Action Segmentation on Representations of Skeleton Sequences Using Transformer Networks

We propose an approach for action segmentation by representing motions as images. A transformer object detection network is used to segment the sequences from the representation images. We examine different encoding approaches, normalization strategies and skeleton joint orders in an extensive exper...

Full description

Saved in:
Bibliographic Details
Main Authors: Haring, Simon, Memmesheimer, Raphael, Paulus, Dietrich
Format: Conference Proceeding
Language:English
Subjects:
Action segmentation
Conferences
Estimation
Image coding
Image recognition
Image segmentation
Motion segmentation
object detection
skeleton sequence
Transformer
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose an approach for action segmentation by representing motions as images. A transformer object detection network is used to segment the sequences from the representation images. We examine different encoding approaches, normalization strategies and skeleton joint orders in an extensive experiment study. Our approach is evaluated on skeleton sequences from the PKU-MMD dataset. We successfully apply transformer networks for action segmentation on skeleton sequences. Our proposed approach achieves high class accuracies while start and end-time estimation of the action segments are subject to further improvement.
ISSN:2381-8549
DOI:10.1109/ICIP42928.2021.9506687