Adversarial Refinement Network for Human Motion Prediction

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

  • Yanrui Bin
  • Wenqing Chu
  • Xuan Cao
  • Yanhao Ge
  • Chengjie Wang
  • Jilin Li
  • Feiyue Huang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationComputer Vision – ACCV 2020
Subtitle of host publication15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 – December 4, 2020, Revised Selected Papers
EditorsHiroshi Ishikawa, Cheng-Lin Liu, Tomas Pajdla, Jianbo Shi
Place of PublicationCham
PublisherSpringer
Pages454-469
VolumePart II
ISBN (Electronic)9783030695323
ISBN (Print)9783030695316
Publication statusPublished - 2021

Publication series

NameLecture Notes in Computer Science
Volume12623
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Title15th Asian Conference on Computer Vision (ACCV 2020)
LocationVirtual
PlaceJapan
CityKyoto
Period30 November - 4 December 2020

Abstract

Human motion prediction aims to predict future 3D skeletal sequences by giving a limited human motion as inputs. Two popular methods, recurrent neural networks and feed-forward deep networks, are able to predict rough motion trend, but motion details such as limb movement may be lost. To predict more accurate future human motion, we propose an Adversarial Refinement Network (ARNet) following a simple yet effective coarse-to-fine mechanism with novel adversarial error augmentation. Specifically, we take both the historical motion sequences and coarse prediction as input of our cascaded refinement network to predict refined human motion and strengthen the refinement network with adversarial error augmentation. During training, we deliberately introduce the error distribution by learning through the adversarial mechanism among different subjects. In testing, our cascaded refinement network alleviates the prediction error from the coarse predictor resulting in a finer prediction robustly. This adversarial error augmentation provides rich error cases as input to our refinement network, leading to better generalization performance on the testing dataset. We conduct extensive experiments on three standard benchmark datasets and show that our proposed ARNet outperforms other state-of-the-art methods, especially on challenging aperiodic actions in both short-term and long-term predictions.

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

Adversarial Refinement Network for Human Motion Prediction. / Chao, Xianjin; Bin, Yanrui; Chu, Wenqing; Cao, Xuan; Ge, Yanhao; Wang, Chengjie; Li, Jilin; Huang, Feiyue; Leung, Howard.

Computer Vision – ACCV 2020: 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 – December 4, 2020, Revised Selected Papers. ed. / Hiroshi Ishikawa; Cheng-Lin Liu; Tomas Pajdla; Jianbo Shi. Vol. Part II Cham : Springer, 2021. p. 454-469 (Lecture Notes in Computer Science; Vol. 12623).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review