arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.05381cs.CVcs.IRcs.MM
收藏

基于文本的视频检索中的双重编码

Dual Encoding for Video Retrieval by Text

College of Computer and Information Engineering, Zhejiang Gongshang University(浙江工商大学计算机与信息工程学院);Renmin University of China(中国人民大学);School of Computing, National University of Singapore(新加坡国立大学计算机学院);School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机与信息工程学院)

Jianfeng Dong, Xirong Li, Chaoxi Xu, Xun Yang, Gang Yang, Xun Wang, Meng Wang

摘要:

本文研究了基于文本的视频检索这一具有挑战性的问题。在这样的检索范例中,最终用户通过专门以自然语言句子的形式描述的自组织查询来搜索未标记的视频,而不提供视觉示例。给定视频作为帧序列和查询作为词序列,有效的序列到序列跨模态匹配是至关重要的。为此,需要首先将这两种模态编码为实值向量,然后投影到公共空间中。在本文中,我们通过提出一个双重深度编码网络来实现这一点,该网络将视频和查询编码为它们自己的强大密集表示。我们的创新是双重的。首先,与采用特定单级编码器的现有技术不同,所提出的网络执行多级编码,该多级编码以从粗到细的方式表示两种模态的丰富内容。其次,不同于传统的公共空间学习算法,这是基于概念或基于潜在空间,我们引入混合空间学习,结合了潜在空间的高性能和概念空间的良好的可解释性。双重编码在概念上简单,实际上有效,并且通过混合空间学习进行端到端训练。在四个具有挑战性的视频数据集上的大量实验表明了新方法的可行性。

英文摘要:

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Our novelty is two-fold. First, different from prior art that resorts to a specific single-level encoder, the proposed network performs multi-level encoding that represents the rich content of both modalities in a coarse-to-fine fashion. Second, different from a conventional common space learning algorithm which is either concept based or latent space based, we introduce hybrid space learning which combines the high performance of the latent space and the good interpretability of the concept space. Dual encoding is conceptually simple, practically effective and end-to-end trained with hybrid space learning. Extensive experiments on four challenging video datasets show the viability of the new method.

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。

↑