Velocity-to-velocity human motion forecasting

作者：

Highlights：

• We introduce a novel velocity-to-velocity learning paradigm for human motion prediction, and propose different architectures to implement this paradigm.

• We design an end-to-end trainable RMT layer which transforms joint angles from the exponential map to the 3D rotation matrix.

• We define a novel robust loss function in the space of 3D rotation matrices.

• We present a robust training algorithm which exploits several sequence transformation techniques such as Gaussian smoothing.

摘要

•We introduce a novel velocity-to-velocity learning paradigm for human motion prediction, and propose different architectures to implement this paradigm.•We design an end-to-end trainable RMT layer which transforms joint angles from the exponential map to the 3D rotation matrix.•We define a novel robust loss function in the space of 3D rotation matrices.•We present a robust training algorithm which exploits several sequence transformation techniques such as Gaussian smoothing.

论文关键词：Human motion prediction,Action anticipation

论文评审过程：Received 22 December 2020, Revised 2 November 2021, Accepted 6 November 2021, Available online 9 November 2021, Version of Record 28 February 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108424