223 citations · 226 across the 2 of their papers we have counts for
2 papers
cs.CV2016★ 3 cited
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
Jun Liu, Amir Shahroudy, Dong Xu +1
3D action recognition - analysis of human actions based on 3D skeleton data - becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recen…
cs.LG2012★ 223 cited
Learning with Augmented Features for Heterogeneous Domain Adaptation
Lixin Duan, Dong Xu, Ivor Tsang
We propose a new learning method for heterogeneous domain adaptation (HDA), in which the data from the source domain and the target domain are represented by heterogeneous features…