# A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion

arXiv: https://arxiv.org/abs/2207.07381 · HTML: https://mlsanity.com/paper/2207.07381/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 15 Jul 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [Panoptic Studio: A Massively Multiview System for Social Interaction Capture](https://mlsanity.com/paper/1612.03153/) (2016)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach](https://mlsanity.com/paper/2007.09389/) (2020)
- [Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.14304/) (2021)
- [Convolutional Autoencoders for Human Motion Infilling](https://mlsanity.com/paper/2010.11531/) (2020)
- [Single-Shot Motion Completion with Transformer](https://mlsanity.com/paper/2103.00776/) (2021)
- [Recurrent Transition Networks for Character Locomotion](https://mlsanity.com/paper/1810.02363/) (2018)
- [4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras](https://mlsanity.com/paper/2002.12625/) (2020)
- [Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo](https://mlsanity.com/paper/2104.02273/) (2021)
- [Context Modeling in 3D Human Pose Estimation: A Unified Perspective](https://mlsanity.com/paper/2103.15507/) (2021)
- [Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS](https://mlsanity.com/paper/2003.03972/) (2020)
- [Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking](https://mlsanity.com/paper/2106.11589/) (2021)

## Built on by (most cited first, 7 of 7)

- [Deep Compositional Phase Diffusion for Long Motion Sequence Generation](https://mlsanity.com/paper/2510.14427/) (2025)
- [A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis](https://mlsanity.com/paper/2308.07301/) (2023)
- [Aerial Image Object Detection With Vision Transformer Detector (ViTDet)](https://mlsanity.com/paper/2301.12058/) (2023)
- [Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework](https://mlsanity.com/paper/2401.09836/) (2024)
- [Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloud](https://mlsanity.com/paper/2502.02936/) (2025)
- [Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregation](https://mlsanity.com/paper/2603.07697/) (2026)
- [Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learning](https://mlsanity.com/paper/2404.05578/) (2024)

## Abstract (arXiv)

Multi-person motion capture can be challenging due to ambiguities caused by severe occlusion, fast body movement, and complex interactions. Existing frameworks build on 2D pose estimations and triangulate to 3D coordinates via reasoning the appearance, trajectory, and geometric consistencies among multi-camera observations. However, 2D joint detection is usually incomplete and with wrong identity assignments due to limited observation angle, which leads to noisy 3D triangulation results. To overcome this issue, we propose to explore the short-range autoregressive characteristics of skeletal motion using transformer. First, we propose an adaptive, identity-aware triangulation module to reconstruct 3D joints and identify the missing joints for each identity. To generate complete 3D skeletal motion, we then propose a Dual-Masked Auto-Encoder (D-MAE) which encodes the joint status with both skeletal-structural and temporal position encoding for trajectory completion. D-MAE's flexible masking and encoding mechanism enable arbitrary skeleton definitions to be conveniently deployed under the same framework. In order to demonstrate the proposed model's capability in dealing with severe data loss scenarios, we contribute a high-accuracy and challenging motion capture dataset of multi-person interactions with severe occlusion. Evaluations on both benchmark and our new dataset demonstrate the efficiency of our proposed model, as well as its advantage against the other state-of-the-art methods.