# Multitask Non-Autoregressive Model for Human Motion Prediction

arXiv: https://arxiv.org/abs/2007.06426 · HTML: https://mlsanity.com/paper/2007.06426/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 16 of 16)

- [Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction](https://mlsanity.com/paper/2203.16051/) (2022)
- [Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers](https://mlsanity.com/paper/2109.07531/) (2021)
- [Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space](https://mlsanity.com/paper/2207.07351/) (2022)
- [3D Human Motion Prediction: A Survey](https://mlsanity.com/paper/2203.01593/) (2022)
- [Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion](https://mlsanity.com/paper/2404.11375/) (2024)
- [Multimodal Sense-Informed Prediction of 3D Human Motions](https://mlsanity.com/paper/2405.02911/) (2024)
- [Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction](https://mlsanity.com/paper/2405.18700/) (2024)
- [FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations](https://mlsanity.com/paper/2211.14309/) (2022)
- [Mask prior-guided denoising diffusion improves inverse protein folding](https://mlsanity.com/paper/2412.07815/) (2024)
- [Non-Autoregressive Sign Language Production via Knowledge Distillation](https://mlsanity.com/paper/2208.06183/) (2022)
- [SPOTR: Spatio-temporal Pose Transformers for Human Motion Prediction](https://mlsanity.com/paper/2303.06277/) (2023)
- [Meta-Auxiliary Learning for Adaptive Human Pose Prediction](https://mlsanity.com/paper/2304.06411/) (2023)
- [Physics-constrained Attack against Convolution-based Human Motion Prediction](https://mlsanity.com/paper/2306.11990/) (2023)
- [Recent Advances in Deterministic Human Motion Prediction: A Review](https://mlsanity.com/paper/2312.06184/) (2023)
- [Empowering Sign Language Communication: Integrating Sentiment and Semantics for Facial Expression Synthesis](https://mlsanity.com/paper/2408.15159/) (2024)
- [Adaptive Interaction Network for Human Motion Prediction During Human-Robot Collaboration](https://mlsanity.com/paper/2610.16624/) (2026)

## Abstract (arXiv)

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.