# Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation

arXiv: https://arxiv.org/abs/1705.02407 · HTML: https://mlsanity.com/paper/1705.02407/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2017.

## Built on by (most cited first, 18 of 18)

- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Human Pose and Shape Estimation from Single Polarization Images](https://mlsanity.com/paper/2108.06834/) (2021)
- [Prior Knowledge-Guided Attention in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2209.03745/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [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)
- [Data Augmentation for Object Detection via Differentiable Neural Rendering](https://mlsanity.com/paper/2103.02852/) (2021)
- [Improving Multi-Person Pose Tracking with A Confidence Network](https://mlsanity.com/paper/2310.18920/) (2023)
- [HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features](https://mlsanity.com/paper/2411.03086/) (2024)
- [GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields](https://mlsanity.com/paper/2404.06246/) (2024)
- [HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation](https://mlsanity.com/paper/2106.04269/) (2021)
- [Location-free Human Pose Estimation](https://mlsanity.com/paper/2205.12619/) (2022)
- [On The Potential of The Fractal Geometry and The CNNs Ability to Encode it](https://mlsanity.com/paper/2401.04141/) (2024)
- [Performance of different machine learning methods on activity recognition and pose estimation datasets](https://mlsanity.com/paper/2210.10247/) (2022)
- [Accelerating Domain-aware Deep Learning Models with Distributed Training](https://mlsanity.com/paper/2301.11787/) (2023)
- [Revisiting the Efficacy of Signal Decomposition in AI-based Time Series Prediction](https://mlsanity.com/paper/2405.06986/) (2024)
- [Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.11448/) (2024)
- [Refinement Module based on Parse Graph for Human Pose Estimation](https://mlsanity.com/paper/2501.11069/) (2025)

## Abstract (arXiv)

Human pose estimation using deep neural networks aims to map input images with large variations into multiple body keypoints which must satisfy a set of geometric constraints and inter-dependency imposed by the human body model. This is a very challenging nonlinear manifold learning process in a very high dimensional feature space. We believe that the deep neural network, which is inherently an algebraic computation system, is not the most effecient way to capture highly sophisticated human knowledge, for example those highly coupled geometric characteristics and interdependence between keypoints in human poses. In this work, we propose to explore how external knowledge can be effectively represented and injected into the deep neural networks to guide its training process using learned projections that impose proper prior. Specifically, we use the stacked hourglass design and inception-resnet module to construct a fractal network to regress human pose images into heatmaps with no explicit graphical modeling. We encode external knowledge with visual features which are able to characterize the constraints of human body models and evaluate the fitness of intermediate network output. We then inject these external features into the neural network using a projection matrix learned using an auxiliary cost function. The effectiveness of the proposed inception-resnet module and the benefit in guided learning with knowledge projection is evaluated on two widely used benchmarks. Our approach achieves state-of-the-art performance on both datasets.