loading
Papers Papers/2020

Research.Publish.Connect.

Paper

Authors: Hemerson Tacon 1 ; André Brito 1 ; Hugo Chaves 1 ; Marcelo Vieira 1 ; Saulo Villela 1 ; Helena Maia 2 ; Darwin Concha 2 and Helio Pedrini 2

Affiliations: 1 Department of Computer Science, Federal University of Juiz de Fora (UFJF), Juiz de Fora, MG, Brazil ; 2 Institute of Computing, University of Campinas (UNICAMP), Campinas, SP, Brazil

ISBN: 978-989-758-402-2

ISSN: 2184-4321

Keyword(s): Deep Learning, Human Action Recognition, Data Augmentation, Visual Rhythm, Video Analysis.

Abstract: Despite the significant progress of Deep Learning models on the image classification task, it still needs enhancements for the Human Action Recognition task. In this work, we propose to extract horizontal and vertical Visual Rhythms as well as their data augmentations as video features. The data augmentation is driven by crops extracted from the symmetric extension of the time dimension, preserving the video frame rate, which is essential to keep motion patterns. The crops provide a 2D representation of the video volume matching the fixed input size of a 2D Convolutional Neural Network. In addition, multiple crops with stride guarantee coverage of the entire video. We verified that the combination of horizontal and vertical directions leads do better results than previous methods. A multi-stream strategy combining RGB and Optical Flow information is modified to include the additional spatiotemporal streams: one for the horizontal Symmetrically Extended Visual Rhythm (SEVR), and anothe r for the vertical one. Results show that our method achieves accuracy rates close to the state of the art on the challenging UCF101 and HMDB51 datasets. Furthermore, we assessed the impact of data augmentations methods for Human Action Recognition and verified an increase of 10% for the UCF101 dataset. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.238.174.50

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Tacon, H.; Brito, A.; Chaves, H.; Vieira, M.; Villela, S.; Maia, H.; Concha, D. and Pedrini, H. (2020). Multi-stream Architecture with Symmetric Extended Visual Rhythms for Deep Learning Human Action Recognition. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-402-2 ISSN 2184-4321, pages 351-358. DOI: 10.5220/0008958003510358

@conference{visapp20,
author={Hemerson Tacon. and André Brito. and Hugo Chaves. and Marcelo Vieira. and Saulo Villela. and Helena Maia. and Darwin Concha. and Helio Pedrini.},
title={Multi-stream Architecture with Symmetric Extended Visual Rhythms for Deep Learning Human Action Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2020},
pages={351-358},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008958003510358},
isbn={978-989-758-402-2},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Multi-stream Architecture with Symmetric Extended Visual Rhythms for Deep Learning Human Action Recognition
SN - 978-989-758-402-2
IS - 2184-4321
AU - Tacon, H.
AU - Brito, A.
AU - Chaves, H.
AU - Vieira, M.
AU - Villela, S.
AU - Maia, H.
AU - Concha, D.
AU - Pedrini, H.
PY - 2020
SP - 351
EP - 358
DO - 10.5220/0008958003510358

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.