Joint Temporal Pooling for Improving Skeleton-based Action Recognition
Publication Name
2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023
Abstract
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+D120 and PKU-MMD datasets.
Open Access Status
This publication is not available as open access
First Page
403
Last Page
410