arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.01067cs.CVcs.AI
收藏

使用弱注释的视频描述

Video Captioning Using Weak Annotation

Beijing Institute of Technology(北京理工大学)

Jingyi Hou, Yunde Jia, Xinxiao wu, Yayun Qi

摘要:

视频描述近年来取得了令人瞩目的进展。现有方法性能改进的一个关键原因在于大量成对的视频-句子数据,但是收集如此强的注释,即,高质量的句子,费时费力。事实上,现在存在着数量惊人的视频,这些视频具有弱注释,仅包含动作和对象等语义概念。在本文中,我们研究使用弱标注代替强标注来训练一个视频描述模型。为此,我们提出了一个渐进的视觉推理方法,逐步产生细句子弱注释推断更多的语义概念和依赖关系的视频描述。为了对概念关系进行建模,我们使用依赖树,该依赖树通过利用来自大句子语料库的外部知识来构建。通过遍历依赖树,生成句子来训练字幕模型。因此,我们开发了一种迭代细化算法,通过生成依赖树来细化句子,并以另一种训练方式使用细化的句子来微调字幕模型。实验结果表明,我们的方法使用弱注释是非常有竞争力的国家的最先进的方法使用强注释。

英文摘要:

Video captioning has shown impressive progress in recent years. One key reason of the performance improvements made by existing methods lie in massive paired video-sentence data, but collecting such strong annotation, i.e., high-quality sentences, is time-consuming and laborious. It is the fact that there now exist an amazing number of videos with weak annotation that only contains semantic concepts such as actions and objects. In this paper, we investigate using weak annotation instead of strong annotation to train a video captioning model. To this end, we propose a progressive visual reasoning method that progressively generates fine sentences from weak annotations by inferring more semantic concepts and their dependency relationships for video captioning. To model concept relationships, we use dependency trees that are spanned by exploiting external knowledge from large sentence corpora. Through traversing the dependency trees, the sentences are generated to train the captioning model. Accordingly, we develop an iterative refinement algorithm that refines sentences via spanning dependency trees and fine-tunes the captioning model using the refined sentences in an alternative training manner. Experimental results demonstrate that our method using weak annotation is very competitive to the state-of-the-art methods using strong annotation.

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。

↑