# Recurrent Human Pose Estimation

arXiv: https://arxiv.org/abs/1605.02914 · HTML: https://mlsanity.com/paper/1605.02914/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2016.

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

- [TokenPose: Learning Keypoint Tokens for Human Pose Estimation](https://mlsanity.com/paper/2104.03516/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media](https://mlsanity.com/paper/2110.07235/) (2021)
- [Unsupervised Human Pose Estimation through Transforming Shape Templates](https://mlsanity.com/paper/2105.04154/) (2021)
- [HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap](https://mlsanity.com/paper/2104.03100/) (2021)
- [A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision](https://mlsanity.com/paper/2307.03353/) (2023)
- [An Adversarial Human Pose Estimation Network Injected with Graph Structure](https://mlsanity.com/paper/2103.15534/) (2021)
- [Relation-Based Associative Joint Location for Human Pose Estimation in Videos](https://mlsanity.com/paper/2107.03591/) (2021)
- [OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation](https://mlsanity.com/paper/2103.10180/) (2021)
- [Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons](https://mlsanity.com/paper/2208.11975/) (2022)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Multi-Keypoint Affordance Representation for Functional Dexterous Grasping](https://mlsanity.com/paper/2502.20018/) (2025)
- [Benchmarking Shadow Removal for Facial Landmark Detection and Beyond](https://mlsanity.com/paper/2111.13790/) (2021)
- [BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations](https://mlsanity.com/paper/2112.10716/) (2021)
- [2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints](https://mlsanity.com/paper/2212.02163/) (2022)
- [Data Augmentation in Human-Centric Vision](https://mlsanity.com/paper/2403.08650/) (2024)
- [MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding](https://mlsanity.com/paper/2507.12463/) (2025)
- [GoalieNet: A Multi-Stage Network for Joint Goalie, Equipment, and Net Pose Estimation in Ice Hockey](https://mlsanity.com/paper/2306.15853/) (2023)
- [A Dataset and Method for Hallux Valgus Angle Estimation Based on Deep Learing](https://mlsanity.com/paper/2107.03640/) (2021)
- [Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation](https://mlsanity.com/paper/2110.10734/) (2021)
- [Combining Visual Saliency Methods and Sparse Keypoint Annotations to Providently Detect Vehicles at Night](https://mlsanity.com/paper/2204.11535/) (2022)
- [FlexPose: Pose Distribution Adaptation with Limited Guidance](https://mlsanity.com/paper/2412.13463/) (2024)
- [A Real-Time Gesture-Based Control Framework](https://mlsanity.com/paper/2504.19460/) (2025)
- [Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capture](https://mlsanity.com/paper/2604.00857/) (2026)
- [NEEDL-Bench: Dataset for Swiss Needle Cast and Stomata Detection in Microscopy Images](https://mlsanity.com/paper/2607.12076/) (2026)
- [Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration](https://mlsanity.com/paper/2608.02285/) (2026)

## Abstract (arXiv)

We propose a novel ConvNet model for predicting 2D human body poses in an image. The model regresses a heatmap representation for each body keypoint, and is able to learn and represent both the part appearances and the context of the part configuration. We make the following three contributions: (i) an architecture combining a feed forward module with a recurrent module, where the recurrent module can be run iteratively to improve the performance, (ii) the model can be trained end-to-end and from scratch, with auxiliary losses incorporated to improve performance, (iii) we investigate whether keypoint visibility can also be predicted. The model is evaluated on two benchmark datasets. The result is a simple architecture that achieves performance on par with the state of the art, but without the complexity of a graphical model stage (or layers).