GaitSCM: Causal representation learning for gait recognition

Wei Huo, Ke Wang, Jun Tang, Nian Wang, Dong Liang

Abstract: Highlights•A novel causal representation learning framework GaitSCM for gait recognition is proposed.•A causal analysis based on SCM reveals the spurious relation in gait recognition.•Feature decoupling and backdoor adjustment are used to perform causal intervention.•GaitSCM achieves competitive results on the CASIA-B and OU-MVLP datasets.