Uncovering the Temporal Context for Video Question Answering

摘要

In this work, we introduce Video Question Answering in the temporal domain to infer the past, describe the present and predict the future. We present an encoder–decoder approach using Recurrent Neural Networks to learn the temporal structures of videos and introduce a dual-channel ranking loss to answer multiple-choice questions. We explore approaches for finer understanding of video content using the question form of “fill-in-the-blank”, and collect our Video Context QA dataset consisting of 109,895 video clips with a total duration of more than 1000 h from existing TACoS, MPII-MD and MEDTest 14 datasets. In addition, 390,744 corresponding questions are generated from annotations. Extensive experiments demonstrate that our approach significantly outperforms the compared baselines.