Procedural activity understanding requires perceiving human actions in terms of a broader task, where multiple keysteps are performed in sequence across a long video to reach a final goal state -- such as the steps of a recipe or a DIY fix-it task. Prior work largely treats keystep recognition in isolation of this broader structure, or else rigidly confines keysteps to align with a predefined sequential script. We propose discovering a task graph automatically from how-to videos to represent probabilistically how people tend to execute keysteps, and then leverage this graph to regularize keystep recognition in novel videos. On multiple datasets of real-world instructional videos, we show the impact: more reliable zero-shot keystep localization and improved video representation learning, exceeding the state of the art.
@article{arxiv.2307.08763,
title = {Video-Mined Task Graphs for Keystep Recognition in Instructional Videos},
author = {Kumar Ashutosh and Santhosh Kumar Ramakrishnan and Triantafyllos Afouras and Kristen Grauman},
journal= {arXiv preprint arXiv:2307.08763},
year = {2023}
}