Papers
arxiv:2203.04251

End-to-End Semi-Supervised Learning for Video Action Detection

Published on Mar 8, 2022
Authors:

Abstract

A semi-supervised video action detection method using end-to-end consistency and novel spatio-temporal regularization constraints achieves competitive performance with limited labeled data.

AI-generated summary

In this work, we focus on semi-supervised learning for video action detection which utilizes both labeled as well as unlabeled data. We propose a simple end-to-end consistency based approach which effectively utilizes the unlabeled data. Video action detection requires both, action class prediction as well as a spatio-temporal localization of actions. Therefore, we investigate two types of constraints, classification consistency, and spatio-temporal consistency. The presence of predominant background and static regions in a video makes it challenging to utilize spatio-temporal consistency for action detection. To address this, we propose two novel regularization constraints for spatio-temporal consistency; 1) temporal coherency, and 2) gradient smoothness. Both these aspects exploit the temporal continuity of action in videos and are found to be effective for utilizing unlabeled videos for action detection. We demonstrate the effectiveness of the proposed approach on two different action detection benchmark datasets, UCF101-24 and JHMDB-21. In addition, we also show the effectiveness of the proposed approach for video object segmentation on the Youtube-VOS which demonstrates its generalization capability The proposed approach achieves competitive performance by using merely 20% of annotations on UCF101-24 when compared with recent fully supervised methods. On UCF101-24, it improves the score by +8.9% and +11% at 0.5 f-mAP and v-mAP respectively, compared to supervised approach.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2203.04251 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2203.04251 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2203.04251 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.