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

doi:10.1007/978-3-030-69532-3_28

Cited by 9 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Empirically, two main strategies are deployed by leveraging GANs: promoting GANs framework performance and researching how to improve human motion prediction by these frameworks. These methods include: HP-GAN [7], BiHMP-GAN [40],STMI-GAN [86],GAN-poser [37],AM-GAN [56],TC-GAN [16], AGED [28], ARNet [12], SGAN [62].…”

Section: Gan-based Methodsmentioning

confidence: 99%

“…Mathematically, these parameters are mapped to different mathematical spaces and abstracted into different distributions whose features are easy to be extracted by the network. As is shown in Tab 1, representative papers in this category are: SRNN [36], AGED [28], QuaterNet [79], LTD [67], HMR [60], MGCN [110], ARNet [12], LDR [17], LPJP [11], HRI [66], JDM [91], SGRU [62]. MT-GCN [15], MPTC [57], MST-GNN [47], MMA [68].…”

Section: Human Pose Representationmentioning

confidence: 99%

“…Mathematical representation SRNN [36] 2016 AGED [28] 2018 QuaterNet [79] 2018 LTD [67] 2019 HMR [60] 2019 MGCN [110] 2020 HRI [66] 2020 ARNet [12] 2020 LDR [17] 2021 LPJP [11] 2021 TrajectoryCNN [53] 2021 JDM [91] 2021 MMA [68] 2021 MPTC [57] 2021 SGAN [62] 2021 MT-GCN [15] 2021 MPTC [57] 2021 MST-GNN [47] 2021 skeleton as a graph, which makes GCN widely utilized in human pose representation. Additionally, widespread recognition of the Temporal Convolution Networks (TCNs), made the CN-based methods more widely accepted for solving the sequential problem.…”

Section: Physical Representationmentioning

confidence: 99%

“…GAN-based methods HP-GAN [7] 2018 AGED [28] 2018 BiHMP-GAN [40] 2019 STMI-GAN [86] 2019 GAN-poser [37] 2020 ARNet [12] 2020 AM-GAN [56] 2021 TC-GAN [16] 2021 SGAN [62] 2021…”

Section: Prediction Targetmentioning

confidence: 99%

“…The strength of trajectory representation lies in its smooth representation of the object's motion. Discrete Cosine Transform (DCT) [2] is widely used in many methods [67,66,68,12,11] for encoding trajectory. By discarding the high frequencies, it can generate a more compact representation, which can transform the 3D human joints coordinates into smoother motion state, predestining its popularity.…”

Section: Motion Trajectorymentioning

confidence: 99%

See 4 more Smart Citations

3D Human Motion Prediction: A Survey

Lyu¹,

Chen²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

3D human motion prediction, predicting future poses from a given sequence, is an issue of great significance and challenge in computer vision and machine intelligence, which can help machines in understanding human behaviors. Due to the increasing development and understanding of Deep Neural Networks (DNNs) and the availability of large-scale human motion datasets, the human motion prediction has been remarkably advanced with a surge of interest among academia and industrial community. In this context, a comprehensive survey on 3D human motion prediction is conducted for the purpose of retrospecting and analyzing relevant works from existing released literature. In addition, a pertinent taxonomy is constructed to categorize these existing approaches for 3D human motion prediction. In this survey, relevant methods are categorized into three categories: human pose representation, network structure design, and prediction target. We systematically review all relevant journal and conference papers in the field of human motion prediction since 2015, which are presented in detail based on proposed categorizations in this survey. Furthermore, the outline for the public benchmark datasets, evaluation criteria, and performance comparisons are respectively presented in this paper. The limitations of the state-of-the-art methods are discussed as well, hoping for paving the way for future explorations.

show abstract

Section: Gan-based Methodsmentioning

confidence: 99%

Section: Human Pose Representationmentioning

confidence: 99%

Section: Physical Representationmentioning

confidence: 99%

“…GAN-based methods HP-GAN [7] 2018 AGED [28] 2018 BiHMP-GAN [40] 2019 STMI-GAN [86] 2019 GAN-poser [37] 2020 ARNet [12] 2020 AM-GAN [56] 2021 TC-GAN [16] 2021 SGAN [62] 2021…”

Section: Prediction Targetmentioning

confidence: 99%