# HeadPosr: End-to-end Trainable Head Pose Estimation using Transformer Encoders

arXiv: https://arxiv.org/abs/2202.03548 · HTML: https://mlsanity.com/paper/2202.03548/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 7 Feb 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [Fine-Grained Head Pose Estimation Without Keypoints](https://mlsanity.com/paper/1710.00925/) (2017)
- [HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation](https://mlsanity.com/paper/2004.00060/) (2020)
- [HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition](https://mlsanity.com/paper/1603.01249/) (2016)
- [WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose](https://mlsanity.com/paper/2005.10353/) (2020)
- [A Vector-based Representation to Enhance Head Pose Estimation](https://mlsanity.com/paper/2010.07184/) (2020)
- [End-to-End Trainable Multi-Instance Pose Estimation with Transformers](https://mlsanity.com/paper/2103.12115/) (2021)
- [Centroid Transformers: Learning to Abstract with Attention](https://mlsanity.com/paper/2102.08606/) (2021)
- [KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors](https://mlsanity.com/paper/1702.05085/) (2017)
- [Res3ATN -- Deep 3D Residual Attention Network for Hand Gesture Recognition in Videos](https://mlsanity.com/paper/2001.01083/) (2020)
- [Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment](https://mlsanity.com/paper/1905.08609/) (2019)

## Built on by (most cited first, 1 of 1)

- [Ocular-Induced Abnormal Head Posture: Diagnosis and Missing Data Imputation](https://mlsanity.com/paper/2510.05649/) (2025)

## Abstract (arXiv)

In this paper, HeadPosr is proposed to predict the head poses using a single RGB image. textitHeadPosr uses a novel architecture which includes a transformer encoder. In concrete, it consists of: (1) backbone; (2) connector; (3) transformer encoder; (4) prediction head. The significance of using a transformer encoder for HPE is studied. An extensive ablation study is performed on varying the (1) number of encoders; (2) number of heads; (3) different position embeddings; (4) different activations; (5) input channel size, in a transformer used in HeadPosr. Further studies on using: (1) different backbones, (2) using different learning rates are also shown. The elaborated experiments and ablations studies are conducted using three different open-source widely used datasets for HPE, i.e., 300W-LP, AFLW2000, and BIWI datasets. Experiments illustrate that textitHeadPosr outperforms all the state-of-art methods including both the landmark-free and the others based on using landmark or depth estimation on the AFLW2000 dataset and BIWI datasets when trained with 300W-LP. It also outperforms when averaging the results from the compared datasets, hence setting a benchmark for the problem of HPE, also demonstrating the effectiveness of using transformers over the state-of-the-art.