Robust Action Segmentation from Timestamp Supervision
Yaser Souri (Microsoft), Yazan Abu Farha (Birzeit University), Emad Bahrami (University of Bonn),* Gianpiero Francesca (Toyota-Europe), Jürgen Gall (University of Bonn)
The 33rd British Machine Vision Conference
Abstract
Action segmentation is the task of predicting an action label for each frame of an untrimmed video. As obtaining annotations to train an approach for action segmentation in a fully supervised way is expensive, various approaches have been proposed to train action segmentation models using different forms of weak supervision, e.g., action transcripts, action sets, or more recently timestamps. Timestamp supervision is a promising type of weak supervision as obtaining one timestamp per action is less expensive than annotating all frames, but it provides more information than other forms of weak supervision. However, previous works assume that every action instance is annotated with a timestamp, which is a restrictive assumption since it assumes that annotators do not miss any action. In this work, we relax this restrictive assumption and take missing annotations for some action instances into account. We show that our approach is more robust to missing annotations compared to other approaches and various baselines.Video
Citation
@inproceedings{Souri_2022_BMVC,
author = {Yaser Souri and Yazan Abu Farha and Emad Bahrami and Gianpiero Francesca and Jürgen Gall},
title = {Robust Action Segmentation from Timestamp Supervision},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0392.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by