English

Temporal Scale and Shift Invariant Automatic Event Recognition using the Mellin Transform

Computer Vision and Pattern Recognition 2025-02-17 v1

Abstract

The Spatio-temporal holographic correlator combines the traditional 2D optical image correlation techniques with inhomogeneously broadened arrays of cold atoms to achieve 3D time-space correlation to realize automatic event recognition at an ultra-high speed. Here we propose a method to realize such event recognition for videos running at different speeds. With this method, we can highly improve recognition accuracy and filter almost all the unwanted events in the video database.

Keywords

Cite

@article{arxiv.2502.09939,
  title  = {Temporal Scale and Shift Invariant Automatic Event Recognition using the Mellin Transform},
  author = {Xi Shen and Julian Gamboa and Tabassom Hamidfar and Shamima A. Mitu and Selim M. Shahriar},
  journal= {arXiv preprint arXiv:2502.09939},
  year   = {2025}
}
R2 v1 2026-06-28T21:44:05.604Z