To improve motion graph based motion synthesis,semantic control was introduced.Hybrid motion features including both numerical and user-defined semantic relational features were extracted to encode the characteristic ...To improve motion graph based motion synthesis,semantic control was introduced.Hybrid motion features including both numerical and user-defined semantic relational features were extracted to encode the characteristic aspects contained in the character's poses of the given motion sequences.Motion templates were then automatically derived from the training motions for capturing the spatio-temporal characteristics of an entire given class of semantically related motions.The data streams of motion documents were automatically annotated with semantic motion class labels by matching their respective motion class templates.Finally,the semantic control was introduced into motion graph based human motion synthesis.Experiments of motion synthesis demonstrate the effectiveness of the approach which enables users higher level of semantically intuitive control and high quality in human motion synthesis from motion capture database.展开更多
现有的下一个兴趣点(point of interest,PoI)推荐技术存在三个主要问题:使用过于简单的方法构建用户兴趣模型、忽略用户和PoI之间在时空维度上的互动以及未能充分挖掘用户间复杂的高阶交互信息。针对这些问题,提出一种新颖的超图学习模...现有的下一个兴趣点(point of interest,PoI)推荐技术存在三个主要问题:使用过于简单的方法构建用户兴趣模型、忽略用户和PoI之间在时空维度上的互动以及未能充分挖掘用户间复杂的高阶交互信息。针对这些问题,提出一种新颖的超图学习模型FSTMH,细粒度地融合时间、空间和语义信息,用于下一个PoI推荐。FSTMH包括细粒度嵌入模块和多层次嵌入模块。前者通过使用地理图卷积网络和有向超图卷积网络进行学习,获取对应的嵌入信息,并通过对比学习提升PoI表示的质量,使用细粒度超图卷积网络学习该模块的PoI嵌入;后者将多层语义超图输入到多层超图卷积网络,学习多层次语义的PoI嵌入表示。最后,模型将两个模块的PoI嵌入向量进行组合,生成最终的top-K预测结果。通过在广泛使用的三个社交网络公共数据集上进行多种实验,结果均表明FSTMH模型表现出色,说明该新模型可作为提高下一个PoI推荐的有效方法。展开更多
随着科研工作者人数的不断增加,科技论文的发表数量呈现快速增长的趋势。面对海量的科技论文,文献的归档、录入和分析工作变得越发繁重。当前,针对文献的分类模型主要关注论文的内容信息,而忽略了论文相关的关联信息。为此,本文提出一...随着科研工作者人数的不断增加,科技论文的发表数量呈现快速增长的趋势。面对海量的科技论文,文献的归档、录入和分析工作变得越发繁重。当前,针对文献的分类模型主要关注论文的内容信息,而忽略了论文相关的关联信息。为此,本文提出一种融合内容信息与学术网络的论文表征模型PAITKG (paper analysis by incorporating text and knowledge graph),引入知识图谱嵌入技术对文献的多重关联信息进行表征,采用Adapter微调的SciBERT提取内容特征,并将二者融合。在训练过程中,本文改进了动态对抗损失函数来引导模型更好地关注错误结果,并将该方法在数字人文和多模态学习两个领域的文献数据集上进行实验。在科技文献的学科多标签分类任务上,PAITKG比Baselines有显著改善,很好地提高了分类精度。除此以外,通过上游任务的学习,PAITKG的表征获得了更广泛的应用,在没有任何额外训练的情况下,本文模型提取的特征向量能够较好地应用于主题聚类、学者推荐等分析任务。研究结果表明,PAITKG通过构建并表征论文的学术网络,有效融合了文献的关联信息,提高了对文献数据的理解能力,而且其学习到的表征具有优秀的泛化潜力,能够应用于各种文献分析工作。展开更多
基金Project(60801053) supported by the National Natural Science Foundation of ChinaProject(4082025) supported by the Beijing Natural Science Foundation,China+4 种基金Project(20070004037) supported by the Doctoral Foundation of ChinaProject(2009JBM135,2011JBM023) supported by the Fundamental Research Funds for the Central Universities of ChinaProject(151139522) supported by the Hongguoyuan Innovative Talent Program of Beijing Jiaotong University,ChinaProject(YB20081000401) supported by the Beijing Excellent Doctoral Thesis Program,ChinaProject (2006CB303105) supported by the National Basic Research Program of China
文摘To improve motion graph based motion synthesis,semantic control was introduced.Hybrid motion features including both numerical and user-defined semantic relational features were extracted to encode the characteristic aspects contained in the character's poses of the given motion sequences.Motion templates were then automatically derived from the training motions for capturing the spatio-temporal characteristics of an entire given class of semantically related motions.The data streams of motion documents were automatically annotated with semantic motion class labels by matching their respective motion class templates.Finally,the semantic control was introduced into motion graph based human motion synthesis.Experiments of motion synthesis demonstrate the effectiveness of the approach which enables users higher level of semantically intuitive control and high quality in human motion synthesis from motion capture database.
文摘现有的下一个兴趣点(point of interest,PoI)推荐技术存在三个主要问题:使用过于简单的方法构建用户兴趣模型、忽略用户和PoI之间在时空维度上的互动以及未能充分挖掘用户间复杂的高阶交互信息。针对这些问题,提出一种新颖的超图学习模型FSTMH,细粒度地融合时间、空间和语义信息,用于下一个PoI推荐。FSTMH包括细粒度嵌入模块和多层次嵌入模块。前者通过使用地理图卷积网络和有向超图卷积网络进行学习,获取对应的嵌入信息,并通过对比学习提升PoI表示的质量,使用细粒度超图卷积网络学习该模块的PoI嵌入;后者将多层语义超图输入到多层超图卷积网络,学习多层次语义的PoI嵌入表示。最后,模型将两个模块的PoI嵌入向量进行组合,生成最终的top-K预测结果。通过在广泛使用的三个社交网络公共数据集上进行多种实验,结果均表明FSTMH模型表现出色,说明该新模型可作为提高下一个PoI推荐的有效方法。
文摘随着科研工作者人数的不断增加,科技论文的发表数量呈现快速增长的趋势。面对海量的科技论文,文献的归档、录入和分析工作变得越发繁重。当前,针对文献的分类模型主要关注论文的内容信息,而忽略了论文相关的关联信息。为此,本文提出一种融合内容信息与学术网络的论文表征模型PAITKG (paper analysis by incorporating text and knowledge graph),引入知识图谱嵌入技术对文献的多重关联信息进行表征,采用Adapter微调的SciBERT提取内容特征,并将二者融合。在训练过程中,本文改进了动态对抗损失函数来引导模型更好地关注错误结果,并将该方法在数字人文和多模态学习两个领域的文献数据集上进行实验。在科技文献的学科多标签分类任务上,PAITKG比Baselines有显著改善,很好地提高了分类精度。除此以外,通过上游任务的学习,PAITKG的表征获得了更广泛的应用,在没有任何额外训练的情况下,本文模型提取的特征向量能够较好地应用于主题聚类、学者推荐等分析任务。研究结果表明,PAITKG通过构建并表征论文的学术网络,有效融合了文献的关联信息,提高了对文献数据的理解能力,而且其学习到的表征具有优秀的泛化潜力,能够应用于各种文献分析工作。
