How to Make a BLT Sandwich? Learning to Reason towards Understanding Web Instructional Videos
This work addresses the challenge of reasoning in long instructional videos for applications in video understanding, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of understanding long instructional videos by introducing a question-answering dataset called YouQuek and proposing a Recurrent Graph Convolutional Network (RGCN) model, which achieves the best QA accuracy and shows improved performance with human-annotated descriptions.
Understanding web instructional videos is an essential branch of video understanding in two aspects. First, most existing video methods focus on short-term actions for a-few-second-long video clips; these methods are not directly applicable to long videos. Second, unlike unconstrained long videos, e.g., movies, instructional videos are more structured in that they have step-by-step procedure constraining the understanding task. In this paper, we study reasoning on instructional videos via question-answering (QA). Surprisingly, it has not been an emphasis in the video community despite its rich applications. We thereby introduce YouQuek, an annotated QA dataset for instructional videos based on the recent YouCook2. The questions in YouQuek are not limited to cues on one frame but related to logical reasoning in the temporal dimension. Observing the lack of effective representations for modeling long videos, we propose a set of carefully designed models including a novel Recurrent Graph Convolutional Network (RGCN) that captures both temporal order and relation information. Furthermore, we study multiple modalities including description and transcripts for the purpose of boosting video understanding. Extensive experiments on YouQuek suggest that RGCN performs the best in terms of QA accuracy and a better performance is gained by introducing human annotated description.