Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/140842
Title: Deformable pose traversal convolution for 3D action and gesture recognition
Authors: Weng, Junwu
Liu, Mengyuan
Jiang, Xudong
Yuan, Junsong
Keywords: Engineering::Computer science and engineering
Issue Date: 2018
Source: Weng, J., Liu, M., Jiang, X., & Yuan, J. (2018). Deformable pose traversal convolution for 3D action and gesture recognition. Proceedings of Computer Vision – 15th European Conference on Computer Vision 2018, 142-157. doi:10.1007/978-3-030-01234-2_9
Abstract: The representation of 3D pose plays a critical role for 3D action and gesture recognition. Rather than representing a 3D pose directly by its joint locations, in this paper, we propose a Deformable Pose Traversal Convolution Network that applies one-dimensional convolution to traverse the 3D pose for its representation. Instead of fixing the receptive field when performing traversal convolution, it optimizes the convolution kernel for each joint, by considering contextual joints with various weights. This deformable convolution better utilizes the contextual joints for action and gesture recognition and is more robust to noisy joints. Moreover, by feeding the learned pose feature to a LSTM, we perform end-to-end training that jointly optimizes 3D pose representation and temporal sequence recognition. Experiments on three benchmark datasets validate the competitive performance of our proposed method, as well as its efficiency and robustness to handle noisy joints of pose.
URI: https://hdl.handle.net/10356/140842
DOI: 10.1007/978-3-030-01234-2_9
Rights: © 2018 Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of an article published in Proceedings of Computer Vision – 15th European Conference on Computer Vision 2018. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-01234-2_9
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IMI Conference Papers

Files in This Item:
File Description SizeFormat 
Junwu_Weng_Deformable_Pose_Traversal_ECCV_2018_paper.pdf2 MBAdobe PDFThumbnail
View/Open

Page view(s)

39
checked on Sep 28, 2020

Download(s)

3
checked on Sep 28, 2020

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.