Human Pose Forecasting

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

7 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 44 papers with code (58 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• On human motion prediction using recurrent neural networks
  6 May 2017 8 repositories listed Syntology ran 3 of 5 samples · 2 unverified · 3 pointer-only (licence)
  Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented…
• Learning Trajectory Dependencies for Human Motion Prediction
  15 Aug 2019 5 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  In this paper, we propose a simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints.
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
  8 Nov 2016 4 repositories listed
  We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models.
• HP-GAN: Probabilistic 3D human motion prediction via GAN
  27 Nov 2017 3 repositories listed
  Our model, which we call HP-GAN, learns a probability density function of future human poses conditioned on previous poses.
• EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning
  20 Mar 2023 2 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  In motion prediction tasks, maintaining motion equivariance under Euclidean geometric transformations and invariance of agent interaction is a critical and fundamental principle.
• Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space
  15 Jul 2022 2 repositories listed
  In this paper, we propose a novel sampling strategy for sampling very diverse results from an imbalanced multimodal distribution learned by a deep generative model.
• Structural-RNN: Deep Learning on Spatio-Temporal Graphs
  17 Nov 2015 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  The proposed method is generic and principled as it can be used for transforming any spatio-temporal graph through employing a certain set of well defined steps.
• MotionMap: Representing Multimodality in Human Pose Forecasting
  25 Dec 2024 1 repository listed
  This raises key questions: (1) Can we capture multimodality by efficiently sampling a smaller number of predictions?
• Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning
  8 Apr 2024 1 repository listed Syntology ran 23 of 32 samples · 9 unverified · 32 pointer-only (licence)
  Our model effectively handles the multi-modality of human motion and the complexity of long-term multi-agent interactions, improving performance in complex environments.
• Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting
  21 Feb 2024 1 repository listed
  Human motion prediction is still an open problem extremely important for autonomous driving and safety applications.
• Expressive Forecasting of 3D Whole-body Human Motions
  19 Dec 2023 1 repository listed
  Human motion forecasting, with the goal of estimating future human behavior over a period of time, is a fundamental task in many real-world applications.
• GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction
  19 Dec 2023 1 repository listed
  The past few years has witnessed the dominance of Graph Convolutional Networks (GCNs) over human motion prediction.
• Scene-aware Human Motion Forecasting via Mutual Distance Prediction
  1 Oct 2023 1 repository listed Syntology ran 6 of 7 samples · 1 unverified · 7 pointer-only (licence)
  In this paper, we tackle the problem of scene-aware 3D human motion forecasting.
• Staged Contact-Aware Global Human Motion Forecasting
  16 Sep 2023 1 repository listed Syntology ran 0 of 3 samples · 3 unverified · 3 pointer-only (licence)
  So far, only Mao et al.
• InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion
  31 Aug 2023 1 repository listed Syntology ran 6 of 6 samples · 0 unverified
  This paper addresses a novel task of anticipating 3D human-object interactions (HOIs).
• Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction
  31 Aug 2023 1 repository listed
  Our experiments on two challenging benchmark datasets, CMU Mocap and Human3.
• Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
  17 Aug 2023 1 repository listed Syntology ran 13 of 19 samples · 6 unverified · 19 pointer-only (licence)
  To work with auxiliary tasks, we propose a novel auxiliary-adapted transformer, which can handle incomplete, corrupted motion data and achieve coordinate recovery via capturing spatial-temporal dependencies.
• TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Prediction
  30 Jul 2023 1 repository listed
  Predicting human motion plays a crucial role in ensuring a safe and effective human-robot close collaboration in intelligent remanufacturing systems of the future.
• Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection
  14 Jul 2023 1 repository listed Syntology ran 6 of 8 samples · 2 unverified
  Leading OCC techniques constrain the latent representations of normal motions to limited volumes and detect as abnormal anything outside, which accounts satisfactorily for the openset'ness of anomalies.
• Toward Reliable Human Pose Forecasting with Uncertainty
  13 Apr 2023 1 repository listed Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)
  Recently, there has been an arms race of pose forecasting methods aimed at solving the spatio-temporal task of predicting a sequence of future 3D poses of a person given a sequence of past observed ones.
• Best Practices for 2-Body Pose Forecasting
  12 Apr 2023 1 repository listed Syntology ran 3 of 17 samples · 14 unverified
  The task of collaborative human pose forecasting stands for predicting the future poses of multiple interacting people, given those in previous frames.
• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
  9 Feb 2023 1 repository listed
  Predicting diverse human motions given a sequence of historical poses has received increasing attention.
• HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting
  1 Jan 2023 1 repository listed
  Considering the structural-property of the skeleton data in representing human poses and the possible irregularity caused by occlusion, we propose the use of dynamic graph convolution as the basic operator.
• BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction
  25 Nov 2022 1 repository listed
  To address these issues, we present BeLFusion, a model that, for the first time, leverages latent diffusion models in HMP to sample from a latent space where behavior is disentangled from pose and motion.
• A generic diffusion-based approach for 3D human pose prediction in the wild
  11 Oct 2022 1 repository listed
  Predicting 3D human poses in real-world scenarios, also known as human pose forecasting, is inevitably subject to noisy inputs arising from inaccurate 3D pose estimations and occlusions.
• Contact-aware Human Motion Forecasting
  8 Oct 2022 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  In this paper, we tackle the task of scene-aware 3D human motion forecasting, which consists of predicting future human poses given a 3D scene and a past human motion.
• SoMoFormer: Multi-Person Pose Forecasting with Transformers
  30 Aug 2022 1 repository listed
  Although there are several previous works targeting the problem of multi-person dynamic pose forecasting, they often model the entire pose sequence as time series (ignoring the underlying relationship between joints) or…
• Pose Forecasting in Industrial Human-Robot Collaboration
  24 Jul 2022 1 repository listed Syntology ran 7 of 9 samples · 2 unverified · 4 pointer-only (licence)
  Pushing back the frontiers of collaborative robots in industrial environments, we propose a new Separable-Sparse Graph Convolutional Network (SeS-GCN) for pose forecasting.
• Back to MLP: A Simple Baseline for Human Motion Prediction
  4 Jul 2022 1 repository listed Syntology ran 3 of 7 samples · 4 unverified
  This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences.
• MotionMixer: MLP-based 3D Human Body Pose Forecasting
  1 Jul 2022 1 repository listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  Given a stacked sequence of 3D body poses, a spatial-MLP extracts fine grained spatial dependencies of the body joints.

Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.