# Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2103.14304 · HTML: https://mlsanity.com/paper/2103.14304/

## Key facts

- Cited by 94 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 66 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose](https://mlsanity.com/paper/1611.07828/) (2016)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing](https://mlsanity.com/paper/2006.03236/) (2020)
- [Lite Transformer with Long-Short Range Attention](https://mlsanity.com/paper/2004.11886/) (2020)
- [Ordinal Depth Supervision for 3D Human Pose Estimation](https://mlsanity.com/paper/1805.04095/) (2018)
- [Self-Supervised Learning of 3D Human Pose using Multi-view Geometry](https://mlsanity.com/paper/1903.02330/) (2019)
- [SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach](https://mlsanity.com/paper/2007.09389/) (2020)
- [Exploiting temporal information for 3D pose estimation](https://mlsanity.com/paper/1711.08585/) (2017)
- [ConvBERT: Improving BERT with Span-based Dynamic Convolution](https://mlsanity.com/paper/2008.02496/) (2020)
- [Motion Guided 3D Pose Estimation from Videos](https://mlsanity.com/paper/2004.13985/) (2020)
- [Trear: Transformer-based RGB-D Egocentric Action Recognition](https://mlsanity.com/paper/2101.03904/) (2021)
- [Memory Attention Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1804.08254/) (2018)
- [Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation](https://mlsanity.com/paper/1908.08289/) (2019)
- [A generalizable approach for multi-view 3D human pose regression](https://mlsanity.com/paper/1804.10462/) (2018)

## Built on by (most cited first, 30 of 94)

- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2303.17472/) (2023)
- [Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation](https://mlsanity.com/paper/2303.11579/) (2023)
- [P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.07628/) (2022)
- [MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network](https://mlsanity.com/paper/2310.16288/) (2023)
- [GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/2307.05853/) (2023)
- [ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design](https://mlsanity.com/paper/2210.09573/) (2022)
- [Tracking Objects as Pixel-wise Distributions](https://mlsanity.com/paper/2207.05518/) (2022)
- [KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2404.00658/) (2024)
- [Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers](https://mlsanity.com/paper/2210.06110/) (2022)
- [DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model](https://mlsanity.com/paper/2212.02796/) (2022)
- [Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video](https://mlsanity.com/paper/2308.10305/) (2023)
- [HDFormer: High-order Directed Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2302.01825/) (2023)
- [3D Human Pose Perception from Egocentric Stereo Videos](https://mlsanity.com/paper/2401.00889/) (2023)
- [GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation](https://mlsanity.com/paper/2206.06420/) (2022)
- [3D Vision with Transformers: A Survey](https://mlsanity.com/paper/2208.04309/) (2022)
- [Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.05092/) (2021)
- [Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition](https://mlsanity.com/paper/2207.03065/) (2022)
- [Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior](https://mlsanity.com/paper/2207.05375/) (2022)
- [Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation](https://mlsanity.com/paper/2311.12028/) (2023)
- [AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements](https://mlsanity.com/paper/2503.07499/) (2025)
- [Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network](https://mlsanity.com/paper/2105.10882/) (2021)
- [Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration](https://mlsanity.com/paper/2304.04437/) (2023)
- [FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction](https://mlsanity.com/paper/2105.01937/) (2021)
- [CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.13387/) (2022)
- [Regular Splitting Graph Network for 3D Human Pose Estimation](https://mlsanity.com/paper/2305.05785/) (2023)
- [A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation](https://mlsanity.com/paper/2311.03312/) (2023)
- [FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER](https://mlsanity.com/paper/2205.15448/) (2022)
- [Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving](https://mlsanity.com/paper/2307.14889/) (2023)

## Abstract (arXiv)

Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative representations for generating one 3D pose. To this end, we propose an improved Transformer-based architecture, called Strided Transformer, which simply and effectively lifts a long sequence of 2D joint locations to a single 3D pose. Specifically, a Vanilla Transformer Encoder (VTE) is adopted to model long-range dependencies of 2D pose sequences. To reduce the redundancy of the sequence, fully-connected layers in the feed-forward network of VTE are replaced with strided convolutions to progressively shrink the sequence length and aggregate information from local contexts. The modified VTE is termed as Strided Transformer Encoder (STE), which is built upon the outputs of VTE. STE not only effectively aggregates long-range information to a single-vector representation in a hierarchical global and local fashion, but also significantly reduces the computation cost. Furthermore, a full-to-single supervision scheme is designed at both full sequence and single target frame scales applied to the outputs of VTE and STE, respectively. This scheme imposes extra temporal smoothness constraints in conjunction with the single target frame supervision and hence helps produce smoother and more accurate 3D poses. The proposed Strided Transformer is evaluated on two challenging benchmark datasets, Human3.6M and HumanEva-I, and achieves state-of-the-art results with fewer parameters. Code and models are available at urlhttps://github.com/Vegetebird/StridedTransformer-Pose3D.