Multimodal Subtask Graph Generation from Instructional Videos

arxiv(2023)

引用 0|浏览27
暂无评分
摘要
Real-world tasks consist of multiple inter-dependent subtasks (e.g., a dirty pan needs to be washed before it can be used for cooking). In this work, we aim to model the causal dependencies between such subtasks from instructional videos describing the task. This is a challenging problem since complete information about the world is often inaccessible from videos, which demands robust learning mechanisms to understand the causal structure of events. We present Multimodal Subtask Graph Generation (MSG2), an approach that constructs a Subtask Graph defining the dependency between a task's subtasks relevant to a task from noisy web videos. Graphs generated by our multimodal approach are closer to human-annotated graphs compared to prior approaches. MSG2 further performs the downstream task of next subtask prediction 85% and 30% more accurately than recent video transformer models in the ProceL and CrossTask datasets, respectively.
更多
查看译文
关键词
multimodal subtask graph generation,instructional videos
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要