# GateAttentionPose: Enhancing Pose Estimation with Agent Attention and Improved Gated Convolutions

Source: [GateAttentionPose: Enhancing Pose Estimation with Agent Attention and Improved Gated Convolutions](<https://www.sota2.com/research/paper/68fa74cd1e209131cea63f42>)

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

Data updated: 2025-10-26T03:18:28.201Z

Authors: Liang Feng, Zhixuan Shen, Lihua Wen, Shiyao Li, Ming Xu

Published: 2024-09-12T07:04:26.000Z

## Abstract

This paper introduces GateAttentionPose, an innovative approach that enhances the UniRepLKNet architecture for pose estimation tasks. We present two key contributions: the Agent Attention module and the Gate-Enhanced Feedforward Block (GEFB). The Agent Attention module replaces large kernel convolutions, significantly improving computational efficiency while preserving global context modeling. The GEFB augments feature extraction and processing capabilities, particularly in complex scenes. Extensive evaluations on COCO and MPII datasets demonstrate that GateAttentionPose outperforms existing state-of-the-art methods, including the original UniRepLKNet, achieving superior or comparable results with improved efficiency. Our approach offers a robust solution for pose estimation across diverse applications, including autonomous driving, human motion capture, and virtual reality.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2409.07798>)

[PDF](<https://arxiv.org/pdf/2409.07798.pdf>)