# Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

arXiv: https://arxiv.org/abs/1407.3399 · HTML: https://mlsanity.com/paper/1407.3399/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2014.

## Built on by (most cited first, 24 of 24)

- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild](https://mlsanity.com/paper/2108.02452/) (2021)
- [Context Modeling in 3D Human Pose Estimation: A Unified Perspective](https://mlsanity.com/paper/2103.15507/) (2021)
- [Test-Time Personalization with a Transformer for Human Pose Estimation](https://mlsanity.com/paper/2107.02133/) (2021)
- [Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network](https://mlsanity.com/paper/2105.10882/) (2021)
- [Part-Based Models Improve Adversarial Robustness](https://mlsanity.com/paper/2209.09117/) (2022)
- [3D Pose Estimation and Future Motion Prediction from 2D Images](https://mlsanity.com/paper/2111.13285/) (2021)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery](https://mlsanity.com/paper/2205.15895/) (2022)
- [CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey](https://mlsanity.com/paper/2301.06187/) (2023)
- [Human Modelling and Pose Estimation Overview](https://mlsanity.com/paper/2406.19290/) (2024)
- [Bias-Compensated Integral Regression for Human Pose Estimation](https://mlsanity.com/paper/2301.10431/) (2023)
- [Pretrained equivariant features improve unsupervised landmark discovery](https://mlsanity.com/paper/2104.02925/) (2021)
- [Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach](https://mlsanity.com/paper/2409.02715/) (2024)
- [A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities](https://mlsanity.com/paper/2409.09678/) (2024)
- [Deep Dependency Networks for Multi-Label Classification](https://mlsanity.com/paper/2302.00633/) (2023)
- [Dataset and Benchmark for Urdu Natural Scenes Text Detection, Recognition and Visual Question Answering](https://mlsanity.com/paper/2405.12533/) (2024)
- [MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection](https://mlsanity.com/paper/2412.01422/) (2024)
- [FootFormer: Estimating Stability from Visual Input](https://mlsanity.com/paper/2510.19170/) (2025)
- [Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification](https://mlsanity.com/paper/2404.11667/) (2024)
- [Computer Vision and Its Relationship to Cognitive Science: A perspective from Bayes Decision Theory](https://mlsanity.com/paper/2602.00289/) (2026)

## Abstract (arXiv)

We present a method for estimating articulated human pose from a single static image based on a graphical model with novel pairwise relations that make adaptive use of local image measurements. More precisely, we specify a graphical model for human pose which exploits the fact the local image measurements can be used both to detect parts (or joints) and also to predict the spatial relationships between them (Image Dependent Pairwise Relations). These spatial relationships are represented by a mixture model. We use Deep Convolutional Neural Networks (DCNNs) to learn conditional probabilities for the presence of parts and their spatial relationships within image patches. Hence our model combines the representational flexibility of graphical models with the efficiency and statistical power of DCNNs. Our method significantly outperforms the state of the art methods on the LSP and FLIC datasets and also performs very well on the Buffy dataset without any training.