arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.04768cs.MMcs.AIcs.CV
收藏

DualVGR:一种用于视频问答的双视觉图推理单元

DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering

Nanjing University of Posts and Telecommunications(南京邮电大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)

Jianyu Wang, Bing-Kun Bao, Changsheng Xu

摘要:

视频问答是一个具有挑战性的任务,它要求智能体能够理解丰富的视频内容并进行时空推理。然而,现有的基于图的方法不能很好地执行多步推理,忽略了VideoQA的两个特性:(1)即使对于同一个视频,不同的问题可能需要不同数量的视频片段或对象来推断答案;(2)在推理过程中,外观和运动特征具有复杂的相互依赖性,它们相互关联,相互补充。基于这些观察,我们提出了一个双视觉图推理单元(DualVGR),它以端到端的方式对视频进行推理。我们的DualVGR的第一个贡献是设计了一个可解释的查询惩罚模块,它可以通过多个循环的推理过滤掉不相关的视觉特征。第二个贡献是提出了基于视频的多视图图注意力网络,它捕捉外观和运动特征之间的关系。我们的DualVGR网络在基准MSVD-QA和SVQA数据集上实现了最先进的性能,并在基准MSRVTT-QA数据集上展示了具有竞争力的结果。我们的代码可在https://github.com/MMIR/DualVGR-VideoQA上获得。

英文摘要:

Video question answering is a challenging task, which requires agents to be able to understand rich video contents and perform spatial-temporal reasoning. However, existing graph-based methods fail to perform multi-step reasoning well, neglecting two properties of VideoQA: (1) Even for the same video, different questions may require different amount of video clips or objects to infer the answer with relational reasoning; (2) During reasoning, appearance and motion features have complicated interdependence which are correlated and complementary to each other. Based on these observations, we propose a Dual-Visual Graph Reasoning Unit (DualVGR) which reasons over videos in an end-to-end fashion. The first contribution of our DualVGR is the design of an explainable Query Punishment Module, which can filter out irrelevant visual features through multiple cycles of reasoning. The second contribution is the proposed Video-based Multi-view Graph Attention Network, which captures the relations between appearance and motion features. Our DualVGR network achieves state-of-the-art performance on the benchmark MSVD-QA and SVQA datasets, and demonstrates competitive results on benchmark MSRVTT-QA datasets. Our code is available at https://github.com/MMIR/DualVGR-VideoQA.

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。

↑