arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02648cs.LGstat.ML
收藏

基于图Wasserstein相关分析的电影检索

Graph Wasserstein Correlation Analysis for Movie Retrieval

Nanjing University of Science and Technology(南京理工大学)

Xueya Zhang, Tong Zhang, Xiaobin Hong, Zhen Cui, Jian Yang

摘要:

在以人为中心的检索中,电影图在连接视频和文本的异质模态方面起着重要的作用。在这项工作中,我们提出了图Wasserstein相关分析(GWCA)来处理其中的核心问题,即跨异构图比较。引入谱图滤波对图信号进行编码,然后将其嵌入Wasserstein空间中的概率分布,称为图Wasserstein度量学习。图信号滤波与度量学习的这种无缝集成导致两个学习过程的惊人一致性,其中度量学习的目标只是优化信号滤波器,反之亦然。此外,我们推导出的图比较模型的解决方案作为一个经典的广义特征值分解问题,它有一个精确的封闭形式的解决方案。最后,GWCA连同电影/文本图生成统一到电影检索的框架来评估我们提出的方法。在MovieGrpahs数据集上的大量实验证明了我们的GWCA以及整个框架的有效性。

英文摘要:

Movie graphs play an important role to bridge heterogenous modalities of videos and texts in human-centric retrieval. In this work, we propose Graph Wasserstein Correlation Analysis (GWCA) to deal with the core issue therein, i.e, cross heterogeneous graph comparison. Spectral graph filtering is introduced to encode graph signals, which are then embedded as probability distributions in a Wasserstein space, called graph Wasserstein metric learning. Such a seamless integration of graph signal filtering together with metric learning results in a surprise consistency on both learning processes, in which the goal of metric learning is just to optimize signal filters or vice versa. Further, we derive the solution of the graph comparison model as a classic generalized eigenvalue decomposition problem, which has an exactly closed-form solution. Finally, GWCA together with movie/text graphs generation are unified into the framework of movie retrieval to evaluate our proposed method. Extensive experiments on MovieGrpahs dataset demonstrate the effectiveness of our GWCA as well as the entire framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑