Recent Advances in Deterministic Human Motion Prediction: A Review
Not on the map. Why?
Abstract (arXiv)
In recent years, with the continuous advancement of deep learning and the emergence of large-scale human motion datasets, human motion prediction technology has gradually gained prominence in various fields such as human-computer interaction, autonomous driving, sports analysis, and personnel tracking. This article introduces common model architectures in this domain along with their respective advantages and disadvantages. It also systematically summarizes recent research innovations, focusing on in-depth discussions of relevant papers in these areas, thereby highlighting forward-looking insights into the field's development. Furthermore, this paper provides a comprehensive overview of existing methods, commonly used datasets, and evaluation metrics in this field. Finally, it discusses some of the current limitations in the field and proposes potential future research directions to address these challenges and promote further advancements in human motion prediction.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 54 of its 94 references that are in the map. First posted on arXiv 11 Dec 2023.
Builds on
54 of 94 references.
References · 54
- 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
- 2020Simple and Deep Graph Convolutional Networkscited by 857
- 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
- 2021MetaFormer Is Actually What You Need for Visioncited by 523
- 2018Efficient Attention: Attention with Linear Complexitiescited by 366
- 2017On human motion prediction using recurrent neural networkscited by 336
- 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
- 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
- 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
- 2020Long-term Human Motion Prediction with Scene Contextcited by 191
- 2018Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNNcited by 142
- 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
38 more
- 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
- 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
- 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
- 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 99
- 2017Deep representation learning for human motion prediction and classificationcited by 97
- 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
- 2020Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognitioncited by 91
- 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
- 2022Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Predictioncited by 66
- 2018Action-Agnostic Human Pose Forecastingcited by 56
- 2019Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Predictioncited by 50
- 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
- 2019Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Predictioncited by 46
- 2021Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformerscited by 46
- 2019SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognitioncited by 42
- 2022MotionMixer: MLP-based 3D Human Body Pose Forecastingcited by 42
- 2018Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamiccited by 41
- 2021Multi-level Motion Attention for Human Motion Predictioncited by 35
- 20223D Human Motion Prediction: A Surveycited by 30
- 2022Skeleton-Parted Graph Scattering Networks for 3D Human Motion Predictioncited by 29
- 2019PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Predictioncited by 20
- 2021Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Networkcited by 20
- 2023Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Predictioncited by 20
- 2020Multitask Non-Autoregressive Model for Human Motion Predictioncited by 15
- 2023Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypointscited by 12
- 2023Toward Reliable Human Pose Forecasting with Uncertaintycited by 11
- 2020Motion Prediction Using Temporal Inception Modulecited by 10
- 2023Spatio-Temporal Branching for Motion Prediction using Motion Incrementscited by 9
- 2022Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Predictioncited by 7
- 2020Long Term Motion Prediction Using Keyposescited by 6
- 2023Robust Human Motion Forecasting using Transformer-based Modelcited by 6
- 2023DE-TGN: Uncertainty-Aware Human Motion Forecasting using Deep Ensemblescited by 6
- 2019TrajectoryNet: a new spatio-temporal feature learning network for human motion predictioncited by 5
- 2022Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Predictioncited by 4
- 2023Towards Accurate Human Motion Prediction via Iterative Refinementcited by 4
- 2023AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equationscited by 4
- 2023Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Predictioncited by 3
- 2021Temporal Consistency Two-Stream CNN for Human Motion Predictioncited by 2
50 most cited of 54 All 54 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.