# Beyond Physical Connections: Tree Models in Human Pose Estimation

arXiv: https://arxiv.org/abs/1305.2269 · HTML: https://mlsanity.com/paper/1305.2269/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2013.

## Built on by (most cited first, 14 of 14)

- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2307.16687/) (2023)
- [Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2203.15227/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video](https://mlsanity.com/paper/2303.08475/) (2023)
- [Scene-aware Human Pose Generation using Transformer](https://mlsanity.com/paper/2308.02177/) (2023)
- [Joint-Motion Mutual Learning for Pose Estimation in Videos](https://mlsanity.com/paper/2408.02285/) (2024)
- [Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach](https://mlsanity.com/paper/2409.02715/) (2024)
- [Deep Learning for Human Parsing: A Survey](https://mlsanity.com/paper/2301.12416/) (2023)
- [DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors](https://mlsanity.com/paper/2512.21054/) (2025)
- [PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding](https://mlsanity.com/paper/2107.10466/) (2021)
- [Hand Gesture Classification on Praxis Dataset: Trading Accuracy for Expense](https://mlsanity.com/paper/2311.00767/) (2023)
- [4-Dimensional deformation part model for pose estimation using Kalman filter constraints](https://mlsanity.com/paper/2402.04953/) (2024)
- [An End-to-End Framework for Video Multi-Person Pose Estimation](https://mlsanity.com/paper/2509.01095/) (2025)

## Abstract (arXiv)

Simple tree models for articulated objects prevails in the last decade. However, it is also believed that these simple tree models are not capable of capturing large variations in many scenarios, such as human pose estimation. This paper attempts to address three questions: 1) are simple tree models sufficient? more specifically, 2) how to use tree models effectively in human pose estimation? and 3) how shall we use combined parts together with single parts efficiently? Assuming we have a set of single parts and combined parts, and the goal is to estimate a joint distribution of their locations. We surprisingly find that no latent variables are introduced in the Leeds Sport Dataset (LSP) during learning latent trees for deformable model, which aims at approximating the joint distributions of body part locations using minimal tree structure. This suggests one can straightforwardly use a mixed representation of single and combined parts to approximate their joint distribution in a simple tree model. As such, one only needs to build Visual Categories of the combined parts, and then perform inference on the learned latent tree. Our method outperformed the state of the art on the LSP, both in the scenarios when the training images are from the same dataset and from the PARSE dataset. Experiments on animal images from the VOC challenge further support our findings.