no code implementations • ICML 2020 • Ning Xu, Yun-Peng Liu, Jun Shu, Xin Geng
Label distribution covers a certain number of labels, representing the degree to which each label describes the instance.
no code implementations • 18 Sep 2020 • Jiaqi Lv, Tianran Wu, Chenglun Peng, Yun-Peng Liu, Ning Xu, Xin Geng
In this paper, we present a compact learning (CL) framework to embed the features and labels simultaneously and with mutual guidance.
no code implementations • 17 Nov 2017 • Tianci Liu, Zelin Shi, Yun-Peng Liu
In this natural geometry-aware way, any metric on the Grassmann manifold can be resided in our model theoreti-cally.