# Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network

arXiv: https://arxiv.org/abs/1406.3474 · HTML: https://mlsanity.com/paper/1406.3474/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2014.

## Built on by (most cited first, 11 of 11)

- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions](https://mlsanity.com/paper/2103.03170/) (2021)
- [Multi-task Learning by Leveraging the Semantic Information](https://mlsanity.com/paper/2103.02546/) (2021)
- [MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification](https://mlsanity.com/paper/2107.00808/) (2021)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs](https://mlsanity.com/paper/2101.12431/) (2021)
- [Ranking Micro-Influencers: a Novel Multi-Task Learning and Interpretable Framework](https://mlsanity.com/paper/2107.13943/) (2021)
- [PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent](https://mlsanity.com/paper/2202.00531/) (2022)
- [Robust-Multi-Task Gradient Boosting](https://mlsanity.com/paper/2507.11411/) (2025)
- [BTranspose: Bottleneck Transformers for Human Pose Estimation with Self-Supervised Pre-Training](https://mlsanity.com/paper/2204.10209/) (2022)
- [Tensorized Multi-Task Learning for Personalized Modeling of Heterogeneous Individuals with High-Dimensional Data](https://mlsanity.com/paper/2508.15676/) (2025)

## Abstract (arXiv)

We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network. In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part detector in a deep network architecture. We show that including the body-part detection task helps to regularize the network, directing it to converge to a good solution. We report competitive and state-of-art results on several data sets. We also empirically show that the learned neurons in the middle layer of our network are tuned to localized body parts.