# Improving Pose Estimation through Contextual Activity Fusion

arXiv: https://arxiv.org/abs/2111.02500 · HTML: https://mlsanity.com/paper/2111.02500/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 3 Nov 2021.

## Builds on (most cited first, 12 of 12)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Compositional Human Pose Regression](https://mlsanity.com/paper/1704.00159/) (2017)
- [Learning Feature Pyramids for Human Pose Estimation](https://mlsanity.com/paper/1708.01101/) (2017)
- [Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation](https://mlsanity.com/paper/1705.00389/) (2017)
- [Adversarial Semantic Data Augmentation for Human Pose Estimation](https://mlsanity.com/paper/2008.00697/) (2020)
- [Quantized Densely Connected U-Nets for Efficient Landmark Localization](https://mlsanity.com/paper/1808.02194/) (2018)
- [Context-aware CNNs for person head detection](https://mlsanity.com/paper/1511.07917/) (2015)
- [Generative Model-Enhanced Human Motion Prediction](https://mlsanity.com/paper/2010.11699/) (2020)

## Abstract (arXiv)

This research presents the idea of activity fusion into existing Pose Estimation architectures to enhance their predictive ability. This is motivated by the rise in higher level concepts found in modern machine learning architectures, and the belief that activity context is a useful piece of information for the problem of pose estimation. To analyse this concept we take an existing deep learning architecture and augment it with an additional 1x1 convolution to fuse activity information into the model. We perform evaluation and comparison on a common pose estimation dataset, and show a performance improvement over our baseline model, especially in uncommon poses and on typically difficult joints. Additionally, we perform an ablative analysis to indicate that the performance improvement does in fact draw from the activity information.