mlsanityData to 7 Oct 2026

Learning Multiscale Correlations for Human Motion Prediction

arXiv 2103.10674 ↗First posted 19 Mar 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

In spite of the great progress in human motion prediction, it is still a challenging task to predict those aperiodic and complicated motions. We believe that to capture the correlations among human body components is the key to understand the human motion. In this paper, we propose a novel multiscale graph convolution network (MGCN) to address this problem. Firstly, we design an adaptive multiscale interactional encoding module (MIEM) which is composed of two sub modules: scale transformation module and scale interaction module to learn the human body correlations. Secondly, we apply a coarse-to-fine decoding strategy to decode the motions sequentially. We evaluate our approach on two standard benchmark datasets for human motion prediction: Human3.6M and CMU motion capture dataset. The experiments show that the proposed approach achieves the state-of-the-art performance for both short-term and long-term prediction especially in those complicated action category.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 19 of its 33 references that are in the map. First posted on arXiv 19 Mar 2021.

Builds on

19 of 33 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Pyramid Scene Parsing Networkcited by 2,472
  3. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  4. 2017On human motion prediction using recurrent neural networkscited by 336
  5. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  6. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
  7. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
  8. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  9. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 164
  10. 2019Scale-Aware Trident Networks for Object Detectioncited by 159
  11. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
  12. 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
7 more
  1. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 108
  2. 2017Deep representation learning for human motion prediction and classificationcited by 97
  3. 2019Imitation Learning for Human Pose Predictioncited by 44
  4. 2018Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamiccited by 41
  5. 2020Motion Prediction Using Temporal Inception Modulecited by 10
  6. 2020Complex Sequential Understanding through the Awareness of Spatial and Temporal Conceptscited by 8
  7. 2019Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Networkcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 1; 2025: 2.

9 papers.

  1. 20223D Human Motion Prediction: A Surveycited by 30
  2. 2023Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Predictioncited by 10
  3. 2024Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecastingcited by 5
  4. 2025HVIS: A Human-like Vision and Inference System for Human Motion Predictioncited by 3
  5. 2023Remembering What Is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Predictioncited by 2
  6. 2023Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Predictioncited by 1
  7. 2023Learning Snippet-to-Motion Progression for Skeleton-based Human Motion Predictioncited by 1
  8. 2025Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forwardcited by 1
  9. 2023Personalized Pose Forecastingcited by 0