mlsanityData to 7 Oct 2026

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

arXiv 2409.07798 ↗First posted 12 Sep 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 27 references that are in the map. First posted on arXiv 12 Sep 2024.

Builds on

22 of 27 references.

References · 22

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  6. 2016Language Modeling with Gated Convolutional Networkscited by 688
  7. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  8. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  9. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  10. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  11. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  12. 2020TransPose: Keypoint Localization via Transformercited by 126
10 more
  1. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
  2. 2021Pose Recognition with Cascade Transformerscited by 99
  3. 2023Agent Attention: On the Integration of Softmax and Linear Attentioncited by 90
  4. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  5. 2023UniHCP: A Unified Model for Human-Centric Perceptionscited by 59
  6. 2023Learning to Upsample by Learning to Samplecited by 57
  7. 2024GLACE: Global Local Accelerated Coordinate Encodingcited by 48
  8. 2023Human Pose as Compositional Tokenscited by 45
  9. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  10. 2023Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguitycited by 13

Built on by

Not cited yet.