Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing redundant temporal information and achieving fine-grained perception because they only focus on processing low-resolution features. To address these challenges, we propose a novel multi-scale resolution framework that encodes spatio-temporal representations at varying granularities and executes fine-grained perception compensation. Furthermore, we employ a density peaks clustering method to dynamically identify and prioritize tokens that offer important semantic information. This strategy effectively prunes redundant feature tokens, especially those arising from multi-frame features, thereby optimizing computational efficiency without sacrificing semantic richness. Empirically, it sets new benchmarks for both performance and efficiency on three large-scale datasets. Our method achieves a 93.8% improvement in inference speed compared to the baseline, while also enhancing pose estimation accuracy, reaching 87.4 mAP on the PoseTrack2017 dataset.
@article{arxiv.2503.05365,
title = {Multi-Grained Feature Pruning for Video-Based Human Pose Estimation},
author = {Zhigang Wang and Shaojing Fan and Zhenguang Liu and Zheqi Wu and Sifan Wu and Yingying Jiao},
journal= {arXiv preprint arXiv:2503.05365},
year = {2025}
}