KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition

TL;DR

This paper introduces KAN-HyperpointNet, a novel architecture for 3D human action recognition from point cloud sequences that effectively captures both micro-movements and macro-structures, achieving state-of-the-art results.

Contribution

The paper proposes D-Hyperpoint and a new network architecture integrating Kolmogorov-Arnold Networks to improve spatio-temporal modeling of human actions in point cloud sequences.

Findings

Achieves state-of-the-art accuracy on MSR Action3D dataset.

Outperforms existing methods on NTU-RGB+D 60 dataset.

Effectively balances micro-movement and macro-structure information.

Abstract

Point cloud sequence-based 3D action recognition has achieved impressive performance and efficiency. However, existing point cloud sequence modeling methods cannot adequately balance the precision of limb micro-movements with the integrity of posture macro-structure, leading to the loss of crucial information cues in action inference. To overcome this limitation, we introduce D-Hyperpoint, a novel data type generated through a D-Hyperpoint Embedding module. D-Hyperpoint encapsulates both regional-momentary motion and global-static posture, effectively summarizing the unit human action at each moment. In addition, we present a D-Hyperpoint KANsMixer module, which is recursively applied to nested groupings of D-Hyperpoints to learn the action discrimination information and creatively integrates Kolmogorov-Arnold Networks (KAN) to enhance spatio-temporal interaction within D-Hyperpoints. Finally, we propose KAN-HyperpointNet, a spatio-temporal decoupled network architecture for 3D action recognition. Extensive experiments on two public datasets: MSR Action3D and NTU-RGB+D 60, demonstrate the state-of-the-art performance of our method.