Multitask Non-Autoregressive Model for Human Motion Prediction

07/13/2020
by   Bin Li, et al.
0

Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem. Therefore, extensive efforts have been continued on exploring different RNN-based encoder-decoder architectures. However, by generating target poses conditioned on the previously generated ones, these models are prone to bringing issues such as error accumulation problem. In this paper, we argue that such issue is mainly caused by adopting autoregressive manner. Hence, a novel Non-auToregressive Model (NAT) is proposed with a complete non-autoregressive decoding scheme, as well as a context encoder and a positional encoding module. More specifically, the context encoder embeds the given poses from temporal and spatial perspectives. The frame decoder is responsible for predicting each future pose independently. The positional encoding module injects positional signal into the model to indicate temporal order. Moreover, a multitask training paradigm is presented for both low-level human skeleton prediction and high-level human action recognition, resulting in the convincing improvement for the prediction task. Our approach is evaluated on Human3.6M and CMU-Mocap benchmarks and outperforms state-of-the-art autoregressive methods.

READ FULL TEXT
research
06/15/2019

VRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction

Human motion prediction, which aims to predict future human poses given ...
research
09/15/2021

Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers

We propose to leverage Transformer architectures for non-autoregressive ...
research
03/17/2022

PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer

Nowadays, our mobility systems are evolving into the era of intelligent ...
research
11/26/2021

3D Pose Estimation and Future Motion Prediction from 2D Images

This paper considers to jointly tackle the highly correlated tasks of es...
research
05/02/2023

FlightBERT++: A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework

Flight Trajectory Prediction (FTP) is an essential task in Air Traffic C...
research
09/15/2022

STPOTR: Simultaneous Human Trajectory and Pose Prediction Using a Non-Autoregressive Transformer for Robot Following Ahead

In this paper, we develop a neural network model to predict future human...
research
06/25/2022

Self-supervision and Learnable STRFs for Age, Emotion, and Country Prediction

This work presents a multitask approach to the simultaneous estimation o...

Please sign up or login with your details

Forgot password? Click here to reset