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

6 Jun 2019  ·  Zhou Yu, Dejing Xu, Jun Yu, Ting Yu, Zhou Zhao, Yueting Zhuang, DaCheng Tao ·

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

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Video Question Answering ActivityNet-QA E-SA Accuracy 0.318 # 5
Video Question Answering ActivityNet-QA E-VQA Accuracy 0.251 # 7
Video Question Answering ActivityNet-QA E-MN Accuracy 0.271 # 6

Methods


No methods listed for this paper. Add relevant methods here