Unsupervised Discovery of Actions in Instructional Videos
This addresses the challenge of extracting structured activity steps from unannotated instructional videos for applications like autonomous robots or virtual assistants.
The paper tackles the problem of automatically discovering atomic actions in instructional videos without supervision, proposing a sequential stochastic autoregressive model that outperforms state-of-the-art unsupervised methods by large margins.
In this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos. Instructional videos contain complex activities and are a rich source of information for intelligent agents, such as, autonomous robots or virtual assistants, which can, for example, automatically `read' the steps from an instructional video and execute them. However, videos are rarely annotated with atomic activities, their boundaries or duration. We present an unsupervised approach to learn atomic actions of structured human tasks from a variety of instructional videos. We propose a sequential stochastic autoregressive model for temporal segmentation of videos, which learns to represent and discover the sequential relationship between different atomic actions of the task, and which provides automatic and unsupervised self-labeling for videos. Our approach outperforms the state-of-the-art unsupervised methods with large margins. We will open source the code.