ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
This provides a crucial resource for researchers in video understanding, though it is incremental as it extends existing image QA datasets to the video domain.
The authors introduced ActivityNet-QA, a large-scale dataset of 58,000 QA pairs on 5,800 complex web videos to address the lack of fully annotated benchmarks for video question answering, enabling improved performance through various video representation strategies.
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