# Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision

arXiv: https://arxiv.org/abs/1911.01138 · HTML: https://mlsanity.com/paper/1911.01138/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2019.

## Built on by (most cited first, 27 of 27)

- [Synthesis of Compositional Animations from Textual Descriptions](https://mlsanity.com/paper/2103.14675/) (2021)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild](https://mlsanity.com/paper/2104.04029/) (2021)
- [A generic diffusion-based approach for 3D human pose prediction in the wild](https://mlsanity.com/paper/2210.05669/) (2022)
- [StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation](https://mlsanity.com/paper/2304.03959/) (2023)
- [Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction](https://mlsanity.com/paper/2108.00238/) (2021)
- [Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion](https://mlsanity.com/paper/2111.00993/) (2021)
- [Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions](https://mlsanity.com/paper/2503.03262/) (2025)
- [Toward Reliable Human Pose Forecasting with Uncertainty](https://mlsanity.com/paper/2304.06707/) (2023)
- [Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment](https://mlsanity.com/paper/2503.17267/) (2025)
- [Under the Hood of Transformer Networks for Trajectory Forecasting](https://mlsanity.com/paper/2203.11878/) (2022)
- [Panoptic Segmentation Forecasting](https://mlsanity.com/paper/2104.03962/) (2021)
- [Indoor Future Person Localization from an Egocentric Wearable Camera](https://mlsanity.com/paper/2103.04019/) (2021)
- [ManiCast: Collaborative Manipulation with Cost-Aware Human Forecasting](https://mlsanity.com/paper/2310.13258/) (2023)
- [Dual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling](https://mlsanity.com/paper/2310.07623/) (2023)
- [Joint Forecasting of Panoptic Segmentations with Difference Attention](https://mlsanity.com/paper/2204.07157/) (2022)
- [Evaluating Human Trajectory Prediction with Metamorphic Testing](https://mlsanity.com/paper/2407.18756/) (2024)
- [Towards Explainable, Privacy-Preserved Human-Motion Affect Recognition](https://mlsanity.com/paper/2105.03958/) (2021)
- ["If you could see me through my eyes": Predicting Pedestrian Perception](https://mlsanity.com/paper/2202.13981/) (2022)
- [Adversarial Attention for Human Motion Synthesis](https://mlsanity.com/paper/2204.11751/) (2022)
- [SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving](https://mlsanity.com/paper/2306.03538/) (2023)
- [Visual Forecasting as a Mid-level Representation for Avoidance](https://mlsanity.com/paper/2310.07724/) (2023)
- [UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction](https://mlsanity.com/paper/2505.14866/) (2025)
- [GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction](https://mlsanity.com/paper/2103.14113/) (2021)
- [Trajectory Prediction using Generative Adversarial Network in Multi-Class Scenarios](https://mlsanity.com/paper/2110.11401/) (2021)
- [3D Pose Nowcasting: Forecast the Future to Improve the Present](https://mlsanity.com/paper/2308.12914/) (2023)
- [Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle](https://mlsanity.com/paper/2309.06313/) (2023)

## Abstract (arXiv)

We tackle the problem of Human Locomotion Forecasting, a task for jointly predicting the spatial positions of several keypoints on the human body in the near future under an egocentric setting. In contrast to the previous work that aims to solve either the task of pose prediction or trajectory forecasting in isolation, we propose a framework to unify the two problems and address the practically useful task of pedestrian locomotion prediction in the wild. Among the major challenges in solving this task is the scarcity of annotated egocentric video datasets with dense annotations for pose, depth, or egomotion. To surmount this difficulty, we use state-of-the-art models to generate (noisy) annotations and propose robust forecasting models that can learn from this noisy supervision. We present a method to disentangle the overall pedestrian motion into easier to learn subparts by utilizing a pose completion and a decomposition module. The completion module fills in the missing key-point annotations and the decomposition module breaks the cleaned locomotion down to global (trajectory) and local (pose keypoint movements). Further, with Quasi RNN as our backbone, we propose a novel hierarchical trajectory forecasting network that utilizes low-level vision domain specific signals like egomotion and depth to predict the global trajectory. Our method leads to state-of-the-art results for the prediction of human locomotion in the egocentric view. Project pade: https://karttikeya.github.io/publication/plf/