BriefGPT.xyz
Jun, 2019
ActivityNet-QA: 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
HTML
PDF
Zhou Yu, Dejing Xu, Jun Yu, Ting Yu, Zhou Zhao...
TL;DR
本文介绍一种名为ActivityNet-QA的全新、已标注的大规模VideoQA数据集，以此作为基础，探讨了在长视频情境下提高VideoQA性能的各种视频表示方法和已有的VideoQA基准测试的比较方法。
Abstract
Recent developments in
modeling
language
and
vision
have been successfully applied to image question answering. It is both crucial and nat
→