Timestamp-Supervised Action Segmentation with Graph Convolutional Networks

We introduce a novel approach for temporal activity segmentation with timestamp supervision. Our main contribution is a graph convolutional network, which is learned in an end-to-end manner to exploit both frame features and connections between neighboring frames to generate dense framewise labels f...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-08
Main Authors: Khan, Hamza, Haresh, Sanjay, Ahmed, Awais, Siddiqui, Shakeeb, Konin, Andrey, Zia, M Zeeshan, Tran, Quoc-Huy
Format: Article
Language:English
Subjects:
Artificial neural networks
Labels
Multilayer perceptrons
Multilayers
Salads
Segmentation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce a novel approach for temporal activity segmentation with timestamp supervision. Our main contribution is a graph convolutional network, which is learned in an end-to-end manner to exploit both frame features and connections between neighboring frames to generate dense framewise labels from sparse timestamp labels. The generated dense framewise labels can then be used to train the segmentation model. In addition, we propose a framework for alternating learning of both the segmentation model and the graph convolutional model, which first initializes and then iteratively refines the learned models. Detailed experiments on four public datasets, including 50 Salads, GTEA, Breakfast, and Desktop Assembly, show that our method is superior to the multi-layer perceptron baseline, while performing on par with or better than the state of the art in temporal activity segmentation with timestamp supervision.
ISSN:2331-8422