ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
arXiv:1906.02467
Abstract
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
Accepted at AAAI 2019
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- VQA: Visual Question Answering
- Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering
- Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
- Ask Your Neurons: A Neural-based Approach to Answering Questions about Images
- Dual Attention Networks for Multimodal Reasoning and Matching
- TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering
- DeepStory: Video Story QA by Deep Embedded Memory Networks
- A Read-Write Memory Network for Movie Story Understanding