Video Question Answering on Screencast Tutorials
This work addresses a domain-specific problem for software tutorial users, but it is incremental as it adapts existing video QA methods to a new dataset.
The paper tackles video question answering on screencast tutorials by introducing a dataset with grounded answers and proposing baseline neural models, resulting in significant performance improvements through multi-modal context and domain knowledge integration.
This paper presents a new video question answering task on screencast tutorials. We introduce a dataset including question, answer and context triples from the tutorial videos for a software. Unlike other video question answering works, all the answers in our dataset are grounded to the domain knowledge base. An one-shot recognition algorithm is designed to extract the visual cues, which helps enhance the performance of video question answering. We also propose several baseline neural network architectures based on various aspects of video contexts from the dataset. The experimental results demonstrate that our proposed models significantly improve the question answering performances by incorporating multi-modal contexts and domain knowledge.