arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.12465cs.CVcs.AIcs.CLcs.MM
收藏

PDKEEPAAA:用于多模态视频摘要的生成式预训练Transformer-2

GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization

University of Amsterdam(阿姆斯特丹大学);BBC Research and Development(BBC研发部)

Jia-Hong Huang, Luka Murn, Marta Mrak, Marcel Worring

摘要:

传统的视频摘要方法生成固定的视频表示,而不管用户的兴趣。因此,这样的方法限制了用户在内容搜索和探索场景中的期望。多模态视频摘要是用来解决这个问题的方法之一。当使用多模态视频摘要来帮助视频探索时,基于文本的查询被认为是视频摘要生成的主要驱动因素之一,因为它是用户定义的。因此,对基于文本的查询和视频进行有效的编码对于多模态视频摘要的任务都是重要的。在这项工作中,提出了一种新的方法,使用专门的注意力网络和上下文的单词表示来解决这个任务。该模型包括一个上下文视频摘要控制器,多模态注意力机制,一个交互式注意力网络,和一个视频摘要生成器。通过对现有多模态视频摘要基准的评价,实验结果表明,与现有方法相比,该模型的准确率提高了+5.88%,F1分数提高了+4.06%。

英文摘要:

Traditional video summarization methods generate fixed video representations regardless of user interest. Therefore such methods limit users' expectations in content search and exploration scenarios. Multi-modal video summarization is one of the methods utilized to address this problem. When multi-modal video summarization is used to help video exploration, a text-based query is considered as one of the main drivers of video summary generation, as it is user-defined. Thus, encoding the text-based query and the video effectively are both important for the task of multi-modal video summarization. In this work, a new method is proposed that uses a specialized attention network and contextualized word representations to tackle this task. The proposed model consists of a contextualized video summary controller, multi-modal attention mechanisms, an interactive attention network, and a video summary generator. Based on the evaluation of the existing multi-modal video summarization benchmark, experimental results show that the proposed model is effective with the increase of +5.88% in accuracy and +4.06% increase of F1-score, compared with the state-of-the-art 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。

↑