# PE-former: Pose Estimation Transformer

Source: [PE-former: Pose Estimation Transformer](<https://www.sota2.com/research/paper/68fa6b611e209131cea2dde7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:13:04.664Z

Authors: Paschalis Panteleris, Antonis Argyros

Published: 2021-12-09T15:20:23.000Z

## Abstract

Vision transformer architectures have been demonstrated to work very effectively for image classification tasks. Efforts to solve more challenging vision tasks with transformers rely on convolutional backbones for feature extraction. In this paper we investigate the use of a pure transformer architecture (i.e., one with no CNN backbone) for the problem of 2D body pose estimation. We evaluate two ViT architectures on the COCO dataset. We demonstrate that using an encoder-decoder transformer architecture yields state of the art results on this estimation problem.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [2D Human Pose Estimation on COCO 2017 (val)](<https://www.sota2.com/research/sota/2d-human-pose-estimation-on-coco-2017-val.md>): 2D Human Pose Estimation; COCO 2017 (val); AP: 72.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2112.04981>)

[PDF](<https://arxiv.org/pdf/2112.04981.pdf>)

[Implementation](<https://github.com/padeler/PE-former>)