# Learning Human Pose Estimation Features with Convolutional Networks

arXiv: https://arxiv.org/abs/1312.7302 · HTML: https://mlsanity.com/paper/1312.7302/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Dec 2013.

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

- [Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views](https://mlsanity.com/paper/2309.11962/) (2023)
- [VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation](https://mlsanity.com/paper/2210.06028/) (2022)
- [Video-based Human Action Recognition using Deep Learning: A Review](https://mlsanity.com/paper/2208.03775/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Single View Physical Distance Estimation using Human Pose](https://mlsanity.com/paper/2106.10335/) (2021)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Multi-person 3D pose estimation from unlabelled data](https://mlsanity.com/paper/2212.08731/) (2022)
- [Teeth Localization and Lesion Segmentation in CBCT Images using SpatialConfiguration-Net and U-Net](https://mlsanity.com/paper/2312.12189/) (2023)
- [MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection](https://mlsanity.com/paper/2412.01422/) (2024)
- [RT-DEMT: A hybrid real-time acupoint detection model combining mamba and transformer](https://mlsanity.com/paper/2502.11179/) (2025)
- [Hybrid model for Single-Stage Multi-Person Pose Estimation](https://mlsanity.com/paper/2305.01167/) (2023)

## Abstract (arXiv)

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained human pose estimation is one of the hardest problems in computer vision, and our new architecture and learning schema shows significant improvement over the current state-of-the-art results. The main contribution of this paper is showing, for the first time, that a specific variation of deep learning is able to outperform all existing traditional architectures on this task. The paper also discusses several lessons learned while researching alternatives, most notably, that it is possible to learn strong low-level feature detectors on features that might even just cover a few pixels in the image. Higher-level spatial models improve somewhat the overall result, but to a much lesser extent then expected. Many researchers previously argued that the kinematic structure and top-down information is crucial for this domain, but with our purely bottom up, and weak spatial model, we could improve other more complicated architectures that currently produce the best results. This mirrors what many other researchers, like those in the speech recognition, object recognition, and other domains have experienced.