Back to Search Start Over

Unsupervised Action Segmentation for Instructional Videos

Authors :
Piergiovanni, AJ
Angelova, Anelia
Ryoo, Michael S.
Essa, Irfan
Publication Year :
2021

Abstract

In this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos, which are rarely annotated with atomic actions. We present an unsupervised approach to learn atomic actions of structured human tasks from a variety of instructional videos based on a sequential stochastic autoregressive model for temporal segmentation of videos. This learns to represent and discover the sequential relationship between different atomic actions of the task, and which provides automatic and unsupervised self-labeling.<br />Comment: 4 page abstract for LUV workshop

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2106.03738
Document Type :
Working Paper