# Toward Reliable Human Pose Forecasting with Uncertainty

arXiv: https://arxiv.org/abs/2304.06707 · HTML: https://mlsanity.com/paper/2304.06707/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 85 references that are in the map.
- First posted on arXiv 13 Apr 2023.

## Builds on (most cited first, 30 of 48)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [Learning Trajectory Dependencies for Human Motion Prediction](https://mlsanity.com/paper/1908.05436/) (2019)
- [Structural-RNN: Deep Learning on Spatio-Temporal Graphs](https://mlsanity.com/paper/1511.05298/) (2015)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [Stochastic Scene-Aware Motion Prediction](https://mlsanity.com/paper/2108.08284/) (2021)
- [Long-term Human Motion Prediction with Scene Context](https://mlsanity.com/paper/2007.03672/) (2020)
- [DLow: Diversifying Latent Flows for Diverse Human Motion Prediction](https://mlsanity.com/paper/2003.08386/) (2020)
- [Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning](https://mlsanity.com/paper/1809.08835/) (2018)
- [History Repeats Itself: Human Motion Prediction via Motion Attention](https://mlsanity.com/paper/2007.11755/) (2020)
- [Human Trajectory Forecasting in Crowds: A Deep Learning Perspective](https://mlsanity.com/paper/2007.03639/) (2020)
- [Convolutional Sequence to Sequence Model for Human Dynamics](https://mlsanity.com/paper/1805.00655/) (2018)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving](https://mlsanity.com/paper/1808.05819/) (2018)
- [An Uncertain Future: Forecasting from Static Images using Variational Autoencoders](https://mlsanity.com/paper/1606.07873/) (2016)
- [Context-aware Human Motion Prediction](https://mlsanity.com/paper/1904.03419/) (2019)
- [Space-Time-Separable Graph Convolutional Network for Pose Forecasting](https://mlsanity.com/paper/2110.04573/) (2021)
- [Quantifying Uncertainties in Natural Language Processing Tasks](https://mlsanity.com/paper/1811.07253/) (2018)
- [Learning Human Motion Models for Long-term Predictions](https://mlsanity.com/paper/1704.02827/) (2017)
- [Generating Smooth Pose Sequences for Diverse Human Motion Prediction](https://mlsanity.com/paper/2108.08422/) (2021)
- [Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction](https://mlsanity.com/paper/2203.16051/) (2022)
- [Action-Agnostic Human Pose Forecasting](https://mlsanity.com/paper/1810.09676/) (2018)

## Built on by (most cited first, 11 of 11)

- [UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction](https://mlsanity.com/paper/2403.15098/) (2024)
- [Social-Transmotion: Promptable Human Trajectory Prediction](https://mlsanity.com/paper/2312.16168/) (2023)
- [Multi-Transmotion: Pre-trained Model for Human Motion Prediction](https://mlsanity.com/paper/2411.02673/) (2024)
- [MotionMap: Representing Multimodality in Human Pose Forecasting](https://mlsanity.com/paper/2412.18883/) (2024)
- [Certified Human Trajectory Prediction](https://mlsanity.com/paper/2403.13778/) (2024)
- [Social-Pose: Enhancing Trajectory Prediction with Human Body Pose](https://mlsanity.com/paper/2507.22742/) (2025)
- [Heteroscedastic Diffusion for Multi-Agent Trajectory Modeling](https://mlsanity.com/paper/2605.10717/) (2026)
- [Recent Advances in Deterministic Human Motion Prediction: A Review](https://mlsanity.com/paper/2312.06184/) (2023)
- [HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenario](https://mlsanity.com/paper/2509.10096/) (2025)
- [Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees](https://mlsanity.com/paper/2604.15221/) (2026)
- [Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction](https://mlsanity.com/paper/2608.21093/) (2026)

## Abstract (arXiv)

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. However, the lack of unified benchmarks and limited uncertainty analysis have hindered progress in the field. To address this, we first develop an open-source library for human pose forecasting, including multiple models, supporting several datasets, and employing standardized evaluation metrics, with the aim of promoting research and moving toward a unified and consistent evaluation. Second, we devise two types of uncertainty in the problem to increase performance and convey better trust: 1) we propose a method for modeling aleatoric uncertainty by using uncertainty priors to inject knowledge about the pattern of uncertainty. This focuses the capacity of the model in the direction of more meaningful supervision while reducing the number of learned parameters and improving stability; 2) we introduce a novel approach for quantifying the epistemic uncertainty of any model through clustering and measuring the entropy of its assignments. Our experiments demonstrate up to 25% improvements in forecasting at short horizons, with no loss on longer horizons on Human3.6M, AMSS, and 3DPW datasets, and better performance in uncertainty estimation. The code is available online at https://github.com/vita-epfl/UnPOSed.