PUNet

Temporal Action Proposal Generation With Positive Unlabeled Learning Using Key Frame Annotations

Conference paper (2021)

Authors

O.S. Kayhan Pattern Recognition and Bioinformatics - EEMCS
J.C. van Gemert Pattern Recognition and Bioinformatics - EEMCS
Research Group
Pattern Recognition and Bioinformatics (EEMCS) (TU Delft)
Proposal Generation Action Localization Positive-Unlabeled Learning
More Info
expand_more

Published Date

2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Pattern Recognition and Bioinformatics

Abstract

Popular approaches to classifying action segments in long, realistic, untrimmed videos start with high quality action proposals. Current action proposal methods based on deep learning are trained on labeled video segments. Obtaining annotated segments for untrimmed videos is time consuming, expensive and error-prone as annotated temporal action boundaries are imprecise, subjective and inconsistent. By embracing this uncertainty we explore to significantly speed up temporal annotations by using just a single key frame label for each action instance instead of the inherently imprecise start and end frames. To tackle the class imbalance by using only a single frame, we evaluate an extremely simple Positive-Unlabeled algorithm (PU-learning). We demonstrate on THUMOS’14 and ActivityNet that using a single key frame label give good results while being significantly faster to annotate. In addition, we show that our simple method, PUNet
1, is data-efficient which further reduces the need for expensive annotations.