# Forecasting Characteristic 3D Poses of Human Actions

arXiv: https://arxiv.org/abs/2011.15079 · HTML: https://mlsanity.com/paper/2011.15079/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 16 of 16)

- [CG-HOI: Contact-Guided 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2311.16097/) (2023)
- [IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions](https://mlsanity.com/paper/2212.07555/) (2022)
- [Large Motion Model for Unified Multi-Modal Motion Generation](https://mlsanity.com/paper/2404.01284/) (2024)
- [Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting](https://mlsanity.com/paper/2307.08243/) (2023)
- [Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios](https://mlsanity.com/paper/2203.03245/) (2022)
- [Multimodal Sense-Informed Prediction of 3D Human Motions](https://mlsanity.com/paper/2405.02911/) (2024)
- [FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations](https://mlsanity.com/paper/2211.14309/) (2022)
- [Expressive Forecasting of 3D Whole-body Human Motions](https://mlsanity.com/paper/2312.11972/) (2023)
- [CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation](https://mlsanity.com/paper/2407.06188/) (2024)
- [The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Prediction](https://mlsanity.com/paper/2306.13566/) (2023)
- [SPiKE: 3D Human Pose from Point Cloud Sequences](https://mlsanity.com/paper/2409.01879/) (2024)
- [Multi-Graph Convolution Network for Pose Forecasting](https://mlsanity.com/paper/2304.04956/) (2023)
- [EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning](https://mlsanity.com/paper/2503.00382/) (2025)
- [3D Pose Nowcasting: Forecast the Future to Improve the Present](https://mlsanity.com/paper/2308.12914/) (2023)
- [Personalized Pose Forecasting](https://mlsanity.com/paper/2312.03528/) (2023)
- [Towards a large-scale fused and labeled dataset of human pose while interacting with robots in shared urban areas](https://mlsanity.com/paper/2402.10077/) (2024)

## Abstract (arXiv)

We propose the task of forecasting characteristic 3d poses: from a short sequence observation of a person, predict a future 3d pose of that person in a likely action-defining, characteristic pose -- for instance, from observing a person picking up an apple, predict the pose of the person eating the apple. Prior work on human motion prediction estimates future poses at fixed time intervals. Although easy to define, this frame-by-frame formulation confounds temporal and intentional aspects of human action. Instead, we define a semantically meaningful pose prediction task that decouples the predicted pose from time, taking inspiration from goal-directed behavior. To predict characteristic poses, we propose a probabilistic approach that models the possible multi-modality in the distribution of likely characteristic poses. We then sample future pose hypotheses from the predicted distribution in an autoregressive fashion to model dependencies between joints. To evaluate our method, we construct a dataset of manually annotated characteristic 3d poses. Our experiments with this dataset suggest that our proposed probabilistic approach outperforms state-of-the-art methods by 26% on average.