Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/144139
Title: Learning progressive joint propagation for human motion prediction
Authors: Cai, Yujun
Huang, Lin
Wang, Yiwei
Cham, Tat-Jen
Cai, Jianfei
Yuan, Junsong
Liu, Jun
Yang, Xu
Zhu, Yiheng
Shen, Xiaohui
Liu, Ding
Liu, Jing
Thalmann, Nadia Magnenat
Keywords: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2020
Source: Cai, Y., Huang, L., Wang, Y., Cham, T.-J., Cai, J., Yuan, J., ... Thalmann, N. M. (2020). Learning progressive joint propagation for human motion prediction. European Conference on Computer Vision (ECCV).
Conference: European Conference on Computer Vision (ECCV)
Abstract: Despite the great progress in human motion prediction, it remains a challenging task due to the complicated structural dynamics of human behaviors. In this paper, we address this problem in three aspects. First, to capture the long-range spatial correlations and temporal dependencies, we apply a transformer-based architecture with the global attention mechanism. Speci cally, we feed the network with the sequential joints encoded with the temporal information for spatial and temporal explorations. Second, to further exploit the inherent kinematic chains for better 3D structures, we apply a progressive-decoding strategy, which performs in a central-to-peripheral extension according to the structural connectivity. Last, in order to incorporate a general motion space for high-quality prediction, we build a memory-based dictionary, which aims to preserve the global motion patterns in training data to guide the predictions.We evaluate the proposed method on two challenging benchmark datasets (Human3.6M and CMU-Mocap). Experimental results show our superior performance compared with the state-of-the-art approaches.
URI: https://hdl.handle.net/10356/144139
Schools: School of Computer Science and Engineering 
Research Centres: Institute for Media Innovation (IMI) 
Rights: © 2020 Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of a conference paper published in European Conference on Computer Vision (ECCV).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IMI Conference Papers

Files in This Item:
File Description SizeFormat 
2020-Cai_etal-ECCV2020-human-motion-prediction.pdf1.25 MBAdobe PDFThumbnail
View/Open

Page view(s)

420
Updated on Mar 18, 2024

Download(s) 10

440
Updated on Mar 18, 2024

Google ScholarTM

Check

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