In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame equally. However, in an action sequence, only a few segments of frames carry discriminative information related to the action. This paper presents a novel Joint Motion Adaptive Temporal Pooling (JMAP) method for improving skeleton-based action recognition. Two variants of JMAP, frame-wise pooling and joint-wise pooling, are introduced. The efficacy of JMAP has been validated through experiments on the popular NTU RGB+D 120 and PKU-MMD datasets.
@article{arxiv.2408.09356,
title = {Joint Temporal Pooling for Improving Skeleton-based Action Recognition},
author = {Shanaka Ramesh Gunasekara and Wanqing Li and Jack Yang and Philip Ogunbona},
journal= {arXiv preprint arXiv:2408.09356},
year = {2024}
}