GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction | ✓ Link | 30.5 | 64.7 | | | | | | | | | | | GCNext | 2023-12-19 |
Multi-Graph Convolution Network for Pose Forecasting | | 34.4 | 72.9 | | | | | | | | | | | MGCN | 2023-04-11 |
Remembering What Is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Prediction | | 34.8 | | | | | | | | | | | | FMS-AM | 2023-05-19 |
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction | ✓ Link | 54.1 | 107 | | | | | | | | | | | AuxFormer | 2023-08-17 |
EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning | ✓ Link | 55.0 | 106.9 | | | | | | | | | | | EqMotion | 2023-03-20 |
Towards Accurate Human Motion Prediction via Iterative Refinement | | 55.5 | 109.2 | | | | | | | | | | | Sun et al. | 2023-05-08 |
Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction | ✓ Link | 56.41 | 81.95 | | | | | | | | | | | ResChunk | 2023-08-31 |
Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction | | 56.7 | 108.6 | | | | | | | | | | | GraphMixer | 2023-04-07 |
Back to MLP: A Simple Baseline for Human Motion Prediction | ✓ Link | 57.3 | 109.4 | | | | | | | | | | | siMLPe | 2022-07-04 |
Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction | ✓ Link | 58.5 | 110.3 | 0.54 | 0.69 | | | | | | | | | PGBIG | 2022-03-30 |
MotionMixer: MLP-based 3D Human Body Pose Forecasting | ✓ Link | 59.3 | 111.0 | 0.58 | 0.73 | | | | | | | | | MotionMixer | 2022-07-01 |
A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis | | 61.6 | 112.1 | | | | | | | | | | | UNIMASK-M | 2023-08-14 |
MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction | ✓ Link | 62.9 | 114.2 | | | | | | | | | | | MSR-GCN | 2021-08-16 |
Learning Trajectory Dependencies for Human Motion Prediction | ✓ Link | 63.5 | 113.0 | 0.56 | 0.67 | | | | | | | | | LTD-GCN | 2019-08-15 |
Space-Time-Separable Graph Convolutional Network for Pose Forecasting | ✓ Link | 65.8 | 117.0 | 0.55 | 0.87 | | | | | | | | | STS-GCN | 2021-10-09 |
AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations | | 80.6 | 128.2 | | | | | | | | | | | AnyPose1 | 2023-09-09 |
Intention-based Long-Term Human Motion Anticipation | ✓ Link | 80.8 | 149.2 | 0.91 | | 3070 | | | | | | | 0.465 | Forecast LSTM | 2021-12-01 |
Imitation Learning for Human Pose Prediction | | | | 0.59 | 0.69 | | | | | | | | | BC+WGAIL-div | 2019-09-08 |
Action-Agnostic Human Pose Forecasting | ✓ Link | | | 0.65 | 0.77 | | | | | | | | | TP-RNN | 2018-10-23 |
Structural-RNN: Deep Learning on Spatio-Temporal Graphs | ✓ Link | | | 1.30 | 2.13 | | | | | | | | | SRNN | 2015-11-17 |
Recurrent Network Models for Human Dynamics | | | | 1.78 | 2.38 | | | | | | | | | ERD | 2015-08-02 |
A generic diffusion-based approach for 3D human pose prediction in the wild | ✓ Link | | | | | 19466 | 356 | 396 | 463 | 445 | | | | TCD | 2022-10-11 |
Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors | ✓ Link | | | | | 15884 | 358 | 445 | 442 | 471 | | | | STARS | 2023-02-09 |
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space | ✓ Link | | | | | 15310 | 370 | 485 | 475 | 516 | 11.692 | 2.083 | | DiverseSampling | 2022-07-15 |
Generating Smooth Pose Sequences for Diverse Human Motion Prediction | ✓ Link | | | | | 14757 | 389 | 496 | 476 | 525 | 10.758 | 2.103 | | GSPS | 2021-08-19 |
Diverse Trajectory Forecasting with Determinantal Point Processes | | | | | | 9330 | 493 | 592 | 550 | 599 | | | | DSF | 2019-07-11 |
BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction | ✓ Link | | | | | 7602 | 372 | 474 | 473 | 507 | 5.988 | 0.209 | | BeLFusion | 2022-11-25 |
HP-GAN: Probabilistic 3D human motion prediction via GAN | ✓ Link | | | | | 7214 | 858 | 867 | 847 | 858 | | | | HP-GAN | 2017-11-27 |
Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders | ✓ Link | | | | | 6769 | 461 | 555 | 524 | 566 | | | | GMVAE | 2016-11-08 |
The Pose Knows: Video Forecasting by Generating Pose Futures | ✓ Link | | | | | 6723 | 461 | 560 | 522 | 569 | 6.326 | 0.538 | | Pose-Knows | 2017-04-28 |
Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective | ✓ Link | | | | | 6265 | 448 | 533 | 514 | 544 | | | | BoM | 2018-06-20 |
TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Prediction | ✓ Link | | | | | 5975 | 358 | 468 | 506 | 539 | | | | TransFusion | 2023-07-30 |
MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics | ✓ Link | | | | | 403 | 457 | 595 | 716 | 883 | | | | MT-VAE | 2018-08-14 |