AI RESEARCH
SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition
arXiv CS.CV
•
ArXi:2606.03160v1 Announce Type: new Recognizing human actions from point cloud sequences is critical for 3D perception driven applications such as autonomous driving and human-computer interaction. However, the irregular structure and temporal inconsistency of point clouds pose unique challenges for spatio-temporal representation learning, especially in capturing both global motion context and fine-grained temporal dynamics.