TSW-FD: A Novel Temporal and Spatial Domain Weight Analysis of Feature Difference for Micro-Expression Spotting

Zhihao Zhang, Fan Mo, Ke Zhao, Tong Chen, Xiaolan Fu · Journal of Physics Conference Series · 2021

Abstract The micro-expression spotting has recently attracted increasing attention from psychology and computer vision community, since embraced in the second facial Micro-Expression Grand Challenge (MEGC 2019). Different from the original feature difference (FD) analysis, in this paper, we proposed a novel temporal and spatial domain weight analysis of feature difference (TSW-FD) to achieve micro-expression spotting. The experimental results showed that TSW-FD improved 17.86% and 24.21% in F1-Score comparing to the FD in CASME II and SMIC-E-HS.

Read the paper · More papers on PaperTik