# Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformer

arXiv: https://arxiv.org/abs/2303.09681 · HTML: https://mlsanity.com/paper/2303.09681/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 68 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Asynchronous, Photometric Feature Tracking using Events and Frames](https://mlsanity.com/paper/1807.09713/) (2018)
- [Event-Based Fusion for Motion Deblurring with Cross-modal Attention](https://mlsanity.com/paper/2112.00167/) (2021)
- [Attention Spiking Neural Networks](https://mlsanity.com/paper/2209.13929/) (2022)
- [Temporal-wise Attention Spiking Neural Networks for Event Streams Classification](https://mlsanity.com/paper/2107.11711/) (2021)
- [Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks](https://mlsanity.com/paper/2106.01862/) (2021)
- [Object Tracking by Jointly Exploiting Frame and Event Domain](https://mlsanity.com/paper/2109.09052/) (2021)
- [ESS: Learning Event-based Semantic Segmentation from Still Images](https://mlsanity.com/paper/2203.10016/) (2022)
- [EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera](https://mlsanity.com/paper/1908.11505/) (2019)
- [GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2210.13768/) (2022)
- [Adversarial Spatio-Temporal Learning for Video Deblurring](https://mlsanity.com/paper/1804.00533/) (2018)
- [Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video](https://mlsanity.com/paper/2203.08534/) (2022)
- [Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/1511.09439/) (2015)
- [Event-based, 6-DOF Camera Tracking from Photometric Depth Maps](https://mlsanity.com/paper/1607.03468/) (2016)

## Built on by (most cited first, 10 of 10)

- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Direct Learning-Based Deep Spiking Neural Networks: A Review](https://mlsanity.com/paper/2305.19725/) (2023)
- [Spiking-PhysFormer: Camera-Based Remote Photoplethysmography with Parallel Spike-driven Transformer](https://mlsanity.com/paper/2402.04798/) (2024)
- [Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks](https://mlsanity.com/paper/2401.04486/) (2024)
- [Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions](https://mlsanity.com/paper/2409.02111/) (2024)
- [ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognition](https://mlsanity.com/paper/2409.01564/) (2024)
- [Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation](https://mlsanity.com/paper/2512.06306/) (2025)
- [SDformerFlow: Spatiotemporal swin spikeformer for event-based optical flow estimation](https://mlsanity.com/paper/2409.04082/) (2024)
- [Continuous-Time Human Motion Field from Events](https://mlsanity.com/paper/2412.01747/) (2024)
- [Toward Efficient Spiking Transformers: Synapse Pruning Meets Synergistic Learning-Based Compensation](https://mlsanity.com/paper/2508.01992/) (2025)

## Abstract (arXiv)

Event camera, as an asynchronous vision sensor capturing scene dynamics, presents new opportunities for highly efficient 3D human pose tracking. Existing approaches typically adopt modern-day Artificial Neural Networks (ANNs), such as CNNs or Transformer, where sparse events are converted into dense images or paired with additional gray-scale images as input. Such practices, however, ignore the inherent sparsity of events, resulting in redundant computations, increased energy consumption, and potentially degraded performance. Motivated by these observations, we introduce the first sparse Spiking Neural Networks (SNNs) framework for 3D human pose tracking based solely on events. Our approach eliminates the need to convert sparse data to dense formats or incorporate additional images, thereby fully exploiting the innate sparsity of input events. Central to our framework is a novel Spiking Spatiotemporal Transformer, which enables bi-directional spatiotemporal fusion of spike pose features and provides a guaranteed similarity measurement between binary spike features in spiking attention. Moreover, we have constructed a large-scale synthetic dataset, SynEventHPD, that features a broad and diverse set of 3D human motions, as well as much longer hours of event streams. Empirical experiments demonstrate the superiority of our approach over existing state-of-the-art (SOTA) ANN-based methods, requiring only 19.1% FLOPs and 3.6% energy cost. Furthermore, our approach outperforms existing SNN-based benchmarks in this task, highlighting the effectiveness of our proposed SNN framework. The dataset will be released upon acceptance, and code can be found at https://github.com/JimmyZou/HumanPoseTracking_SNN.