arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.02467cs.CV
收藏

ActivityNet-QA:一个通过问答理解复杂网络视频的数据集

ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering

Hangzhou Dianzi University(杭州电子科技大学);Zhejiang University(浙江大学);University of Sydney(悉尼大学)

Zhou Yu, Dejing Xu, Jun Yu, Ting Yu, Zhou Zhao, Yueting Zhuang, Dacheng Tao

摘要:

在建模语言和视觉方面的最新发展已经成功地应用于图像问答。将这一研究方向扩展到视频领域的视频问答(VideoQA)是非常必要和自然的。相比于图像领域的大规模和完全注释的基准数据集,VideoQA数据集仅限于小规模和自动生成等,这些限制限制了它们在实践中的适用性。在这里,我们介绍ActivityNet-QA,一个完全注释的大规模VideoQA数据集。该数据集由来自流行的ActivityNet数据集的5,800个复杂网络视频的58,000个QA对组成。我们对ActivityNet-QA数据集进行了统计分析,并通过比较现有的VideoQA基线对其进行了广泛的实验。此外,我们探索各种视频表示策略,以提高VideoQA的性能,特别是对于长视频。该数据集可在https://github.com/MILVLG/activitynet-qa上获得

英文摘要:

Recent developments in modeling language and vision have been successfully applied to image question answering. It is both crucial and natural to extend this research direction to the video domain for video question answering (VideoQA). Compared to the image domain where large scale and fully annotated benchmark datasets exists, VideoQA datasets are limited to small scale and are automatically generated, etc. These limitations restrict their applicability in practice. Here we introduce ActivityNet-QA, a fully annotated and large scale VideoQA dataset. The dataset consists of 58,000 QA pairs on 5,800 complex web videos derived from the popular ActivityNet dataset. We present a statistical analysis of our ActivityNet-QA dataset and conduct extensive experiments on it by comparing existing VideoQA baselines. Moreover, we explore various video representation strategies to improve VideoQA performance, especially for long videos. The dataset is available at https://github.com/MILVLG/activitynet-qa

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。

↑