# Convolutional Pose Machines

arXiv: https://arxiv.org/abs/1602.00134 · HTML: https://mlsanity.com/paper/1602.00134/

## Key facts

- Cited by 325 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2016.

## Built on by (most cited first, 30 of 325)

- [Style Aligned Image Generation via Shared Attention](https://mlsanity.com/paper/2312.02133/) (2023)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on](https://mlsanity.com/paper/2403.01779/) (2024)
- [PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark](https://mlsanity.com/paper/2203.11089/) (2022)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [SimPoE: Simulated Character Control for 3D Human Pose Estimation](https://mlsanity.com/paper/2104.00683/) (2021)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [TokenPose: Learning Keypoint Tokens for Human Pose Estimation](https://mlsanity.com/paper/2104.03516/) (2021)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [Pose Recognition with Cascade Transformers](https://mlsanity.com/paper/2104.06976/) (2021)
- [EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild](https://mlsanity.com/paper/2308.16894/) (2023)
- [InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction](https://mlsanity.com/paper/2209.12354/) (2022)
- [Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark](https://mlsanity.com/paper/2306.02898/) (2023)
- [MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image](https://mlsanity.com/paper/2112.02753/) (2021)
- [Neural Monocular 3D Human Motion Capture with Physical Awareness](https://mlsanity.com/paper/2105.01057/) (2021)
- [LooseControl: Lifting ControlNet for Generalized Depth Conditioning](https://mlsanity.com/paper/2312.03079/) (2023)
- [HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation](https://mlsanity.com/paper/2407.17438/) (2024)
- [Do Different Tracking Tasks Require Different Appearance Models?](https://mlsanity.com/paper/2107.02156/) (2021)
- [Drivable Volumetric Avatars using Texel-Aligned Features](https://mlsanity.com/paper/2207.09774/) (2022)
- [Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features](https://mlsanity.com/paper/2104.04480/) (2021)
- [OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association](https://mlsanity.com/paper/2103.02440/) (2021)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/2103.14843/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction](https://mlsanity.com/paper/2306.05872/) (2023)
- [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021)
- [Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification](https://mlsanity.com/paper/2206.07389/) (2022)
- [Sign Language Translation from Instructional Videos](https://mlsanity.com/paper/2304.06371/) (2023)

## Abstract (arXiv)

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets.