Cover Image

ICE-GCN: An interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition

CC BY

Saved in:
Bibliographic Details
Main Authors: Shuxi, Wang, Jiahui, Pan, Binyuan, Huang
Format: Book
Language:English
Published: Springer 2023
Subjects:
pose estimation algorithms
convolutional network frameworks
Online Access:https://link.springer.com/article/10.1007/s00138-023-01386-2
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7673
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-7673
record_format dspace
spelling oai:localhost:PNK-76732023-04-07T08:01:51Z ICE-GCN: An interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition Shuxi, Wang Jiahui, Pan Binyuan, Huang pose estimation algorithms convolutional network frameworks CC BY Thanks to the development of depth sensors and pose estimation algorithms, skeleton-based action recognition has become prevalent in the computer vision community. Most of the existing works are based on spatio-temporal graph convolutional network frameworks, which learn and treat all spatial or temporal features equally, ignoring the interaction with channel dimension to explore different contributions of different spatio-temporal patterns along the channel direction and thus losing the ability to distinguish confusing actions with subtle differences. In this paper, an interactional channel excitation (ICE) module is proposed to explore discriminative spatio-temporal features of actions by adaptively recalibrating channel-wise pattern maps. 2023-04-07T08:01:51Z 2023-04-07T08:01:51Z 2023 Book https://link.springer.com/article/10.1007/s00138-023-01386-2 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7673 en application/pdf Springer
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic pose estimation algorithms
convolutional network frameworks
spellingShingle pose estimation algorithms
convolutional network frameworks
Shuxi, Wang
Jiahui, Pan
Binyuan, Huang
ICE-GCN: An interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition
description CC BY
format Book
author Shuxi, Wang
Jiahui, Pan
Binyuan, Huang
author_facet Shuxi, Wang
Jiahui, Pan
Binyuan, Huang
author_sort Shuxi, Wang
title ICE-GCN: An interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition
title_short ICE-GCN: An interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition
title_full ICE-GCN: An interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition
title_fullStr ICE-GCN: An interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition
title_full_unstemmed ICE-GCN: An interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition
title_sort ice-gcn: an interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition
publisher Springer
publishDate 2023
url https://link.springer.com/article/10.1007/s00138-023-01386-2
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7673
_version_ 1762546699422662656
score 8.891145

Similar Items