavior sequence features based on the recurrent structure of ＲNN model and integrating the features into location prediction model.
57874 实验结果证明，引入行为序列特征的 BCP-ＲNN 和 TS-ＲNN 模 型，其预测性能均高于现有的位置预测模型，验证了行为序列特征对挖掘用户移动模式的重要性. Experiments show that，compared with the existing location prediction models，BCP-ＲNN and TS-ＲNN improves the prediction performance，verifying the importance of behavior sequence features in mining user movement patterns.
57875 相较于人工提取行为序列特征的 BCP-ＲNN 模型，TS-ＲNN 不仅节省了人工特征提取的成本，还弥补了人工分析的片面性造成的偏差，具有更高的预测性能. Besides，compared with the BCP-ＲNN model of manually extracting behavior sequence features，TS-ＲNN not only saves the cost of artificial feature extraction，but also makes up for the deviation caused by one-sided human analysis，and has higher prediction accuracy.
57876 为了精准地捕捉用户行为模式，引入中期兴趣的概念，提出一个基于循环神经网络( ＲNN) 的个性化分层循环模型，通过在同一框架下联合利用用户的会话、区块和全部行为序列来学习用户的综合兴趣. The existing studies of session-based recommendations mainly focus on the short-term and long-term interests of users. In order to accurately depict behavior patterns of users，the author introduces the medium-term interests and proposes personalized hierarchical recurrent model ( PHＲM) based on re- current neural networks ( ＲNNs) ，to learn a comprehensive description of user interests by jointly levera- ging session，block and global behaviors in a unified framework.
57877 利用一个捕捉会话内序列模式的会话级 ＲNN 建模用户的短期兴趣; First，to model short-term interests，a session-level ＲNN is designed to capture sequential patterns in sessions.