Progressive Feature Learning for Realistic Cloth-Changing Gait Recognition

arXiv:2207.11720v2 Announce Type: replace-cross
Abstract: Gait recognition is instrumental in crime prevention and social security, for it can be conducted at a long distance to figure out the identity of persons. However, existing datasets and methods cannot satisfactorily deal with the most challenging cloth-changing problem in practice. Specifically, the practical gait models are usually trained on automatically labeled data, in which the sequences' views and cloth conditions of each person have some restrictions. To be concrete, the cross-view sub-dataset only …

abstract arxiv crime crime prevention cs.cv cs.lg datasets deal feature figure however identity long distance practical practice prevention recognition security social type