“…In addition, we also conduct experiments on three small video re-ID datasets. On these datasets, we compare with twenty state-of-the-art methods, including VR [48], DVR [52], DVDL [65], STFV3D [49], AFDA [51], LFDA [17], STFV3D+KISSME [66], PaMM [55], TDL [54], SIIDL [53], RFA [38], RNN [31], RNN+OF [31], RCN+KISSME [32], CNN+BRNN [37], ASTPN [35], CNN+XQDA [33], CNN+SRM+TAM [34], CAR [36] and QAN [39]. Among the compared approaches, the first ten approaches use hand-crafted features and the left are deep learning based models.…”