Large-scale Web Video Shot Ranking Based on Visual Features and Tag Co-occurrence
Large-scale Web Video Shot Ranking Based on Visual Features and Tag Co-occurrence
复制标题
基于视觉特征和标签共现的大规模网络视频镜头排序
DOI：
10.1145/2502081.2502139
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Do Hang Nga and Keiji Yanai
中科院分区：
文献类型：
--
作者：
Kento Sugiura;Arata Hayashi;Ting Ting Dong;Yoshiharu Ishikawa;Do Hang Nga and Keiji Yanai
在本文中，我们提出了一种新的排名方法，VisualTextualRank，它扩展了[1]和[2]。我们的方法是基于二分图上的随机游走，有效地整合视频镜头的视觉信息和Web视频的标签信息。请注意，我们不是将文本信息视为镜头排名的附加特征，而是探索镜头及其相应视频的文本信息之间的相互强化，以提高镜头排名。我们将我们提出的方法应用于从Web视频中自动提取特定动作的相关视频镜头的系统[3]。基于我们的实验结果，我们证明了我们的排名方法可以提高视频镜头检索的性能。
In this paper, we propose a novel ranking method, VisualTextualRank, which extends [1] and [2]. Our method is based on random walk over bipartite graph to integrate visual information of video shots and tag information of Web videos effectively. Note that instead of treating the textual information as an additional feature for shot ranking, we explore the mutual reinforcement between shots and textual information of their corresponding videos to improve shot ranking. We apply our proposed method to the system of extracting automatically relevant video shots of specific actions from Web videos [3]. Based on our experimental results, we demonstrate that our ranking method can improve the performance of video shot retrieval.