Learning Temporal Action Proposals With Fewer Labels

Jingwei Ji, Kaidi Cao, Juan Carlos Niebles; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 7073-7082


Temporal action proposals are a common module in action detection pipelines today. Most current methods for training action proposal modules rely on fully supervised approaches that require large amounts of annotated temporal action intervals in long video sequences. The large cost and effort in annotation that this entails motivate us to study the problem of training proposal modules with less supervision. In this work, we propose a semi-supervised learning algorithm specifically designed for training temporal action proposal networks. When only a small number of labels are available, our semi-supervised method generates significantly better proposals than the fully-supervised counterpart and other strong semi-supervised baselines. We validate our method on two challenging action detection video datasets, ActivityNet v1.3 and THUMOS14. We show that our semi-supervised approach consistently matches or outperforms the fully supervised state-of-the-art approaches.

Related Material

author = {Ji, Jingwei and Cao, Kaidi and Niebles, Juan Carlos},
title = {Learning Temporal Action Proposals With Fewer Labels},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}