GMFL-Net: A Global Multi-geometric Feature Learning Network for Repetitive Action Counting

TL;DR

GMFL-Net introduces a multi-geometric feature fusion approach for more accurate repetitive action counting, overcoming pose instability issues caused by viewpoint changes, and is validated on a new dataset with state-of-the-art results.

Contribution

The paper proposes GMFL-Net with novel modules for multi-geometric feature fusion and global feature enhancement, and introduces a new annotated dataset for repetitive action counting.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effectively handles pose distortions due to viewpoint changes.

Outperforms existing methods in accuracy and robustness.

Abstract

With the continuous development of deep learning, the field of repetitive action counting is gradually gaining notice from many researchers. Extraction of pose keypoints using human pose estimation networks is proven to be an effective pose-level method. However, existing pose-level methods suffer from the shortcomings that the single coordinate is not stable enough to handle action distortions due to changes in camera viewpoints, thus failing to accurately identify salient poses, and is vulnerable to misdetection during the transition from the exception to the actual action. To overcome these problems, we propose a simple but efficient Global Multi-geometric Feature Learning Network (GMFL-Net). Specifically, we design a MIA-Module that aims to improve information representation by fusing multi-geometric features, and learning the semantic similarity among the input multi-geometric features. Then, to improve the feature representation from a global perspective, we also design a GBFL-Module that enhances the inter-dependencies between point-wise and channel-wise elements and combines them with the rich local information generated by the MIA-Module to synthesise a comprehensive and most representative global feature representation. In addition, considering the insufficient existing dataset, we collect a new dataset called Countix-Fitness-pose (https://github.com/Wantong66/Countix-Fitness) which contains different cycle lengths and exceptions, a test set with longer duration, and annotate it with fine-grained annotations at the pose-level. We also add two new action classes, namely lunge and rope push-down. Finally, extensive experiments on the challenging RepCount-pose, UCFRep-pose, and Countix-Fitness-pose benchmarks show that our proposed GMFL-Net achieves state-of-the-art performance.