“…We collect 3D human shapes from some public datasets and manually label the genders, such as SCAPE [23], SHREC 2007 [24], TOSCA [25], AdobeData [26], Statistical Model [27], SHREC 2014 [28], SHREC 2015 [28]- [30], Breuckmann BodyScan [31], MoSh [32], MPI FAUST [33], SPRING [34], Dyna [35], MPII CAESAR [36], MPI D-FAUST [37], and DUTH [38], which are mainly aimed at registration, correspondence and other applications. The constructed 3D Human Shapes Gender Recognition Dataset (3D-HSRD for short) consists of more than one hundred thousand shapes with various appearances and postures for evaluation of the proposed method.…”